Julian Scott Yeomans

Recently, small modular reactors (SMRs) have received greater interest as a source for clean and affordable district heating (DH). Compared to power plants, the low-pressure, low-temperature design and nearly 100 % efficiency reduce the cost of produced energy considerably. However, few practical implementations exist yet, and cost estimates and design principles are subject to uncertainties whose interactions remain largely unknown. In this work, we present a techno-economic optimization and sensitivity analysis of a natural circulation DH SMR primary heat exchanger. A Cuckoo Search variant augmented with a modified Hooke-Jeeves search was used as the optimizer, with SimDec (simulation decomposition) subsequently employed for global sensitivity analysis. The reactor pressure vessel and containment vessel specific costs exhibited the greatest impact on the cost of heat and the optimized configurations. While low-pressure, low-temperature design is central to heating reactor cost-effectiveness, optimized primary circuit temperatures clearly exceeded previous assumptions. In a 5260 full-load hours mid-load application, a 34–41 €/MWh cost range was found for produced heat at 8 % interest and 20-year lifetime. For heat exchanger optimization, the results indicate the potential for considerable performance improvement from using deterministic local search for terminal convergence and sensitivity analysis for dimensionality reduction.

Computational modeling is frequently incorporated into environmental decision-making in order to capture inherently complex relationships and system dynamics. The complexity of such models often lies in various heterogeneous effects that arise due to the interaction of different input factors or due to designed structural variation in the model. In the past, various sensitivity analysis approaches have been implemented in attempts to identify essential decision factors. However, existing sensitivity analysis methods fail to capture critical information in the presence of heterogeneous effects. In this paper, the recently introduced simulation decomposition (SimDec) visualization method is extended to include quantitative sensitivity analysis. The framework is tested on several decision-making problems and is shown to capture heterogeneous behavior. A formal definition and classification of heterogeneous effects for computational models is introduced. The framework is open-sourced in a variety of scientific programming languages.

“Real world” risk analysis in environmental contexts frequently requires the need to contrast numerous uncertain factors simultaneously and to communicate difficult-to-capture interactions. Monte Carlo simulation modelling of complex environmental sytems is frequently employed to integrate uncertain inputs and to construct probability distributions of the resulting outputs. Visual analytics and data visualization can then be employed for the processing, analyzing, and communicating of the influence of any multi-variable uncertainties on the system. The simulation decomposition (SimDec) analytical technique has recently been employed in the complex assessments of environmental systems. SimDec has proved to be beneficial in revealing interdependencies in complex models, lowering computational burdens, facilitating decision-maker perceptions, and especially, making analytical components visualizable. It has been demonstrated that many analytical findings would not have been revealed without the coloured visualizations provided by SimDec. However, an ad hoc colouring scheme of the distribution output is neither sufficient nor capable of producing much of the key visualizable information requisite for an effective SimDec analysis. Instead, an approach that has recently been referred to as an intelligent colouring has been proposed. This paper outlines, highlights, and demonstrates the importance of and best-practices in an intelligent colouring scheme needed for an effective SimDec analysis of complex environmental systems.

This paper contributes to the existing stock market anomaly literature by being the first to analyze the benefits of combining two distinct anomalies; specifically, the low-volatility and mean-reversion anomalies. Our results show that on a long-only basis, these two time-varying anomalies could be combined into a double-sort investment strategy that includes some desirable characteristics from each of them, thereby making the portfolio return accumulation more stable over time. As the added-value of low-volatility investing stems mostly from the risk-reduction side, while contrarian stocks are generally highly volatile with remarkable upside potential, the use of the double-sort portfolio-formation in which the contrarian stocks are picked from the sub-set of below-median volatility stocks can shorten the below-market performance periods that have occasionally materialized for plain low-volatility or plain contrarian investors.

Urban planning often involves decision-making under highly uncertain circumstances. System dynamics and multi-agent modeling frameworks are commonly employed to model the social phenomena in this type of urban planning. However, because the outputs from these approaches are regularly characterized as a function of time, the majority of studies in this modeling domain lack appropriate sensitivity analysis. Consequently, important insights into model behavior are frequently overlooked. Monte Carlo simulation has been used to incorporate uncertain features in urban planning with the outputs displayed as probability distributions. Recently simulation decomposition (SimDec) has been used to enhance the visualization of the cause-effect relationships of multi-variable combinations of inputs on the corresponding simulated outputs. SimDec maps each output value of a Monte Carlo simulation on to the multivariable groups of inputs or scenarios from which it originated. By visually projecting the subdivided scenarios onto the overall output, SimDec can reveal previously unidentified influences between the various combinations of inputs on to the outputs. SimDec can be generalized to any Monte Carlo method with insignificant computational overhead and is, therefore, extendable to any simulated urban planning analysis. This study demonstrates the efficacy of adapting SimDec for the sensitivity analysis of urban dynamics modeling on a paradigmatic simplified version of Forrester’s Urban Dynamics- URBAN1 model. SimDec reveals complexities in model behavior that are not, and can not be, captured by standard sensitivity analysis methods and highlights, in particular, the intricate joint effect of immigration and outmigration on system development.

In “real life” decision-making situations, inevitably, there are numerous unmodelled components, not incorporated into the underlying mathematical programming models, that hold substantial influence on the overall acceptability of the solutions calculated. Under such circumstances, it is frequently beneficial to produce a set of dissimilar–yet “good”–alternatives that contribute very different perspectives to the original problems. The approach for creating maximally different solutions is known as modelling-to-generate alternatives (MGA). Recently, a data structure that permits MGA using any population-based solution procedure has been formulated that can efficiently construct sets of maximally different solution alternatives. This new approach permits the production of an overall best solution together with n locally optimal, maximally different alternatives in a single computational run. The efficacy of this novel computational approach is tested on four benchmark optimization problems.

We introduce a new return-momentum indicator that is based on monotonicity of monthly-return rank order within a lookback period (henceforth abbreviated as MRRO). Based on an extensive post-cost performance comparison of long-only momentum portfolios formed on six stand-alone and 36 double-sort criteria across three holding period lengths in the non-microcap universe of U.S. stocks over the 55-year sample period, MRRO is particularly useful for annual holding periods, towards the end of whom the conventional return-momentum indicators tend to lose their prediction power. Based on the return-based style analysis, MRRO adds some favorable style-diversification characteristics into long-only momentum portfolio selection.

Corporate strategic decisions are often supported by evaluation with real options framework. However, the majority of real options studies choose to analyze generic types of real
options. In this extended abstract, we demonstrate how customized real options can be systematically discovered by employing a recently developed approach called Simulation Decomposition or SimDec. SimDec is an enhancement of Monte Carlo simulation, which allows tracing how different input factors and their interactions affect the outcome(s) while preserving the holistic picture of the overall uncertainty. We show the application of SimDec to the two cases of corporate strategic decisionmaking: 1. Investment strategy and 2. Compliance with emissions regulations. Both cases demonstrate that SimDec reveals previously hidden interactions of factors in a model and provides actionable outcome by discovering optionality in strategic decisions

In interconnected environmental systems, the innocuous failure of one component can sometimes trigger a subsequent domino-like effect resulting in a cascading collapse of the entire system. Risk analysis in “real world” contexts frequently requires the need to simultaneously contrast numerous uncertain factors and difficult-to-capture dimensions. Monte Carlo simulation modelling has often been employed to integrate uncertain inputs and to construct probability distributions of the resulting outputs. Visual analytics and data visualization can be used to support the processing, analyzing, and communicating of the influence of multi-variable uncertainties on the decision-making process. In this paper, the novel Simulation Decomposition (SimDec) analytical technique is extended into complex assessments of cascading risk analysis and used to quantitatively examine situations involving potentially catastrophic, domino-like collapses of an entire system. SimDec analysis proves to be beneficial due to its ability to reveal interdependencies in complex models, its ease of decision-maker perception, its visualizable analytic capabilities, and its significantly lower computational burdens. The case example visually demonstrates that when a system collapse is a low-probability/high-impact event, more expensive, reactive policies minimize the overall value loss under conditions of system survival, while more proactive policies enable better loss prevention under system survival. However, proactive approaches significantly decrease the likelihoods and magnitudes of losses for scenarios resulting from the collapse of the system. Such findings would not have been revealed without the visualization provided by SimDec.

This issue contains applied computational analytics papers that either create new methods or provide innovative applications of existing methods to assist with sustainability analysis and environmental decision-making applications. In practice, environmental analytics is an integra-tion of science, methods, and techniques that involves a combination of computers, computational intelligence, information technology, mathematical modelling, and system science to assess re-al-world, sustainability, and environmental problems. The contributions to this issue all inves-tigate novel approaches of computational analytics – modelling, computational solution proce-dures, optimization, simulation, and technologies—as applied to sustainability analysis. The papers emphasize both the practical relevance and the methodological contributions of the work to environmental decision-making. Areas of application encompass a wide spectrum of environ-mental decision-making and sustainability, from waste, water, energy, climate change, industrial ecology, resource recovery, to recycling.

Computational decision-making in “real world” environmental and sustainability contexts frequently requires the need to contrast numerous uncertain factors and difficult-to-capture dimensions. Monte Carlo simulation modelling has frequently been employed to integrate the uncertain inputs and to construct probability distributions of the resulting outputs. Visual analytics and data visualization can be used to support the processing, analyzing, and communicating of the influence of multi-variable uncertainties on the decision-making process. In this paper, the novel Simulation Decomposition (SimDec) analytical technique is used to quantitatively examine carbon emission impacts resulting from a transformation of the aviation industry toward a state of greater airline electrification. SimDec is used to decompose a Monte Carlo model of the flying range of all-electric aircraft based upon improvements to batteries and motor efficiencies. Since SimDec can be run concurrently with any Monte Carlo model with only negligible additional overhead, it can easily be extended into the analysis of any environmental application that employs simulation. This generalizability in conjunction with its straightforward visualizations of complex stochastic uncertainties makes the practical contributions of SimDec very powerful in environmental decision-making.

Monte Carlo (MC) simulation is widely used in many different disciplines in order to analyze problems that involve uncertainty. Simulation decomposition has recently provided a simple, but powerful, advancement to the standard Monte Carlo approach. Its value for better informing decision making has been previously shown in the investment-analysis field. In this paper, we demonstrate that simulation decomposition can enhance problem analysis in a wide array of domains by applying it to three very different disciplines: geology, business, and environmental science. Further extensions to such disciplines as engineering, natural sciences, and social sciences are discussed. We propose that by incorporating simulation decomposition into pedagogical practices, we expect students to significantly advance their problem-understanding and problem-solving skills.

As a result of increasing urban intensification, civic planners have devoted additional resources to more sustainability-focused logistics planning. Electric vehicles have proved to be both a lower cost alternative and more environmentally friendly than the more ubiquitous internal combustion engine vehicles. However, the predominant decision-making approaches employed by businesses and municipalities are not necessarily computationally conducive for the optimization and evaluation of urban transportation systems involving electric vehicles. An innovative modelling and planning approach is proposed to enable urban planners to more readily evaluate the contribution of electric vehicles in city logistics and to support the decision-making process. Specifically, this paper provides a multicriteria modelling-to-generate-alternatives (MGA) decision-support procedure that employs the Bat Algorithm (BA) metaheuristic for generating sets of alternatives for electric vehicle planning in urban transshipment problems. The efficacy of this multicriteria, BA-driven MGA approach for creating planning alternatives is demonstrated on an urban transshipment problem involving electric trucks.

Environmental sustainability problems frequently require the need for decision-making in situations containing considerable uncertainty. Monte Carlo simulation methods have been used in a wide array of environmental planning settings to incorporate these uncertain features. Simulation-generated outputs are commonly displayed as probability distributions. Recently simulation decomposition (SD) has enhanced the visualization of the cause-effect relationships of multi-variable combinations of inputs on the corresponding simulated outputs. SD partitions sub-distributions of the Monte Carlo outputs by pre-classifying selected input variables into states, grouping combinations of these states into scenarios, and then collecting simulated outputs attributable to each multi-variable input scenario. Since it is a straightforward task to visually project the contribution of the subdivided scenarios onto the overall output, SD can illuminate previously unidentified connections between the multi-variable combinations of inputs on the outputs. SD is generalizable to any Monte Carlo method with negligible additional computational overhead and, therefore, can be readily extended into most environmental analyses that use simulation models. This study demonstrates the efficacy of SD for environmental sustainability decision-making on a carbon footprint analysis case for wooden pallets.

Increasing urban intensification has caused civic planners to devote additional resources to more appropriate logistics planning. Electric vehicles have proved to be both a lower cost alternative and more environmentally friendly than the more ubiquitous internal combustion engine vehicles. However, prevailing decision-making formulations employed by municipalities and businesses are not necessarily computationally conducive for the evaluation and optimization of urban transportation systems using electric vehicles. An innovative computational approach, the range limited routing problem, is introduced that enables urban planners to more readily evaluate the contributions of electric vehicles to the city logistics decision-making process. While there is no generalized solution technique for solving this new formulation, this paper employs the Firefly Algorithm (FA) metaheuristic to solve the range limited routing problem using electric trucks.

Decision-making in the “real world” can become dominated by inconsistent performance requirements and incompatible specifications that can be difficult to detect when supporting mathematical programming models are formulated. There are invariably unmodelled elements, not apparent during model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, it can frequently prove beneficial to construct a set of options that provide dissimilar approaches to such problems. These alternatives should possess near-optimal objective measures with respect to all known objectives, but be maximally different from each other in terms of their decision variables. The approach for creating maximally different sets of solutions is referred to as modelling-to-generate-alternatives (MGA). This article provides an efficient biologically-inspired algorithm that can generate sets of maximally different alternatives by employing the Firefly Algorithm metaheuristic. The computational efficacy of this MGA approach is demonstrated on a commonly-tested benchmark problem.

While solving waste management (WM) planning problems, it may often be preferable to generate several quantifiably good options that provide multiple, contrasting perspectives. This is because WM planning generally contains complex problems that are riddled with inconsistent performance objectives and contain design requirements that are very difficult to quantify and capture when supporting decision models must be constructed. The generated alternatives should satisfy all of the stated system conditions, but be maximally different from each other in the requisite decision space. The process for creating maximally different sets of solutions is referred to as modelling-to-generate-alternatives (MGA). Simulation-optimization approaches have frequently been used to solve computationally difficult, stochastic WM problems. This paper outlines a stochastic multicriteria MGA approach for WM planning that can generate sets of maximally different alternatives for any simulation-optimization method that employs a population-based solution algorithm. This algorithmic approach is computationally efficient because it simultaneously produces the prescribed number of maximally different solution alternatives in a single computational run of the procedure. The efficacy of this stochastic MGA method is demonstrated on a “real world” waste management facility expansion case.

Various components within environmental decision-making problems often contain considerable uncertainty. Monte Carlo simulation approaches have frequently been used to incorporate a wide array of this uncertainty into environmental planning. Simulated outputs summarizing these uncertainties are commonly portrayed in the form of probability distributions. Visualization of the disparate uncertainties within these distributions is a key aspect for effective decision support in Monte Carlo analysis. This study contrasts the performance and benefits of two visual analytics tools – overlay charts and simulation decomposition. Overlay charts enable the display of multiple sources of uncertainty overlaid on top of each other in a single graphical representation and come as a standard feature in numerous commercial Monte Carlo software packages. Conversely, simulation decomposition combines user-defined sub-distributions of the simulation uncertainties and collectively displays them in a combined graphical output figure. This paper contrasts the efficacy of overlay charts versus simulation decomposition for the visual analysis uncertainty into the environmental decision-making process.

When solving complex water resources management (WRM) problems, it is often preferable to construct a number of quantifiably good alternatives that provide multiple, different perspectives. This is because WRM normally involves multifaceted problems that are riddled with incompatible performance objectives and contain inconsistent design requirements which are very difficult to quantify and capture when supporting decisions must be constructed. These alternatives need to satisfy the required system performance criteria and yet be maximally different from each other in the decision space. The approach for creating maximally different sets of solutions is referred to as modelling-to-generate-alternatives (MGA). Simulationoptimization approaches are frequently employed to solve computationally difficult problems containing significant stochastic uncertainties. This paper outlines an MGA approach for WRM that can generate sets of maximally different alternatives for any simulation-optimization method that employs a population-based search algorithm. This algorithmic approach is both computationally efficient and simultaneously produces the prescribed number of maximally different solution alternatives in a single computational run of the procedure. The effectiveness of this stochastic MGA approach for creating alternatives in “real world”, water policy formulation is demonstrated using a WRM case study

When resolving waste management (WM) planning problems, it is often preferable to construct a number of quantifiably good alternatives that provide multiple, disparate perspectives. This is because solid waste planning generally involves complicated problems that are riddled with incompatible performance objectives and contain inconsistent design requirements that are very difficult to quantify and capture when supporting decision models must be constructed. These potential alternatives need to satisfy the required system performance criteria and yet be maximally different from each other in the decision space. The approach for creating maximally different sets of solutions is referred to as modelling-to-generate-alternatives (MGA). Simulation-optimization approaches have frequently been employed to solve computationally difficult problems containing the significant stochastic uncertainties in waste management. This paper outlines a multicriteria MGA approach for WM planning that can generate sets of maximally different alternatives for any simulation-optimization method that employs a population-based solution algorithm. This algorithmic approach is computationally efficient because it simultaneously produces the prescribed number of maximally different solution alternatives in a single computational run of the procedure. The efficacy of this stochastic MGA approach for creating alternatives is demonstrated using a “real world” waste management planning case.

Environmental decision-making commonly involves multifaceted problems that demonstrate considerable uncertainty. Monte Carlo simulation approaches have been employed in a variety of environmental planning venues to address these uncertain aspects. Simulation-based outputs are frequently presented in the form of probability distributions. Recently an approach referred to as simulation decomposition (SD) has been introduced that extends the analysis of Monte Carlo results by enhancing the explanatory power of the cause-effect relationships between the multi-variable combinations of inputs and the simulated outputs. SD constructs sub-distributions of the simulation output by pre-classifying some of the uncertain input variables into states, clustering the various combinations of these different states into scenarios, and then collecting simulated outputs attributable to each multi-variable input scenario. Since the contribution of subdivided scenarios to the overall output is easily portrayed visually, SD can highlight and disclose previously unidentified connections between the multi-variable combinations of inputs on the outputs. An SD approach is generalizable to any Monte Carlo model with negligible additional computational overhead and, hence, can be readily used for environmental analyses that employ simulation models. This study illustrates the efficacy of SD in environmental analysis using a carbon capture and storage project from China.

Complex stochastic engineering problems are frequently inundated with incompatible performance requirements and inconsistent performance specifications that can be difficult to identify when supporting decision models must be constructed. Consequently, it is often advantageous to create a set of dissimilar options that afford distinctive approaches to the problem. These alternatives should satisfy the required system performance criteria and yet be maximally different from each other in their decision spaces. The approach for creating such maximally different solution sets is referred to as modelling-to-generate-alternatives (MGA). This paper describes a dual-criterion stochastic MGA procedure that can generate sets of maximally different alternatives for any simulation-optimization approach that employs a population-based search algorithm. This stochastic algorithmic approach is both computationally efficient and simultaneously produces the prescribed number of maximally different solution alternatives in a single computational run of the procedure.

While solving difficult stochastic engineering problems, it is often desirable to generate several quantifiably good options that provide contrasting perspectives. These alternatives should satisfy all of the stated system conditions, but be maximally different from each other in the requisite decision space. The process of creating maximally different solution sets has been referred to as modelling-to-generate-alternatives (MGA). Simulation-optimization has frequently been used to solve computationally difficult, stochastic problems. This paper applies an MGA method that can create sets of maximally different alternatives for any simulation-optimization approach that employs a population-based algorithm. This algorithmic approach is both computationally efficient and simultaneously produces the prescribed number of maximally different solution alternatives in a single computational run of the procedure. The efficacy of this stochastic MGA method is demonstrated on a waste management facility expansion case.

While solving waste management (WM) planning problems, it may often be preferable to generate several quantifiably good options that provide multiple, contrasting perspectives. This is because WM planning generally contains complex problems that are riddled with inconsistent performance objectives and contain design requirements that are very difficult to quantify and capture when supporting decision models must be constructed. The generated alternatives should satisfy all of the stated system conditions, but be maximally different from each other in the requisite decision space. The process for creating maximally different sets of solutions is referred to as modelling-to-generate-alternatives (MGA). Simulation-optimization approaches have frequently been used to solve computationally difficult, stochastic WM problems. This paper outlines a stochastic multicriteria MGA approach for WM planning that can generate sets of maximally different alternatives for any simulation-optimization method that employs a population-based solution algorithm. This algorithmic approach is computationally efficient because it simultaneously produces the prescribed number of maximally different solution alternatives in a single computational run of the procedure. The efficacy of this stochastic MGA method is demonstrated on a “real world” waste management facility expansion case.

Stochastic systems are often overwhelmed by incompatible performance requirements and inconsistent performance specifications that can be difficult to identify when supporting decision models must be constructed. Consequently, it is often advantageous to create a set of dissimilar options that afford distinctive approaches to the problem. These alternatives should satisfy the required system performance criteria and yet be maximally different from each other in their decision spaces. This paper describes a stochastic bicriteria procedure that can generate sets of maximally different alternatives. This stochastic algorithmic approach is both computationally efficient and simultaneously produces the prescribed number of maximally different solution alternatives in a single computational run of the procedure.

When solving complex stochastic engineering problems, it can prove preferable to create numerous quantifiably good alternatives that provide multiple, disparate perspectives. These alternatives need to satisfy the required system performance criteria and yet be maximally different from each other in the decision space. The approach for creating maximally different sets of solutions is referred to as modelling-togenerate-alternatives (MGA). Simulation-optimization approaches are frequently employed to solve computationally difficult problems containing significant stochastic uncertainties. This paper outlines an MGA algorithm that can generate sets of maximally different alternatives for any simulation-optimization method that employs a population-based procedure. This algorithmic approach is both computationally efficient and simultaneously produces the prescribed number of maximally different solution alternatives in a single computational run of the procedure

Complex problems are frequently overwhelmed by inconsistent performance requirements and incompatible specifications that can be difficult to identify at the time of problem formulation. Consequently, it is often beneficial to construct a set of different options that provide distinct approaches to the problem. These alternatives need to be close-to-optimal with respect to the specified objective(s), but be maximally different from each other in the solution domain. The approach for creating maximally different solution sets is referred to as modelling-to-generate-alternatives (MGA). This paper introduces a computationally efficient, population-based multicriteria MGA algorithm for generating sets of maximally different alternatives.

Stochastic optimization problems are often overwhelmed with inconsistent performance requirements and incompatible performance specifications that can be difficult to detect during problem formulation. Therefore, it can prove beneficial to create a set of dissimilar options that provide divergent perspectives to the problem. These alternatives should be near-optimal with respect to the specified objective(s), but be maximally different from each other in the decision region. The approach for creating maximally different sets of solutions is referred to as modelling-to-generate-alternatives (MGA). Simulationoptimization approaches are commonly employed to solve computationally difficult problems containing significant stochastic uncertainties. This paper provides a new, stochastic, multicriteria MGA approach that can generate sets of maximally different alternatives for any simulation-optimization method that employs a population-based algorithm.

Complex problems are frequently inundated with incompatible performance requirements and inconsistent performance specifications that can be difficult – if not impossible – to identify at the time of problem formulation. Consequently, it is often advantageous to create a set of dissimilar options that provide distinct approaches to the problem. These disparate alternatives need to be close-to-optimal with respect to the specified objective(s), but remain maximally different from each other in the decision domain. The approach for creating such maximally different solution sets is referred to as modelling-to-generate-alternatives (MGA). This paper provides a new, bicriterion MGA approach that can generate sets of maximally different alternatives using any population-based algorithm.

As a consequence of urban intensification, logistics planning becomes more important than ever. Electric vehicles have proved to be both environmentally friendly and a lower-cost alternative to internal combustion engine vehicles. However, existing decision methods employed by businesses and municipalities are not universally conducive to the optimization and evaluation of urban transportation systems. An innovative model and planning approach is proposed to enable urban planners to more readily evaluate the contribution of electric vehicles in city logistics and to support the decision-making process. When faced with decision-making situations that involve multiple and inconsistent performance objectives, it is often preferable to consider several quantifiably good alternatives that provide various, very different perspectives. This paper provides a modeling-to-generate-alternatives (MGA) decision-support procedure that uses the firefly algorithm (FA) metaheuristic for generating sets of maximally different alternatives for electric vehicle planning in urban transshipment problems.

This paper compares the efficacy of both traditional valuation ratios and an extensive set of related combination criteria in identifying the future best-performing stocks for a comprehensive U.S. sample over the period 1971–2013. Value portfolios formed on different criteria have remarkably different exposures to style factors. We find evidence of strong relative efficacy of three enterprise value multiples (EBIT/EV, EBITDA/EV, and S/EV). Particularly, the evidence for the unique characteristics of S/EV contributes to the existing literature. The defensive characteristic of high dividend yield is pervasive both as a stand-alone criterion and as a combination sub-criterion.

“Real world” applications tend to contain complex performance specifications riddled with contradictory performance elements. This state arises because policymaking naturally involves multifaceted problems that are riddled with competing performance objectives and contain incompatible design requirements which are very problematic – if not impossible – to capture at the time that the requisite decision models are constructed. There are invariably unmodelled components, not readily apparent during model formulation, which could greatly impact the suitability of the model’s solutions. Consequently, it proves preferable to generate a number of dissimilar alternatives that provide multiple, distinct perspectives to the problem. These different options should all possess close-to-optimal measures with respect to the specified objective(s), but be maximally different from each other in the decision space. These maximally different solution construction approaches have been referred to as modelling-to-generate-alternatives (MGA). This study provides a procedure that simultaneously generates multiple, maximally different alternatives by employing the metaheuristic, Firefly Algorithm. The efficacy of this efficient algorithmic optimization approach is demonstrated on a commonly-tested engineering benchmark problem.

This paper compares the efficacy of four multicriteria decision-making (MCDM) methods in identifying the future best-performing stocks in two comprehensive samples of U.S. stocks. This is the first time that median-scaling (MS), the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS), the Analytic Hierarchy Process (AHP), and the additive Data Envelopment Analysis (add.DEA) have been used to combine value and momentum indicators into a single efficiency score. The results show that the MCDM methods examined can successfully be applied to equity portfolio selection. As a robustness check, we repeat all the main sample tests for the sample of the largest-cap stocks included in the two biggest size quintiles (i.e., stocks above 40% NYSE market-cap breakpoint) and find that the overall results are surprisingly robust to size effect. However, the best-performing portfolios formed on the basis of different MCDM methods have remarkably different exposures to the style factors that are commonly used to explain the abnormal returns of active equity portfolios. As a practical implication of this study, investors following certain investing styles could take these different style exposures into account when choosing the MCDM criteria that best fit their portfolio-selection purposes.

This study provides new evidence on anomaly interactions, as well as on the cross-section of returns in all-but-microcap universe of U.S. stocks over the 42-year sample period from 1971 to 2013. The five anomalies being examined are size, value, profitability, investment/asset growth, and momentum. We form 5×5 conditional double-sort portfolios for each pair of anomaly variables, resulting in 20 different 5×5 sorts when using each variable in the first-stage sorting and the remaining four in the second-stage sorting. The interrelation between each pair of anomaly variables is evaluated on the basis of the monotonic relation (MR) test of Patton and Timmermann (2010) for portfolio raw returns, and in addition, by means of the Sharpe ratio comparisons. Moreover, we run Fama-MacBeth (1973) cross-sectional regressions to compare the relative explanatory power of each variable in the presence of the others. The results show that investment/asset growth and momentum dimensions capture the cross-sectional return patterns better than size, value, or profitability. The relative efficacy of momentum is higher in all-but-microcap universe than previously documented for the corresponding unlimited market-cap samples of U.S. stocks.

“Real-world” decision-making applications generally contain multifaceted performance requirements riddled with incongruent performance specifications. This is because decision making typically involves complex problems that are riddled with incompatible performance objectives and contain competing design requirements which are very difficult—if not impossible—to capture and quantify at the time that the supporting decision models are actually constructed. There are invariably unmodelled elements, not apparent during model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, it is preferable to generate several distinct alternatives that provide multiple disparate perspectives to the problem. These alternatives should possess near-optimal objective measures with respect to all known objective(s), but be maximally different from each other in terms of their decision variables. This maximally different solution creation approach is referred to as modelling-to-generate-alternatives (MGA). This chapter provides an efficient optimization algorithm that simultaneously generates multiple, maximally different alternatives by employing the metaheuristic firefly algorithm. The efficacy of this mathematical programming approach is demonstrated on a commonly tested engineering optimization benchmark problem.

“Real world” problems typically possess complex performance conditions peppered with inconsistent performance requirements. This situation occurs because multifaceted problems are often riddled with incompatible performance objectives and contradictory design requirements which can be difficult – if not impossible – to specify when the requisite decision models are formulated. Thus, it is often desirable to generate a set of disparate alternatives that provide diverse approaches to the problem. These dissimilar options should be close-to-optimal with respect to any specified objective(s), but remain maximally different from all other solutions in the decision space. The approach for creating maximally different sets of solutions is referred to as modelling-to-generate-alternatives (MGA). This paper outlines an MGA algorithmic approach that can simultaneously generate a set of maximally different alternatives using any population-based metaheuristic.

Environmental policy formulation can prove complicated when the various system components contain considerable degrees of stochastic uncertainty. In addition, there are invariably unmodelled issues, not apparent at the time a model is constructed, that can greatly impact the acceptability of its solutions. While a mathematically optimal solution may be the best solution for the modelled problem, it is frequently not the best solution for the real problem. Consequently, it is generally preferable to create several good alternatives that provide different approaches and perspectives to the same problem. This study shows how a computationally efficient simulation-optimization (SO) approach that combines evolutionary optimization with simulation can be used to generate multiple policy alternatives that satisfy required system criteria and are maximally different in decision space. The efficacy of this stochastic modelling-to-generate-alternatives approach is demonstrated on a waste management planning case. Since SO techniques can be adapted to model a wide variety of problem types in which system components are stochastic, the practicality of this approach can be extended into many other operational and strategic planning applications containing significant sources of uncertainty.

Decision-making in the “real world” involves complex problems that tend to be riddled with competing performance objectives and possess requirements which are very difficult to incorporate into any underlying decision support models. There are invariably unmodelled elements, not apparent during model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, it is preferable to generate numerous dissimilar alternatives that provide disparate perspectives to the problem. These alternatives should possess near-optimal objective measures with respect to all known objectives, but be maximally different from each other in terms of their decision variables. This maximally different solution creation approach is referred to as modelling-to-generate-alternatives (MGA). This article provides an efficient biologically-inspired algorithm that simultaneously generates multiple, maximally different alternatives by employing the Firefly Algorithm metaheuristic. The effectiveness of this algorithm is demonstrated on an engineering optimization benchmark test problem

In solving many “real world” engineering optimization applications, it is generally preferable to formulate several quantifiably good alternatives that provide distinct perspectives to the particular problem. This is because decision-making typically involves complex problems that are riddled with incompatible performance objectives and contain competing design requirements which are very difficult – if not impossible – to capture and quantify at the time that the supporting mathematical programming models are actually constructed. There are invariably unmodelled design issues, not apparent at the time of model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, it is preferable to generate several, distinct alternatives that provide multiple, disparate perspectives to the problem. These alternatives should possess nearoptimal objective measures with respect to all known modelled objective(s), but be fundamentally different from each other in terms of their decision variables. This solution approach is referred to as modelling to generatealternatives (MGA). This paper provides an efficient computational procedure for simultaneously generating multiple different alternatives to optimal solutions that employs the Firefly Algorithm. The efficacy of this approach will be illustrated using a well-known engineering optimization benchmark problem.

In solving many practical mathematical programming applications, it is generally preferable to formulate several quantifiably good alternatives that provide very different approaches to the particular problem. This is because decisionmaking typically involves complex problems that are riddled with incompatible performance objectives and possess competing design requirements which are very difficult – if not impossible – to quantify and capture at the time that the supporting decision models are constructed. There are invariably unmodelled design issues, not apparent at the time of model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, it is preferable to generate several alternatives that provide multiple, disparate perspectives to the problem. These alternatives should possess near-optimal objective measures with respect to all known modelled objective(s), but be fundamentally different from each other in terms of the system structures characterized by their decision variables. This solution approach is referred to as modelling to generate-alternatives (MGA). This paper provides a biologically-inspired simulationoptimization MGA approach that uses the Firefly Algorithm to efficiently create multiple solution alternatives to stochastic problems that satisfy required system performance criteria and yet remain maximally different in their decision spaces. The efficacy of this stochastic MGA method is demonstrated using a waste facility expansion case study.

When solving “real world” optimization applications, it is generally preferable to formulate several quantifiably good alternatives that provide distinct perspectives to the particular problem. This is because decision-making typically involves complex problems that are riddled with incompatible performance objectives and contain competing design requirements which are very difficult – if not impossible – to capture and quantify at the time that the supporting decision models are actually constructed. There are invariably unmodelled design issues, not apparent at the time of model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, it is preferable to generate several, distinct alternatives that provide multiple, disparate perspectives to the problem. These alternatives should possess nearoptimal objective measures with respect to all known modelled objective(s), but be fundamentally different from each other in terms of their decision variables. This solution approach is referred to as modelling to generate-alternatives (MGA). This paper provides an efficient optimization algorithm that simultaneously generates multiple, maximally different alternatives by employing the metaheuristic, Firefly Algorithm. The efficacy of this mathematical programming approach is demonstrated on a commonly-tested engineering optimization benchmark problem

An evolutionary nature-inspired Firefly Algorithm (FA) is employed to set the optimal osmotic dehydration parameters in a case study of papaya. In the case, the functional form of the dehydration model is established via a response surface technique with the resulting optimization formulation being a non-linear goal programming model. For optimization, a computationally efficient, FA-driven method is employed and the resulting solution is shown to be superior to those from previous approaches for determining the osmotic process parameters. The final component of this study provides a computational experimentation performed on the FA to illustrate the relative sensitivity of this evolutionary metaheuristic approach over a range of the two key parameters that most influence its running time-the number of iterations and the number of fireflies. This sensitivity analysis revealed that for intermediateto-high values of either of these two key parameters, the FA would always determine overall optimal solutions, while lower values of either parameter would generate greater variability in solution quality. Since the running time complexity of the FA is polynomial in the number of fireflies but linear in the number of iterations, this experimentation shows that it is more computationally practical to run the FA using a “reasonably small” number of fireflies together with a relatively larger number of iterations than the converse.

In solving many “real world” decision-making applications, it is generally preferable to formulate several quantifiably good alternatives that provide numerous, distinct approaches to the problem. This is because policy formulation typically involves complex problems that are riddled with incongruent performance objectives and possess incompatible design requirements that can be very difficult – if not impossible – to incorporate at the time supporting decision models are constructed. By generating a set of maximally different solutions, it is believed that some of the dissimilar alternatives will provide unique perspectives that serve to satisfy the unmodelled characteristics. This maximally different solution creation approach is referred to as modelling-to-generate-alternatives (MGA). This paper provides a stochastic biologically-inspired metaheuristic simulation-optimization MGA method that can efficiently create multiple solution alternatives to problems containing significant stochastic uncertainties that satisfy required system performance criteria and yet are maximally different in their decision spaces. The efficacy of this stochastic MGA approach is demonstrated on a municipal solid waste case study. It is shown that this new computationally efficient algorithmic approach can simultaneously produce the desired number of maximally different solution alternatives in a single computational run of the procedure.

The Firefly Algorithm (FA) metaheuristic is employed to determine the optimal parameter settings in a case study of the osmotic dehydration of mushrooms. In the case, the functional form of the dehydration model is established through a response surface technique and the resulting mathematical programming is formulated as a non-linear goal programming model. For optimization purposes, a computationally efficient, FA-driven method is used and the resulting optimal process parameters are shown to be superior to those from previous approaches.

In solving many practical mathematical programming applications, it is generally preferable to formulate several quantifiably good alternatives that provide distinct perspectives to the particular problem. This is because decision-making typically involves complex problems that are riddled with incompatible performance objectives and contain competing design requirements which are very difficult – if not impossible – to capture and quantify at the time that the supporting decision models are actually constructed. There are invariably unmodelled design issues, not apparent at the time of model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, it is preferable to generate several, distinct alternatives that provide multiple, disparate perspectives to the problem. These alternatives should possess near-optimal objective measures with respect to all known modelled objective(s), but be fundamentally different from each other in terms of their decision variables. This solution approach is referred to as modelling to generate-alternatives (MGA). This paper provides an efficient computational procedure for simultaneously generating multiple different alternatives to optimal solutions that employs the Firefly Algorithm. The efficacy of this approach will be illustrated using a well-known engineering optimization benchmark problem.

The Firefly Algorithm (FA) is employed to determine the optimal parameter settings in a case study of the osmotic dehydration process of mushrooms. In the case, the functional form of the dehydration model is established through a response surface technique and the resulting mathematical programming is formulated as a non-linear goal programming model. For optimization purposes, a computationally efficient, FA-driven method is used and the resulting optimal process parameters are shown to be superior to those from previous approaches.

In solving many environmental policy formulation applications, it is generally preferable to formulate several quantifiably good alternatives that provide multiple, disparate approaches to the problem. This is because environmental decision-making typically involves complex problems that are riddled with incompatible performance objectives and possess competing design requirements which are very difficult – if not impossible – to quantify and capture at the time when supporting decision models must be constructed. By generating a set of maximally different solutions, it is hoped that some of the dissimilar alternatives can provide very different perspectives that may serve to satisfy the unmodelled objectives. This maximally different solution creation approach is referred to as modelling to generate-alternatives (MGA). This paper provides a biologically-inspired metaheuristic simulation-optimisation MGA method that can efficiently create multiple solution alternatives to environmental problems containing significant stochastic uncertainties that satisfy required system performance criteria and yet are maximally different in their decision spaces. The efficacy of this stochastic MGA approach for environmental policy formulation is demonstrated using a municipal solid waste case study. It is shown that this new computationally efficient algorithmic approach can simultaneously produce the desired number of maximally different solution alternatives in a single computational run of the procedure.

In solving complex water resources management (WRM) problems, it can prove preferable to create numerous quantifiably good alternatives that provide multiple, disparate perspectives. This is because WRM normally involves multifaceted problems that are riddled with incompatible performance objectives and contain inconsistent design requirements, which are very difficult to quantify and capture when supporting decisions must be constructed. By producing a set of options that are maximally different from each other in terms of their unmodelled variable structures, it is hoped that some of these dissimilar solutions may convey very different perspectives that may serve to address these unmodelled objectives. In environmental planning, this maximally different option production procedure is referred to as modelling-to-generate-alternatives (MGA). In addition, many components of WRM problems possess extensive stochastic uncertainty. This study provides a firefly algorithm-driven simulation-optimization approach for MGA that can be used to efficiently create multiple solution alternatives to problems containing significant stochastic uncertainties that satisfy required system performance criteria and yet are maximally different in their decision spaces. This algorithmic approach is both computationally efficient and simultaneously produces a prescribed number of maximally different solution alternatives in a single computational run of the procedure. The effectiveness of this stochastic MGA approach for creating alternatives in “real world”, environmental policy formulation is demonstrated using a WRM case study.

This study employs a Firefly Algorithm (FA) to determine the optimal osmotic dehydration parameters for papaya. The functional form of the osmotic dehydration model is established via a standard response surface technique. The format of the resulting optimization model to be solved is a non-linear goal programming problem. While various alternate solution approaches are possible, an FA-driven procedure is employed. For optimization purposes, it has been demonstrated that the FA is more computationally efficient than other such commonly-used metaheuristics as genetic algorithms, simulated annealing, and enhanced particle swarm optimization. Hence, the FA approach is a very computationally efficient procedure. It can be shown that the resulting solution determined for the osmotic process parameters is superior to those from all previous approaches.

This study uses the Firefly Algorithm (FA) for computing process drying parameters for agricultural produce dehydration. In a case study of mushroom dehydration, the functional form of the dehydration model is approximated using a response surface technique and the resulting optimization model is a non-linear goal programming problem. While various alternate calculational approaches are possible, an FA-driven procedure is implemented for computing the solution. For optimization purposes, it has been demonstrated that the FA is more computationally efficient than other such commonly-used metaheuristics as genetic algorithms, simulated annealing, and enhanced particle swarm optimization. Hence, the FA approach is a very computationally efficient procedure. It can be shown that the resulting solution computed for the dehydration process parameters is superior to those from all previous approaches.

The Firefly Algorithm (FA) is employed to determine the optimal parameter settings in a case study of the osmotic dehydration process of mushrooms. In the case, the functional form of the dehydration model is established through a response surface technique and the resulting mathematical programming is formulated as a non-linear goal programming model. For optimization purposes, a computationally efficient, FA-driven method is used and the resulting optimal process parameters are shown to be superior to those from previous approaches. The final section of this study provides a computational experimentation performed on the FA to analyze its relative sensitivity over a range of the two key parameters that most influence its running time.

Many municipal solid waste management decision-making applications contain considerable elements of stochastic uncertainty. Simulation-optimisation techniques can be adapted to model a wide variety of problem types in which system components are stochastic. The family of optimisation methods referred to as simulation-optimisation incorporate stochastic uncertainties expressed as probability distributions directly into their computational procedures. In this paper, a new simulation-optimisation approach is presented that implements a modified version of the computationally efficient, nature-inspired firefly algorithm (FA). The effectiveness of this stochastic FA-driven simulation-optimisation procedure for optimisation is demonstrated using a municipal solid waste management case study.

This study employs a Firefly Algorithm (FA) to determine the optimal osmotic dehydration parameters for papaya. The functional form of the osmotic dehydration model is established via a standard response surface technique. The format of the resulting optimization model to be solved is a non-linear goal programming problem. While various alternate solution approaches are possible, an FA-driven procedure is employed. For optimization purposes, it has been demonstrated that the FA is more computationally efficient than other such commonly-used metaheuristics as genetic algorithms, simulated annealing, and enhanced particle swarm optimization. Hence, the FA approach is a very computationally efficient procedure. It can be shown that the resulting solution determined for the osmotic process parameters is superior to those from all previous approaches

In solving many “real world” decision-making applications, it is generally preferable to formulate several quantifiably good alternatives that provide numerous, distinct approaches to the problem. This is because policy formulation typically involves complex problems that are riddled with incongruent performance objectives and possess incompatible design requirements that can be very difficult – if not impossible – to incorporate at the time supporting decision models are constructed. By generating a set of maximally different solutions, it is believed that some of the dissimilar alternatives will provide unique perspectives that serve to satisfy the unmodelled characteristics. This maximally different solution creation approach is referred to as modelling-to-generate-alternatives (MGA). This paper provides a stochastic biologically-inspired metaheuristic simulation-optimization MGA method that can efficiently create multiple solution alternatives to problems containing significant stochastic uncertainties that satisfy required system performance criteria and yet are maximally different in their decision spaces. The efficacy of this stochastic MGA approach is demonstrated on a municipal solid waste case study. It is shown that this new computationally efficient algorithmic approach can simultaneously produce the desired number of maximally different solution alternatives in a single computational run of the procedure.

In solving many practical mathematical programming applications, it is generally preferable to formulate several quantifiably good alternatives that provide very different approaches to the particular problem. This is because decisionmaking typically involves complex problems that are riddled with incompatible performance objectives and possess competing design requirements which are very difficult – if not impossible – to quantify and capture at the time that the supporting decision models are constructed. There are invariably unmodelled design issues, not apparent at the time of model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, it is preferable to generate several alternatives that provide multiple, disparate perspectives to the problem. These alternatives should possess near-optimal objective measures with respect to all known modelled objective(s), but be fundamentally different from each other in terms of the system structures characterized by their decision variables. This solution approach is referred to as modelling to generate-alternatives (MGA). This paper provides a biologically-inspired simulationoptimization MGA approach that uses the Firefly Algorithm to efficiently create multiple solution alternatives to stochastic problems that satisfy required system performance criteria and yet remain maximally different in their decision spaces. The efficacy of this stochastic MGA method is demonstrated using a waste facility expansion case study.

“Real world” decision-making often involves complex problems that are riddled with incompatible and inconsistent performance objectives. These problems typically possess competing design requirements which are very difficult – if not impossible – to quantify and capture at the time that any supporting decision models are constructed. There are invariably unmodelled design issues, not apparent during the time of model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, when solving many practical mathematical programming applications, it is generally preferable to formulate numerous quantifiably good alternatives that provide very different perspectives to the problem. These alternatives should possess near-optimal objective measures with respect to all known modelled objectives, but be fundamentally different from each other in terms of the system structures characterized by their decision variables. This solution approach is referred to as modelling-to-generate-alternatives (MGA). This study demonstrates how the nature-inspired, Firefly Algorithm can be used to efficiently create multiple solution alternatives that both satisfy required system performance criteria and yet are maximally different in their decision spaces.

Public sector decision-making typically involves complex problems that are riddled with incompatible performance objectives and possess competing design requirements which are very difficult – if not impossible – to quantify and capture when supporting decision models need to be constructed. There are invariably unmodelled design issues, not apparent at the time of model creation, which can greatly impact the acceptability of the solutions proposed by the model. Consequently, it is generally preferable to create several quantifiably good alternatives that provide multiple, disparate perspectives and very different approaches to the particular problem. These alternatives should possess near-optimal objective measures with respect to the known modelled objective(s), but be fundamentally different from each other in terms of the system structures characterized by their decision variables. By generating a set of very different solutions, it is hoped that some of the dissimilar alternatives can provide very different perspectives that may serve to satisfy the unmodelled objectives. This study shows how simulation-optimization (SO) modelling can be combined with niching operators to efficiently generate multiple policy alternatives that satisfy required system performance criteria in stochastically uncertain environments and yet are maximally different in the decision space. This new stochastic approach is very computationally efficient, since it permits the simultaneous generation of good solution alternatives in a single computational run of the SO algorithm. The efficacy and efficiency of this modelling-to-generate-alternatives (MGA) method is specifically demonstrated on a municipal solid waste management facility expansion case.

In solving many practical mathematical programming applications, it is generally preferable to formulate several quantifiably good alternatives that provide very different approaches to the particular problem. This is because decision-making typically involves complex problems that are riddled with incompatible performance objectives and possess competing design requirements which are very difficult—if not impossible—to quantify and capture at the time that the supporting decision models are constructed. There are invariably unmodeled design issues, not apparent at the time of model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, it is preferable to generate several alternatives that provide multiple, disparate perspectives to the problem. These alternatives should possess near-optimal objective measures with respect to all known modeled objective(s) but be fundamentally different from each other in terms of the system structures characterized by their decision variables. This solution approach is referred to as modeling-to-generate-alternatives (MGA). This chapter provides a synopsis of various MGA techniques and demonstrates how biologically inspired MGA algorithms are particularly efficient at creating multiple solution alternatives that both satisfy required system performance criteria and yet are maximally different in their decision spaces. The efficacy and efficiency of these MGA methods are demonstrated using a number of case studies.

Real world” decision-making applications generally contain multifaceted performance requirements riddled with incongruent performance specifications. There are invariably unmodelled elements, not apparent during model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, it is preferable to generate numerous alternatives that provide dissimilar approaches to the problem. These alternatives should possess near-optimal objective measures with respect to all known objectives, but be maximally different from each other in terms of their decision variables. This maximally different solution creation approach is referred to as modelling-to-generate-alternatives MGA. This study demonstrates how the Firefly Algorithm can concurrently create multiple solution alternatives that both satisfy required system performance criteria and yet are maximally different in their decision spaces. This new approach is computationally efficient, since it permits the concurrent generation of multiple, good solution alternatives in a single computational run rather than the multiple implementations required in previous MGA procedures.

In finding solutions to many “real world” engineering optimizationproblems, it is generally desirable to be able to construct several quantifiably good alternatives that provide very different perspectives to the particular problem. This is because complex decision-making situations typically involve problems riddled with incompatible performance objectives and possess competing design requirements that are very difficult – if not impossible – to quantify and capture when the supporting decision models must be formulated. There are invariably unmodelled design issues, not apparent during model construction, which can greatly impact the acceptability of any model’s solutions. Consequently, it is preferable to generate numerous alternatives that provide dissimilar approaches to the problem. These alternatives should possess near-optimal objective measures with respect to all known modelled objective(s), but be fundamentally different from each other in terms of the system structures characterized by their decision variables. This maximally different solution creation approach is referred to as modelling-to-generate-alternatives (MGA). This paper provides an efficient, biologicallyinspired metaheuristic MGA method that can concurrently create multiple solution alternatives that simultaneously satisfy the required system performance criteria and are maximally different in the decision space. The efficacy of this MGA approach is demonstrated on a number of benchmark engineering optimizationproblems

Simulation-Optimisation (SO) techniques, which incorporate inherent system uncertainties using probability distributions, have been used for optimal waste management planning. While SO can be applied to numerous stochastic problems, its solution times vary considerably from one implementation to the next. In this study, SO has been concurrently combined with both penalty functions and a Grey Programming (GP) technique in order to efficiently generate sets of numerous, good policy alternatives – an approach referred to as modelling-to-generate-alternatives. The efficacy of this approach is illustrated on a planning problem for expanding a landfill and municipal waste management facilities.

Public sector decision-making typically involves complex problems that are riddled with competing performance objectives and possess design requirements which are difficult to capture at the time that supporting decision models are constructed. Environmental policy formulation can prove additionally complicated because the various system components often contain considerable stochastic uncertainty and frequently numerous stakeholders exist that hold completely incompatible perspectives. Consequently, there are invariably unmodelled performance design issues, not apparent at the time of the problem formulation, which can greatly impact the acceptability of any proposed solutions. While a mathematically optimal solution might provide the best solution to a modelled problem, normally this will not be the best solution to the underlying real problem. Therefore, in public environmental policy formulation, it is generally preferable to be able to create several quantifiably good alternatives that provide very different approaches and perspectives to the problem. This study shows how a computationally efficient simulation-driven optimization approach that combines evolutionary optimization with simulation can be used to generate multiple policy alternatives that satisfy required system criteria and are maximally different in decision space. The efficacy of this modelling-to-generate-alternatives method is specifically demonstrated on a municipal solid waste management facility expansion case.

Public sector decision-making typically involves complex problems that are riddled with competing performance objectives and possess design requirements which are difficult to quantify and capture at the time supporting decision models are constructed. Environmental policy formulation can prove additionally complicated because the various system components often contain considerable degrees of stochastic uncertainty. Furthermore, there are frequently numerous stakeholders with incompatible perspectives. Consequently, there are invariably unmodelled performance design issues, not apparent at the time of the construction of a decision support model, which can greatly impact the acceptability of its solutions. While a mathematically optimal solution may be the best solution to the modelled problem, it is frequently not the best solution to the real, underlying problem. Therefore, in public environmental policy formulation, it is generally preferable to create several quantifiably good alternatives that provide very different approaches to the problem. By generating a diverse set of solutions, it is hoped that some of these dissimilar alternatives can provide very different perspectives that may serve to satisfy the unmodelled objectives. This study shows how simulation-optimization (SO) modelling can be used to efficiently generate multiple policy alternatives that satisfy required system performance criteria in stochastically uncertain environments and yet are maximally different in the decision space. This new approach is very computationally efficient, since, in addition to finding the best solution to the problem, it permits the simultaneous generation of multiple, good solution alternatives in a single computational run of the SO algorithm rather than the multiple implementations required in other modelling-to-generate-alternatives procedures. The efficacy of this approach is specifically demonstrated using a previously studied waste management case from the Municipality of Hamilton-Wentworth, Ontario.

Public environmental policy formulation can prove complicated when the various system components contain considerable elements of stochastic uncertainty. Invariably, there are unmodelled issues, not captured or apparent at the time a model is constructed, that can greatly impact the acceptability of its solutions. While a mathematically optimal solution may be the best solution to the modelled problem, it is frequently not the best solution for the underlying real problem. Consequently, it is generally preferable to create several good alternatives that provide very different approaches and perspectives to the same problem. This study shows how a computationally efficient simulation-driven optimization (SDO) approach that combines evolutionary optimization with simulation can be used to generate multiple policy alternatives that satisfy required system criteria and are maximally different in decision space. The efficacy of this stochastic modelling-to-generate-alternatives approach is demonstrated on a waste management planning case. Since SDO techniques can be adapted to model a wide variety of problem types in which system components are stochastic, the practicality of this approach can be extended into many other application areas containing significant sources of uncertainty.

Public sector decision-making typically involves complex problems that are riddled with incompatible performance objectives and possess competing design requirements which are very difficult-if not impossible-to quantify and capture when supporting decision models need to be constructed. There are invariably unmodelled design issues, not apparent at the time of model creation, which can greatly impact the acceptability of the solutions proposed by the model. Consequently, it is generally preferable to create several quantifiably good alternatives that provide multiple, disparate perspectives and very different approaches to the particular problem. These alternatives should possess near-optimal objective measures with respect to the known modelled objectives, but be fundamentally different from each other in terms of the system structures characterized by their decision variables. By generating a set of very different solutions, it is hoped that some of the dissimilar alternatives can provide very different perspectives that may serve to satisfy the unmodelled objectives. This study shows how simulation-optimization SO modelling can be combined with niching operators to efficiently generate multiple policy alternatives that satisfy required system performance criteria in stochastically uncertain environments and yet are maximally different in the decision space. This new stochastic approach is very computationally efficient, since it permits the simultaneous generation of good solution alternatives in a single computational run of the SO algorithm. The efficacy and efficiency of this modelling-to-generate-alternatives MGA method is specifically demonstrated on a municipal solid waste management facility expansion case.

The Toronto District School Board (TDSB) oversees the largest school district in Canada and has been spent more than one third of its annual maintenance budget on energy and waste. This has directed attention toward system-wide reductions to both energy consumption patterns and waste generation rates. In this paper, a decision support system (DSS) that can process unit-incompatible measures is used for rating, ranking, and benchmarking the schools within the TDSB. Results: The DSS permits the ranking of any set of schools by contextually evaluating their relative attractiveness to other identified school groupings. Consequently, the DSS was used to explicitly rank each school’s performance within the district and to determine realistic energy improvement targets. Achieving these benchmarks would reduce system-wide energy costs by twenty-five percent. Conclusions: The TDSB study demonstrates that this DSS provides an extremely useful approach for evaluating, benchmarking and ranking the relative energy and waste performance within the school system, and the potential to extend its much broader applicability into other applications clearly warrants additional exploration.

“Real world” decision-making often involves complex problems that are riddled with incompatible and inconsistent performance objectives. These problems typically possess competing design requirements which are very difficult — if not impossible — to quantify and capture at the time that any supporting decision models are constructed. There are invariably unmodelled design issues, not apparent at the time of model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, when solving many practical mathematical programming applications, it is generally preferable to formulate numerous quantifiably good alternatives that provide very different perspectives to the problem. These alternatives should possess near-optimal objective measures with respect to all known modelled objective(s), but be fundamentally different from each other in terms of the system structures characterized by their decision variables. This solution approach is referred to as modelling-to-generate-alternatives (MGA). This study demonstrates how the biologically-inspired, Firefly Algorithm can be used to efficiently create multiple solution alternatives that both satisfy required system performance criteria and yet are maximally different in their decision spaces.

In solving many practical mathematical programming applications, it is preferable to formulate numerous quantifiably good alternatives that provide very different perspectives to the problem. This is because decision-making typically involves complex problems that are riddled with incompatible and inconsistent performance objectives and possess competing design requirements which are very difficult – if not impossible – to quantify and capture at the time that the supporting decision models are constructed. There are invariably unmodelled design issues, not apparent at the time of model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, it is preferable to generate several alternatives that provide multiple, disparate perspectives to the problem. These alternatives should possess near-optimal objective measures with respect to all known modelled objective(s), but be fundamentally different from each other in terms of the system structures characterized by their decision variables. This solution approach is referred to as modelling-to-generatealternatives (MGA). This study demonstrates how the biologically-inspired, Firefly algorithm can be used to efficiently create multiple solution alternatives that both satisfy required system performance criteria and yet are maximally different in their decision spaces

Engineering optimization problems usually contain multifaceted performance requirements that can be riddled with unquantifiable specifications and incompatible performance objectives. Such problems typically possess competing design requirements which are very difficult – if not impossible – to quantify and capture at the time of model formulation. There are invariably unmodelled design issues, not apparent at the time of model construction, which can greatly impact the acceptability of the model’s solutions. Consequently, when solving many “real life” mathematical programming applications, it is generally preferable to formulate several quantifiably good alternatives that provide very different perspectives to the problem. These alternatives should possess near-optimal objective measures with respect to all known modelled objective(s), but be fundamentally different from each other in terms of the system structures characterized by their decision variables. This solution approach is referred to as modelling-to-generate-alternatives (MGA). This study demonstrates how the nature-inspired, Firefly Algorithm can be used to concurrently create multiple solution alternatives that both satisfy required system performance criteria and yet are maximally different in their decision spaces. This new co-evolutionary approach is very computationally efficient, since it permits the concurrent generation of multiple, good solution alternatives in a single computational run rather than the multiple implementations required in previous MGA procedures.