In real-world optimisation, it is common to face several sub-problems interacting and forming the main problem. There is an inter-dependency between the sub-problems, making it impossible to solve such a problem by focusing on only one component. The travelling thief problem (TTP) belongs to this category and is formed by the integration of the travelling salesperson problem (TSP) and the knapsack problem (KP). In this paper, we investigate the inter-dependency of the TSP and the KP by means of quality diversity (QD) approaches. QD algorithms provide a powerful tool not only to obtain high-quality solutions but also to illustrate the distribution of high-performing solutions in the behavioural space. We introduce a multi-dimensional archive of phenotypic elites (MAP-Elites) based evolutionary algorithm using well-known TSP and KP search operators, taking the TSP and KP score as the behavioural descriptor. MAP-Elites algorithms are QD-based techniques to explore high-performing solutions in a behavioural space. Afterwards, we conduct comprehensive experimental studies that show the usefulness of using the QD approach applied to the TTP. First, we provide insights regarding high-quality TTP solutions in the TSP/KP behavioural space. Afterwards, we show that better solutions for the TTP can be obtained by using our QD approach, and it can improve the best-known solution for a number of TTP instances used for benchmarking in the literature.
{"title":"On the Use of Quality Diversity Algorithms for the Travelling Thief Problem","authors":"Adel Nikfarjam, Aneta Neumann, Frank Neumann","doi":"10.1145/3641109","DOIUrl":"https://doi.org/10.1145/3641109","url":null,"abstract":"In real-world optimisation, it is common to face several sub-problems interacting and forming the main problem. There is an inter-dependency between the sub-problems, making it impossible to solve such a problem by focusing on only one component. The travelling thief problem (TTP) belongs to this category and is formed by the integration of the travelling salesperson problem (TSP) and the knapsack problem (KP). In this paper, we investigate the inter-dependency of the TSP and the KP by means of quality diversity (QD) approaches. QD algorithms provide a powerful tool not only to obtain high-quality solutions but also to illustrate the distribution of high-performing solutions in the behavioural space. We introduce a multi-dimensional archive of phenotypic elites (MAP-Elites) based evolutionary algorithm using well-known TSP and KP search operators, taking the TSP and KP score as the behavioural descriptor. MAP-Elites algorithms are QD-based techniques to explore high-performing solutions in a behavioural space. Afterwards, we conduct comprehensive experimental studies that show the usefulness of using the QD approach applied to the TTP. First, we provide insights regarding high-quality TTP solutions in the TSP/KP behavioural space. Afterwards, we show that better solutions for the TTP can be obtained by using our QD approach, and it can improve the best-known solution for a number of TTP instances used for benchmarking in the literature.","PeriodicalId":220659,"journal":{"name":"ACM Transactions on Evolutionary Learning","volume":" July","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139617893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xunfeng Wu, Qiuzhen Lin, Junwei Zhou, Songbai Liu, C. C. Coello Coello, Victor C. M. Leung
In recent years, surrogate-assisted evolutionary algorithms (SAEAs) have been sufficiently studied for tackling computationally expensive multiobjective optimization problems (EMOPs), as they can quickly estimate the qualities of solutions by using surrogate models to substitute for expensive evaluations. However, most existing SAEAs only show promising performance for solving EMOPs with no more than 10 dimensions, and become less efficient for tackling EMOPs with higher dimensionality. Thus, this article proposes a new SAEA with a simplified helper task for tackling high-dimensional EMOPs. In each generation, one simplified task will be generated artificially by using random dimension reduction on the target task (i.e., the target EMOPs). Then, two surrogate models are trained for the helper task and the target task, respectively. Based on the trained surrogate models, evolutionary multitasking optimization is run to solve these two tasks, so that the experiences of solving the helper task can be transferred to speed up the convergence of tackling the target task. Moreover, an effective model management strategy is designed to select new promising samples for training the surrogate models. When compared to five competitive SAEAs on four well-known benchmark suites, the experiments validate the advantages of the proposed algorithm on most test cases.
{"title":"Evolutionary Optimization with Simplified Helper Task for High-dimensional Expensive Multiobjective Problems","authors":"Xunfeng Wu, Qiuzhen Lin, Junwei Zhou, Songbai Liu, C. C. Coello Coello, Victor C. M. Leung","doi":"10.1145/3637065","DOIUrl":"https://doi.org/10.1145/3637065","url":null,"abstract":"In recent years, surrogate-assisted evolutionary algorithms (SAEAs) have been sufficiently studied for tackling computationally expensive multiobjective optimization problems (EMOPs), as they can quickly estimate the qualities of solutions by using surrogate models to substitute for expensive evaluations. However, most existing SAEAs only show promising performance for solving EMOPs with no more than 10 dimensions, and become less efficient for tackling EMOPs with higher dimensionality. Thus, this article proposes a new SAEA with a simplified helper task for tackling high-dimensional EMOPs. In each generation, one simplified task will be generated artificially by using random dimension reduction on the target task (i.e., the target EMOPs). Then, two surrogate models are trained for the helper task and the target task, respectively. Based on the trained surrogate models, evolutionary multitasking optimization is run to solve these two tasks, so that the experiences of solving the helper task can be transferred to speed up the convergence of tackling the target task. Moreover, an effective model management strategy is designed to select new promising samples for training the surrogate models. When compared to five competitive SAEAs on four well-known benchmark suites, the experiments validate the advantages of the proposed algorithm on most test cases.","PeriodicalId":220659,"journal":{"name":"ACM Transactions on Evolutionary Learning","volume":" 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139625366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Florian Karl, Tobias Pielok, Julia Moosbauer, Florian Pfisterer, Stefan Coors, Martin Binder, Lennart Schneider, Janek Thomas, Jakob Richter, Michel Lang, E.C. Garrido-Merchán, Juergen Branke, B. Bischl
Hyperparameter optimization constitutes a large part of typical modern machine learning workflows. This arises from the fact that machine learning methods and corresponding preprocessing steps often only yield optimal performance when hyperparameters are properly tuned. But in many applications, we are not only interested in optimizing ML pipelines solely for predictive accuracy; additional metrics or constraints must be considered when determining an optimal configuration, resulting in a multi-objective optimization problem. This is often neglected in practice, due to a lack of knowledge and readily available software implementations for multi-objective hyperparameter optimization. In this work, we introduce the reader to the basics of multi-objective hyperparameter optimization and motivate its usefulness in applied ML. Furthermore, we provide an extensive survey of existing optimization strategies, both from the domain of evolutionary algorithms and Bayesian optimization. We illustrate the utility of MOO in several specific ML applications, considering objectives such as operating conditions, prediction time, sparseness, fairness, interpretability and robustness.
{"title":"Multi-Objective Hyperparameter Optimization in Machine Learning – An Overview","authors":"Florian Karl, Tobias Pielok, Julia Moosbauer, Florian Pfisterer, Stefan Coors, Martin Binder, Lennart Schneider, Janek Thomas, Jakob Richter, Michel Lang, E.C. Garrido-Merchán, Juergen Branke, B. Bischl","doi":"10.1145/3610536","DOIUrl":"https://doi.org/10.1145/3610536","url":null,"abstract":"Hyperparameter optimization constitutes a large part of typical modern machine learning workflows. This arises from the fact that machine learning methods and corresponding preprocessing steps often only yield optimal performance when hyperparameters are properly tuned. But in many applications, we are not only interested in optimizing ML pipelines solely for predictive accuracy; additional metrics or constraints must be considered when determining an optimal configuration, resulting in a multi-objective optimization problem. This is often neglected in practice, due to a lack of knowledge and readily available software implementations for multi-objective hyperparameter optimization. In this work, we introduce the reader to the basics of multi-objective hyperparameter optimization and motivate its usefulness in applied ML. Furthermore, we provide an extensive survey of existing optimization strategies, both from the domain of evolutionary algorithms and Bayesian optimization. We illustrate the utility of MOO in several specific ML applications, considering objectives such as operating conditions, prediction time, sparseness, fairness, interpretability and robustness.","PeriodicalId":220659,"journal":{"name":"ACM Transactions on Evolutionary Learning","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132483005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The feature attribution-based explanation (FAE) methods, which indicate how much each input feature contributes to the model’s output for a given data point, are one of the most popular categories of explainable machine learning techniques. Although various metrics have been proposed to evaluate the explanation quality, no single metric could capture different aspects of the explanations. Different conclusions might be drawn using different metrics. Moreover, during the processes of generating explanations, existing FAE methods either do not consider any evaluation metric or only consider the faithfulness of the explanation, failing to consider multiple metrics simultaneously. To address this issue, we formulate the problem of creating FAE explainable models as a multi-objective learning problem that considers multiple explanation quality metrics simultaneously. We first reveal conflicts between various explanation quality metrics, including faithfulness, sensitivity, and complexity. Then, we define the considered multi-objective explanation problem and propose a multi-objective feature attribution explanation (MOFAE) framework to address this newly defined problem. Subsequently, we instantiate the framework by simultaneously considering the explanation’s faithfulness, sensitivity, and complexity. Experimental results comparing with six state-of-the-art FAE methods on eight datasets demonstrate that our method can optimize multiple conflicting metrics simultaneously and can provide explanations with higher faithfulness, lower sensitivity, and lower complexity than the compared methods. Moreover, the results have shown that our method has better diversity, i.e., it provides various explanations that achieve different trade-offs between multiple conflicting explanation quality metrics. Therefore, it can provide tailored explanations to different stakeholders based on their specific requirements.
{"title":"Multi-objective Feature Attribution Explanation For Explainable Machine Learning","authors":"Ziming Wang, Changwu Huang, Yun Li, Xin Yao","doi":"10.1145/3617380","DOIUrl":"https://doi.org/10.1145/3617380","url":null,"abstract":"The feature attribution-based explanation (FAE) methods, which indicate how much each input feature contributes to the model’s output for a given data point, are one of the most popular categories of explainable machine learning techniques. Although various metrics have been proposed to evaluate the explanation quality, no single metric could capture different aspects of the explanations. Different conclusions might be drawn using different metrics. Moreover, during the processes of generating explanations, existing FAE methods either do not consider any evaluation metric or only consider the faithfulness of the explanation, failing to consider multiple metrics simultaneously. To address this issue, we formulate the problem of creating FAE explainable models as a multi-objective learning problem that considers multiple explanation quality metrics simultaneously. We first reveal conflicts between various explanation quality metrics, including faithfulness, sensitivity, and complexity. Then, we define the considered multi-objective explanation problem and propose a multi-objective feature attribution explanation (MOFAE) framework to address this newly defined problem. Subsequently, we instantiate the framework by simultaneously considering the explanation’s faithfulness, sensitivity, and complexity. Experimental results comparing with six state-of-the-art FAE methods on eight datasets demonstrate that our method can optimize multiple conflicting metrics simultaneously and can provide explanations with higher faithfulness, lower sensitivity, and lower complexity than the compared methods. Moreover, the results have shown that our method has better diversity, i.e., it provides various explanations that achieve different trade-offs between multiple conflicting explanation quality metrics. Therefore, it can provide tailored explanations to different stakeholders based on their specific requirements.","PeriodicalId":220659,"journal":{"name":"ACM Transactions on Evolutionary Learning","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126915249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The performance of multiobjective evolutionary algorithms (MOEAs) varies across problems, making it hard to develop new algorithms or apply existing ones to new problems. To simplify the development and application of new multiobjective algorithms, there has been an increasing interest in their automatic design from their components. These automatically designed metaheuristics can outperform their human-developed counterparts. However, it is still unknown what are the most influential components that lead to performance improvements. This study specifies a new methodology to investigate the effects of the final configuration of an automatically designed algorithm. We apply this methodology to a tuned Multiobjective Evolutionary Algorithm based on Decomposition (MOEA/D) designed by the iterated racing (irace) configuration package on constrained problems of 3 groups: (1) analytical real-world problems, (2) analytical artificial problems and (3) simulated real-world. We then compare the impact of the algorithm components in terms of their Search Trajectory Networks (STNs), the diversity of the population, and the anytime hypervolume values. Looking at the objective space behavior, the MOEAs studied converged before half of the search to generally good HV values in the analytical artificial problems and the analytical real-world problems. For the simulated problems, the HV values are still improving at the end of the run. In terms of decision space behavior, we see a diverse set of the trajectories of the STNs in the analytical artificial problems. These trajectories are more similar and frequently reach optimal solutions in the other problems.
{"title":"Multiobjective Evolutionary Component Effect on Algorithm behavior","authors":"Yuri Lavinas, M. Ladeira, G. Ochoa, C. Aranha","doi":"10.1145/3612933","DOIUrl":"https://doi.org/10.1145/3612933","url":null,"abstract":"The performance of multiobjective evolutionary algorithms (MOEAs) varies across problems, making it hard to develop new algorithms or apply existing ones to new problems. To simplify the development and application of new multiobjective algorithms, there has been an increasing interest in their automatic design from their components. These automatically designed metaheuristics can outperform their human-developed counterparts. However, it is still unknown what are the most influential components that lead to performance improvements. This study specifies a new methodology to investigate the effects of the final configuration of an automatically designed algorithm. We apply this methodology to a tuned Multiobjective Evolutionary Algorithm based on Decomposition (MOEA/D) designed by the iterated racing (irace) configuration package on constrained problems of 3 groups: (1) analytical real-world problems, (2) analytical artificial problems and (3) simulated real-world. We then compare the impact of the algorithm components in terms of their Search Trajectory Networks (STNs), the diversity of the population, and the anytime hypervolume values. Looking at the objective space behavior, the MOEAs studied converged before half of the search to generally good HV values in the analytical artificial problems and the analytical real-world problems. For the simulated problems, the HV values are still improving at the end of the run. In terms of decision space behavior, we see a diverse set of the trajectories of the STNs in the analytical artificial problems. These trajectories are more similar and frequently reach optimal solutions in the other problems.","PeriodicalId":220659,"journal":{"name":"ACM Transactions on Evolutionary Learning","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130449541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Editorial to the “Best of GECCO 2022” Special Issue: Part I","authors":"John H. Fieldsend, Markus Wagner","doi":"10.1145/3606034","DOIUrl":"https://doi.org/10.1145/3606034","url":null,"abstract":"","PeriodicalId":220659,"journal":{"name":"ACM Transactions on Evolutionary Learning","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126391409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
T. Friedrich, Timo Kötzing, Aishwarya Radhakrishnan, Leon Schiller, Martin Schirneck, Georg Tennigkeit, Simon Wietheger
To understand better how and why crossover can benefit constrained optimization, we consider pseudo-Boolean functions with an upper bound B on the number of 1-bits allowed in the length-n bit string (i.e., a cardinality constraint). We investigate the natural translation of the OneMax test function to this setting, a linear function where B bits have a weight of 1+ 1/n and the remaining bits have a weight of 1. Friedrich et al. [TCS 2020] gave a bound of Θ (n2) for the expected running time of the (1+1) EA on this function. Part of the difficulty when optimizing this problem lies in having to improve individuals meeting the cardinality constraint by flipping a 1 and a 0 simultaneously. The experimental literature proposes balanced operators, preserving the number of 1-bits, as a remedy. We show that a balanced mutation operator optimizes the problem in O(n log n) if n-B = O(1). However, if n-B = Θ (n), we show a bound of Ω (n2), just as for classic bit mutation. Crossover together with a simple island model gives running times of O(n2 / log n) (uniform crossover) and (O(nsqrt {n})) (3-ary majority vote crossover). For balanced uniform crossover with Hamming-distance maximization for diversity, we show a bound of O(n log n). As an additional contribution, we present an extensive analysis of different balanced crossover operators from the literature.
{"title":"Crossover for Cardinality Constrained Optimization","authors":"T. Friedrich, Timo Kötzing, Aishwarya Radhakrishnan, Leon Schiller, Martin Schirneck, Georg Tennigkeit, Simon Wietheger","doi":"10.1145/3603629","DOIUrl":"https://doi.org/10.1145/3603629","url":null,"abstract":"To understand better how and why crossover can benefit constrained optimization, we consider pseudo-Boolean functions with an upper bound B on the number of 1-bits allowed in the length-n bit string (i.e., a cardinality constraint). We investigate the natural translation of the OneMax test function to this setting, a linear function where B bits have a weight of 1+ 1/n and the remaining bits have a weight of 1. Friedrich et al. [TCS 2020] gave a bound of Θ (n2) for the expected running time of the (1+1) EA on this function. Part of the difficulty when optimizing this problem lies in having to improve individuals meeting the cardinality constraint by flipping a 1 and a 0 simultaneously. The experimental literature proposes balanced operators, preserving the number of 1-bits, as a remedy. We show that a balanced mutation operator optimizes the problem in O(n log n) if n-B = O(1). However, if n-B = Θ (n), we show a bound of Ω (n2), just as for classic bit mutation. Crossover together with a simple island model gives running times of O(n2 / log n) (uniform crossover) and (O(nsqrt {n})) (3-ary majority vote crossover). For balanced uniform crossover with Hamming-distance maximization for diversity, we show a bound of O(n log n). As an additional contribution, we present an extensive analysis of different balanced crossover operators from the literature.","PeriodicalId":220659,"journal":{"name":"ACM Transactions on Evolutionary Learning","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131617918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Delaram Yazdani, D. Yazdani, Donya Yazdani, M. Omidvar, A. Gandomi, X. Yao
Population clustering methods, which consider the position and fitness of the individuals to form sub-populations in multi-population algorithms, have shown high efficiency in tracking the moving global optimum in dynamic optimization problems. However, most of these methods use a fixed population size, making them inflexible and inefficient when the number of promising regions is unknown. The lack of a functional relationship between the population size and the number of promising regions significantly degrades performance and limits an algorithm’s agility to respond to dynamic changes. To address this issue, we propose a new species-based particle swarm optimization with adaptive population size and number of sub-populations for solving dynamic optimization problems. The proposed algorithm also benefits from a novel systematic adaptive deactivation component that, unlike the previous deactivation components, adapts the computational resource allocation to the sub-populations by considering various characteristics of both the problem and the sub-populations. We evaluate the performance of our proposed algorithm for the Generalized Moving Peaks Benchmark and compare the results with several peer approaches. The results indicate the superiority of the proposed method.
{"title":"A Species-based Particle Swarm Optimization with Adaptive Population Size and Deactivation of Species for Dynamic Optimization Problems","authors":"Delaram Yazdani, D. Yazdani, Donya Yazdani, M. Omidvar, A. Gandomi, X. Yao","doi":"10.1145/3604812","DOIUrl":"https://doi.org/10.1145/3604812","url":null,"abstract":"Population clustering methods, which consider the position and fitness of the individuals to form sub-populations in multi-population algorithms, have shown high efficiency in tracking the moving global optimum in dynamic optimization problems. However, most of these methods use a fixed population size, making them inflexible and inefficient when the number of promising regions is unknown. The lack of a functional relationship between the population size and the number of promising regions significantly degrades performance and limits an algorithm’s agility to respond to dynamic changes. To address this issue, we propose a new species-based particle swarm optimization with adaptive population size and number of sub-populations for solving dynamic optimization problems. The proposed algorithm also benefits from a novel systematic adaptive deactivation component that, unlike the previous deactivation components, adapts the computational resource allocation to the sub-populations by considering various characteristics of both the problem and the sub-populations. We evaluate the performance of our proposed algorithm for the Generalized Moving Peaks Benchmark and compare the results with several peer approaches. The results indicate the superiority of the proposed method.","PeriodicalId":220659,"journal":{"name":"ACM Transactions on Evolutionary Learning","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130089790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Peer-to-peer (P2P) energy trading is a decentralized energy market where local energy prosumers act as peers, trading energy among each other. Existing works in this area largely overlook the importance of user behavioral modeling and assume users’ sustained active participation and full compliance in the decision-making process. To overcome these unrealistic assumptions, and their deleterious consequences, in this article, we propose an automated P2P energy-trading framework that specifically considers the users’ perception by exploiting prospect theory. We formalize an optimization problem that maximizes the buyers’ perceived utility while matching energy production and demand. We prove that the problem is NP-hard and we propose a Differential Evolution-based Algorithm for Trading Energy (DEbATE) heuristic. Additionally, we propose two automated pricing solutions to improve the sellers’ profit based on reinforcement learning. The first solution, named Pricing mechanism with Q-learning and Risk-sensitivity (PQR), is based on Q-learning. Additionally, given the scalability issues of PQR, we propose a Deep Q-Network-based algorithm called ProDQN that exploits deep learning and a novel loss function rooted in prospect theory. Results based on real traces of energy consumption and production, as well as realistic prospect theory functions, show that our approaches achieve 26% higher perceived value for buyers and generate 7% more reward for sellers, compared to recent state-of-the-art approaches.
{"title":"P2P Energy Trading through Prospect Theory, Differential Evolution, and Reinforcement Learning","authors":"Ashutosh Timilsina, Simone Silvestri","doi":"10.1145/3603148","DOIUrl":"https://doi.org/10.1145/3603148","url":null,"abstract":"Peer-to-peer (P2P) energy trading is a decentralized energy market where local energy prosumers act as peers, trading energy among each other. Existing works in this area largely overlook the importance of user behavioral modeling and assume users’ sustained active participation and full compliance in the decision-making process. To overcome these unrealistic assumptions, and their deleterious consequences, in this article, we propose an automated P2P energy-trading framework that specifically considers the users’ perception by exploiting prospect theory. We formalize an optimization problem that maximizes the buyers’ perceived utility while matching energy production and demand. We prove that the problem is NP-hard and we propose a Differential Evolution-based Algorithm for Trading Energy (DEbATE) heuristic. Additionally, we propose two automated pricing solutions to improve the sellers’ profit based on reinforcement learning. The first solution, named Pricing mechanism with Q-learning and Risk-sensitivity (PQR), is based on Q-learning. Additionally, given the scalability issues of PQR, we propose a Deep Q-Network-based algorithm called ProDQN that exploits deep learning and a novel loss function rooted in prospect theory. Results based on real traces of energy consumption and production, as well as realistic prospect theory functions, show that our approaches achieve 26% higher perceived value for buyers and generate 7% more reward for sellers, compared to recent state-of-the-art approaches.","PeriodicalId":220659,"journal":{"name":"ACM Transactions on Evolutionary Learning","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131865698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tiwonge Msulira Banda, Alexandru-Ciprian Zavoianu, Andrei V. Petrovski, Daniel Wöckinger, G. Bramerdorfer
Modelling and controlling heat transfer in rotating electrical machines is very important as it enables the design of assemblies (e.g., motors) that are efficient and durable under multiple operational scenarios. To address the challenge of deriving accurate data-driven estimators of key motor temperatures, we propose a multi-objective strategy for creating Linear Regression (LR) models that integrate optimised synthetic features. The main strength of our approach is that it provides decision makers with a clear overview of the optimal trade-offs between data collection costs, the expected modelling errors and the overall explainability of the generated thermal models. Moreover, as parsimonious models are required for both microcontroller deployment and domain expert interpretation, our modelling strategy contains a simple but effective step-wise regularisation technique that can be applied to outline domain-relevant mappings between LR variables and thermal profiling capabilities. Results indicate that our approach can generate accurate LR-based dynamic thermal models when training on data associated with a limited set of load points within the safe operating area of the electrical machine under study.
{"title":"A Multi-Objective Evolutionary Approach to Discover Explainability Trade-Offs when Using Linear Regression to Effectively Model the Dynamic Thermal Behaviour of Electrical Machines","authors":"Tiwonge Msulira Banda, Alexandru-Ciprian Zavoianu, Andrei V. Petrovski, Daniel Wöckinger, G. Bramerdorfer","doi":"10.1145/3597618","DOIUrl":"https://doi.org/10.1145/3597618","url":null,"abstract":"Modelling and controlling heat transfer in rotating electrical machines is very important as it enables the design of assemblies (e.g., motors) that are efficient and durable under multiple operational scenarios. To address the challenge of deriving accurate data-driven estimators of key motor temperatures, we propose a multi-objective strategy for creating Linear Regression (LR) models that integrate optimised synthetic features. The main strength of our approach is that it provides decision makers with a clear overview of the optimal trade-offs between data collection costs, the expected modelling errors and the overall explainability of the generated thermal models. Moreover, as parsimonious models are required for both microcontroller deployment and domain expert interpretation, our modelling strategy contains a simple but effective step-wise regularisation technique that can be applied to outline domain-relevant mappings between LR variables and thermal profiling capabilities. Results indicate that our approach can generate accurate LR-based dynamic thermal models when training on data associated with a limited set of load points within the safe operating area of the electrical machine under study.","PeriodicalId":220659,"journal":{"name":"ACM Transactions on Evolutionary Learning","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126402476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：