Article
Automation & Control Systems
Huangke Chen, Ran Cheng, Witold Pedrycz, Yaochu Jin
Summary: This paper proposes a method to solve multiobjective optimization problems through multi-stage evolutionary search, highlighting convergence and diversity in different search stages. The algorithm balances and addresses the issues in multiobjective optimization through two stages.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Automation & Control Systems
Wenbo Qiu, Jianghan Zhu, Guohua Wu, Huangke Chen, Witold Pedrycz, Ponnuthurai Nagaratnam Suganthan
Summary: The research proposes a general voting-mechanism-based ensemble framework (VMEF) that integrates and cooperates different solution-sorting methods to achieve more robust solution selection. The framework employs a strategy to adaptively allocate total votes based on the contribution of each solution-sorting method, providing good feedback for the optimization process.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Computer Science, Information Systems
Ke Shang, Tianye Shu, Hisao Ishibuchi, Yang Nan, Lie Meng Pang
Summary: In the field of evolutionary multi-objective optimization, the final population is commonly used as the output, but it often contains dominated solutions from previous generations. To address this problem, a novel framework has been developed to store all non-dominated solutions in an archive and select a subset from the archive as the output. However, most studies focus on small candidate solution sets, and there is no benchmark test suite for large-scale subset selection. This study proposes a benchmark test suite and compares several subset selection algorithms using the proposed tests, providing a baseline for researchers in the EMO field to understand, compare, and develop large-scale subset selection algorithms. (c) 2022 Elsevier Inc. All rights reserved.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Lingfeng Hu, Jingxuan Wei, Yang Liu
Summary: With an increasing number of objectives, the proportion of non-dominated individuals in many-objective optimization problems sharply increases, leading to a reduction in convergence pressure of traditional multi-objective optimization algorithms. Existing nonlinear expanded evolutionary algorithms may not be able to find true Pareto fronts in special regions where optimal solutions are located.
Article
Multidisciplinary Sciences
Saykat Dutta, Rammohan Mallipeddi, Kedar Nath Das
Summary: In this work, a Hybrid Selection based MOEA (HS-MOEA) is proposed, which effectively balances the diversity and convergence properties of MOEA by combining Pareto-dominance, reference vectors, and an indicator. Experimental simulations on DTLZ and WFG test suites demonstrate the superior performance of HS-MOEA compared to state-of-the-art MOEAs, with up to 10 objectives.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Artificial Intelligence
Peng Zhang, Jinlong Li, Tengfei Li, Huanhuan Chen
Summary: In order to balance the relationship between diversity and convergence in handling different types of many-objective optimization problems (MaOPs), a Kernel matrix and probability model called determinantal point processes (DPPs) are introduced. The experimental results demonstrate that the MaOEA with DPPs (MaOEADPPs) is competitive on various types of MaOPs with different numbers of objectives.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2021)
Article
Automation & Control Systems
Liang Zhang, Qi Kang, Qi Deng, Luyuan Xu, Qidi Wu
Summary: This study proposes a method to evolve solutions through a line complex instead of solution points in Euclidean space, in order to solve the fast loss of selection pressure in existing nondominated sorting-based multi-objective evolutionary algorithms. Plucker coordinates are used to project solution points to a line complex composed of position vectors and momentum ones, and a new distance function designed for high-dimensional space is proposed to replace Euclidean distance as a more effective distance-based estimator. A novel many-objective evolutionary algorithm (MaOEA) is proposed by integrating a line complex-based environmental selection strategy into the NSGA-III framework.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2023)
Article
Automation & Control Systems
Jiangtao Shen, Peng Wang, Xinjing Wang
Summary: Maintaining a balance between convergence and diversity is crucial in evolutionary multiobjective optimization. A new dominance relation called Strengthened Dominance Relation (SDR) is proposed, which outperforms existing dominance relations in balancing convergence and diversity. An adaptation strategy is presented to dynamically adjust the dominance relation, and the proposed NSGA-II/CSDR outperforms other algorithms in terms of both convergence and diversity on benchmark problems.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Information Systems
Xiaofang Guo
Summary: This paper provides a systematic comparison and classification of six key components of decomposition-based multi-objective evolutionary algorithms, and analyzes the characteristics and application scope of various algorithms in detail.
Article
Computer Science, Artificial Intelligence
Jun Yi, Wei Zhang, Junren Bai, Wei Zhou, Lizhong Yao
Summary: In this article, a novel MFEA based on improved dynamical decomposition (MFEA/IDD) is proposed for solving many-objective optimization problems (MaOPs). The MFEA/IDD algorithm integrates the advantages of multitasking optimization and decomposition-based evolutionary algorithms, and it effectively balances convergence and diversity while reducing the total number of function evaluations for solving MaOPs.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Lucas R. C. de Farias, Aluizio F. R. Araujo
Summary: This paper introduces a MOEA/D-UR algorithm based on decomposition, which utilizes a metric to detect improvements and a procedure to increase diversity in the objective space. Experimental results suggest that MOEA/D-UR is more effective in handling real-world problems and multi-objective scenarios compared to other algorithms.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Information Systems
Maowei He, Haitao Xia, Hanning Chen, Lianbo Ma
Summary: This article introduces an inhomogeneous grid-based evolutionary algorithm called IGEA, which can better reveal the dominance relationship in multi-objective optimization problems through dynamic inhomogeneous grid division and redefining the coordinate assignment of individuals. It also applies a shift-based density estimation strategy to provide a balance between convergence and diversity.
Article
Automation & Control Systems
Kai Zhang, Zhiwei Xu, Shengli Xie, Gary G. Yen
Summary: In this article, a new evolution strategy called MaOES is proposed to address the challenges faced by existing MaOEAs in solving MaOPs. Inspired by the Vector Equilibrium phenomenon, MaOES efficiently solves diversity preservation and dominance resistance issues using self-adaptive mutation and maximum extension distance strategies, resulting in a well-converged and well-diversified Pareto front.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Computer Science, Information Systems
Hao Wang, Chaoli Sun, Guochen Zhang, Jonathan E. Fieldsend, Yaochu Jin
Summary: This study proposes a new multi-objective optimization method that converts multi-objective problems into bi-objective ones by using two performance indicators and non-dominated sorting to address engineering problems with multiple conflicting objectives. The method improves performance by balancing individual performance in different parts of the objective space and measuring diversity of each individual. Experimental results show competitiveness of the proposed method in solving problems with a large number of objectives.
INFORMATION SCIENCES
(2021)
Article
Automation & Control Systems
Ye Tian, Yajie Zhang, Yansen Su, Xingyi Zhang, Kay Chen Tan, Yaochu Jin
Summary: The proposed two-stage evolutionary algorithm adjusts the balance between objective optimization and constraint satisfaction adaptively, addressing the difficulty of striking a good balance in complex feasible regions. Experimental studies demonstrate the superiority of the algorithm over state-of-the-art algorithms, especially on problems with complex feasible regions.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Artificial Intelligence
Tapabrata Ray, Tobias Rodemann, Markus Olhofer, Hemant Kumar Singh, Kamrul Hasan Rahi
Summary: In multi/many-objective optimization, identifying solutions of interest (SOIs) is crucial for decision makers. Existing methods focus on measures based on the objective space and overlook the variable space. This paper proposes an approach that considers both objective and variable spaces to identify SOIs, and develops algorithms for different scenarios.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Bing Wang, Hemant Kumar Singh, Tapabrata Ray
Summary: In this study, a surrogate model-based approach is proposed for solving expensive multi-objective optimization problems. The predicted hypervolume maximization is used as the infill criterion, and a more scalable approach based on surrogate corner search is introduced. The proposed approach demonstrates improved performance and reliability in numerical experiments on benchmark problems with up to 5 objectives.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Mohammad Mohiuddin Mamun, Hemant Kumar Singh, Tapabrata Ray
Summary: This letter proposes a novel approach to treat bilevel optimization problems as multifidelity optimization problems, reducing the number of function evaluations. By learning the appropriate fidelity to evaluate solutions, redundant evaluations can be significantly reduced, improving the efficiency of problem-solving.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Mohammad Mohiuddin Mamun, Hemant Kumar Singh, Tapabrata Ray
Summary: This study introduces a SAO approach for multi-objective optimization problems, which selectively evaluates the objectives of infill solutions. By leveraging principles of non-dominance and sparse subset selection, the approach aims to improve computational efficiency and identify infill solutions through maximization of probabilistic dominance measure.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Angus Kenny, Tapabrata Ray, Hemant Kumar Singh
Summary: Engineering design optimization often involves using numerical simulations to assess candidate designs. Multifidelity optimization methods aim to optimize computationally expensive problems within a limited budget by efficiently managing low-fidelity and high-fidelity evaluations. This article proposes an improved multifidelity approach called MFITS, which uses an iterative, two-stage scheme to search for good candidates for high-fidelity evaluation based on collective information from previously evaluated designs.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Angus Kenny, Tapabrata Ray, Steffen Limmer, Hemant Kumar Singh, Tobias Rodemann, Markus Olhofer
Summary: Tree-based pipeline optimization tool (TPOT) is a tool used to automatically construct and optimize machine learning pipelines for classification or regression tasks. This study integrates TPOT with Bayesian Optimization (BO) to extend its ability to search across continuous hyper-parameter spaces and improve its performance when there is a limited computational budget.
PROCEEDINGS OF THE 2023 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, GECCO 2023
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Quang Nhat Huynh, Hemant Kumar Singh, Tapabrata Ray
Summary: This paper focuses on uncovering implicit equations in the form of a general linear model. The author proposes improved formulations of linear programming and mixed-integer linear programming to solve this problem. The evaluation on 23 simulated benchmarks shows promising results and demonstrates the suitability of the proposed approach for integration with genetic programming frameworks.
PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022
(2022)
Article
Computer Science, Information Systems
Hemant Kumar Singh, Tapabrata Ray, Md Juel Rana, Steffen Limmer, Tobias Rodemann, Markus Olhofer
Summary: With the increasing popularity of electric vehicles, efficient scheduling of charging becomes crucial. This study extends and improves the charging problem, compares the performance of different solution approaches, and provides insights for further development.
Proceedings Paper
Computer Science, Artificial Intelligence
Hemant Kumar Singh, Juergen Branke
Summary: This research tackles the problem of finding a robust solution to disturbances of decision variables by identifying all stochastically non-dominated solutions. Empirical results demonstrate that the algorithm effectively finds these solutions, and proposed efficiency enhancements significantly reduce the required number of function evaluations while maintaining good solution quality.
PARALLEL PROBLEM SOLVING FROM NATURE - PPSN XVII, PPSN 2022, PT II
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Bing Wang, Hemant Kumar Singh, Tapabrata Ray
Summary: This study focuses on examining the effectiveness of direct solution transfer in bilevel optimization, proposing an improved approach based on correlations between neighboring landscapes. Experimental results show the competitive performance of the correlation-based approach on challenging modified problems, providing insights for future development of efficient transfer-based approaches for bilevel optimization.
2022 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Tapabrata Ray, Mohammad Mohiuddin Mamun, Hemant Kumar Singh
Summary: This study introduces a steady-state evolutionary algorithm for solving multi-modal, multi-objective optimization problems, which is simple in design and does not require additional user-defined parameters compared to existing algorithms. The algorithm demonstrates good performance across various benchmark test suites, and aims to promote the design of simple and efficient algorithms for practical applications.
2022 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC)
(2022)
Article
Automation & Control Systems
Md Juel Rana, Forhad Zaman, Tapabrata Ray, Ruhul Sarker
Summary: Community microgrids provide resiliency in smart grid operation and have seen an increased penetration of eco-friendly electric vehicles (EVs) in recent years. However, the uncontrolled charging of EVs can overwhelm electric networks. In this work, an efficient demand response (DR) scheme based on dynamic pricing is proposed to enhance the capacity of microgrids in hosting a large number of EVs. The scheme utilizes a hierarchical optimization framework and employs evolutionary algorithms and mixed-integer linear programming models to solve the problems. The proposed DR scheme is tested on a microgrid system and proves to be effective compared to benchmark pricing policies.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)