Article
Computer Science, Information Systems
Yuanhao Liu, Zan Yang, Danyang Xu, Haobo Qiu, Liang Gao
Summary: This paper proposes a surrogate-assisted differential evolution algorithm (SADE-MI) for solving expensive constrained optimization problems with mixed-integer variables. It overcomes the challenges caused by mixed-integer variables through adaptive pre-screening operation and population diversity maintenance operation, and outperforms other classical algorithms in benchmark problems and engineering optimization cases.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Yong Wang, Jianqing Lin, Jiao Liu, Guangyong Sun, Tong Pang
Summary: This article proposes a surrogate-assisted differential evolution algorithm with region division (ReDSADE) to solve expensive optimization problems with discontinuous objective functions. The algorithm combines region division, Kriging-based search, and RBF-based local search strategies, achieving good convergence accuracy and speed.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Interdisciplinary Applications
Zan Yang, Haobo Qiu, Liang Gao, Liming Chen, Xiwen Cai
Summary: English Summary: This study proposes a constraint boundary Pursuing-based Surrogate-Assisted Differential Evolution (PSADE) method to solve complex optimization problems with mixed constraints, including both inequality and equality constraints. By using Trial Vector Generation Mechanism (TVGM) and Expected Improvement-based Local Search (EILS), PSADE maintains a good balance between convergence and diversity when considering both constraints and objective. Experimental results show that PSADE is highly competitive in solving ECOPs with mixed constraints under an acceptable computational cost.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2023)
Article
Computer Science, Information Systems
Xiaodi Cheng, Yongguang Yu, Wei Hu
Summary: In this paper, a multi-surrogate-assisted stochastic fractal search algorithm (MSASFS) is proposed to solve high-dimensional expensive problems. The proposed algorithm improves the generalization ability and extends the exploration scope by combining the original coordinate system with the eigencoordinate system. It also employs an expected improvement (EI) pre-screening strategy based on the Gaussian process (GP) model and applies two different surrogate models to enhance robustness.
INFORMATION SCIENCES
(2023)
Article
Automation & Control Systems
Feng-Feng Wei, Wei-Neng Chen, Wentao Mao, Xiao-Min Hu, Jun Zhang
Summary: This article proposes an efficient two-stage surrogate-assisted differential evolution (eToSA-DE) algorithm to handle expensive inequality constraints. The algorithm trains a surrogate model for the degree of constraint violation, with the type of surrogate changing during the evolution process. Both types of surrogates are constructed using individuals selected by the boundary training data selection strategy. A feasible exploration strategy is devised to search for promising areas. Extensive experiments demonstrate that the proposed method can achieve satisfactory optimization results and significantly improve the efficiency of the algorithm.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Qinghua Gu, Qian Wang, Neal N. Xiong, Song Jiang, Lu Chen
Summary: A surrogate-assisted evolutionary algorithm is proposed in this paper for solving expensive constrained multi-objective discrete optimization problems. By embedding random forest models and an improved stochastic ranking strategy, the algorithm makes significant progress in optimization efficiency and candidate solution quality.
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Qinghua Gu, Qian Wang, Xuexian Li, Xinhong Li
Summary: A new algorithm, RFMOPSO, is proposed in this paper to optimize constrained combinatorial optimization problems by combining multi-objective particle swarm optimization with a random forest model. Adaptive ranking strategy and novel rule are employed to improve search speed and adaptively update particle states for better objective balance and feasible solutions. Experimental results show promising performance on benchmark problems with discrete variables varying from 10 to 100.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Yong Zhang, Xin-Fang Ji, Xiao-Zhi Gao, Dun-Wei Gong, Xiao-Yan Sun
Summary: This article introduces an objective-constraint mutual-guided surrogate-assisted particle swarm optimization algorithm for expensive constraint multimodal optimization problems. The algorithm utilizes a two-layer cooperative surrogate model framework and a partial evaluation strategy to reduce computational cost while obtaining multiple competitive feasible optimal solutions. It also proposes a hybrid update mechanism and a local search strategy to improve the algorithm's performance. Experimental results demonstrate the effectiveness of the proposed algorithm compared to existing methods.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Information Systems
Zan Yang, Haobo Qiu, Liang Gao, Danyang Xu, Yuanhao Liu
Summary: This paper proposes a general framework of surrogate-assisted evolutionary algorithms (GF-SAEAs) to adaptively arrange search strategies based on actual simulation cost differences. It classifies all constraints and designs a level-by-level feasible region-driven local search strategy to locate potential sub-feasible regions. Three different search mechanisms are employed to explore and exploit these located regions. Experimental studies show that GF-SAEAs outperform other state-of-the-art algorithms.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Yuanchao Liu, Jianchang Liu, Yaochu Jin, Fei Li, Tianzi Zheng
Summary: This work proposes a novel surrogate-assisted two-stage differential evolution (SA-TSDE) algorithm for expensive constrained optimization. It combines a hybrid differential evolution with a repair strategy in the first stage, and a clustering strategy with local surrogates in the second stage. Experimental results show that SA-TSDE is highly competitive compared with state-of-the-art methods.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Engineering, Multidisciplinary
Jiachang Qian, Yuansheng Cheng, Jinlan Zhang, Jun Liu, Dawei Zhan
Summary: The newly proposed PC-EGO algorithm shows faster convergence and better solutions for expensive constrained optimization problems compared to the standard C-EGO algorithm and another state-of-the-art parallel constrained EGO algorithm.
ENGINEERING OPTIMIZATION
(2021)
Article
Computer Science, Interdisciplinary Applications
Spyridon Tsattalios, Ioannis Tsoukalas, Panagiotis Dimas, Panagiotis Kossieris, Andreas Efstratiadis, Christos Makropoulos
Summary: Complex environmental optimization problems often require computationally expensive simulation models, leading to laborious search procedures. The AMSEEAS algorithm is introduced as an extension of its precursor SEEAS, utilizing multiple surrogate models to accelerate convergence towards promising solutions. Extensive benchmarking against SEEAS and other state-of-the-art methods demonstrates the robustness and efficiency of AMSEEAS in both theoretical mathematical problems and a computationally demanding real-world hydraulic design application.
ENVIRONMENTAL MODELLING & SOFTWARE
(2023)
Article
Computer Science, Artificial Intelligence
Gabriel Dominico, Rafael Stubs Parpinelli
Summary: The article discusses two main categories of multimodal optimization: finding a single global optimum and finding multiple global optima. It proposes a self-adaptive Differential Evolution with DBSCAN algorithm named NCjDE-2LS(ar) for solving the problem of multiple global optima optimization. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art algorithms in terms of peak ratio evaluation metric.
APPLIED SOFT COMPUTING
(2021)
Article
Automation & Control Systems
Weizhong Wang, Hai-Lin Liu, Kay Chen Tan
Summary: This article proposes a global and local surrogate-assisted differential evolution algorithm (GL-SADE) that utilizes a global RBF model to estimate global trend and accelerate convergence, as well as a local Kriging model to prevent local optima and further exploit the model through a reward search strategy. The algorithm is validated and demonstrated on benchmark functions of varying dimensions and an airfoil optimization problem.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Information Systems
Zan Yang, Haobo Qiu, Liang Gao, Liming Chen, Jiansheng Liu
Summary: This paper proposes an adaptive surrogate-assisted MOEA/D framework (ASA-MOEA/D) for efficiently solving expensive constrained multi-objective optimization problems. With three specific search strategies, ASA-MOEA/D achieved targeted searches for different subproblems based on their optimization states. The framework maintained feasibility, convergence, and diversity through the use of RBF surrogates and exploration of unexplored subregions. Empirical studies showed that ASA-MOEA/D with tchebycheff approach outperformed four state-of-the-art algorithms.
INFORMATION SCIENCES
(2023)
Article
Automation & Control Systems
Zhong-Yi Shui, Xu-Hao Li, Yun Feng, Bing-Chuan Wang, Yong Wang
Summary: The parameters of a lithium-ion battery are crucial for an effective battery management system. Parameter estimation using the pseudo-two-dimensional (P2D) model is more cost-effective than direct measurement methods, but the simulation of the P2D model is time-consuming. To overcome this, a two-phase surrogate model-assisted parameter estimation algorithm (TPSMA-PEAL) is proposed, combining the advantages of reduced-order and data-driven models. TPSMA-PEAL addresses challenges such as overfitting and low observability using differential evolution and parameter sensitivity analysis. Simulations and experiments demonstrate the efficiency and accuracy of TPSMA-PEAL.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Automation & Control Systems
Zhongwei Ma, Yong Wang
Summary: This article presents a new constraint-handling technique called shift-based penalty (ShiP) for solving constrained multiobjective optimization problems. ShiP utilizes a two-step process by shifting infeasible solutions towards feasible solutions and penalizing them based on constraint violations. ShiP encourages diverse feasible solutions during the early stage of evolution and promotes convergence towards Pareto optimal solutions in the later stage. The effectiveness of ShiP is demonstrated through experiments on benchmark test problems and its application in vehicle scheduling.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Conor Fahy, Shengxiang Yang, Mario Gongora
Summary: This paper proposes an algorithm named COCEL for classification in dynamic data streams. The algorithm combines a stream clustering algorithm and an ensemble of one-class classifiers to recognize and react to changes in the data stream. Experimental results demonstrate that COCEL can achieve superior or comparative accuracy with less labeled data compared to peer stream classification ensembles.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Xiaodong Yang, Zhiyan Zhou, Youbing Zhang, Jiancun Liu, Jinyu Wen, Qiuwei Wu, Shijie Cheng
Summary: This paper proposes a co-deployment framework for soft open points (SOPs) and remote-controlled switches (RCSs) to improve the resilience and management of flexible resources in distribution networks. The model optimizes the investment cost of SOPs and RCSs, as well as the cost caused by de-energized loads, while considering operational constraints. It also analyzes the tradeoff between resilience and cost.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2023)
Article
Computer Science, Information Systems
Xin Li, Xiaoli Li, Kang Wang, Shengxiang Yang
Summary: Evolutionary algorithms are effective for multi-objective optimization problems, but their performance degrades when dealing with many-objective optimization problems, especially with irregular Pareto front shapes. To address this, we propose a strength Pareto evolutionary algorithm based on adaptive reference points (SPEA/ARP), which updates reference points using current and historical population information and balances selection pressure and diversity of non-dominated solutions.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Yingjie Zou, Yuan Liu, Juan Zou, Shengxiang Yang, Jinhua Zheng
Summary: Sparse large scale multiobjective optimization problems (sparse LSMOPs) have a high degree of sparsity in the decision variables of their Pareto optimal solutions. Existing evolutionary algorithms for sparse LSMOPs fail to achieve sufficient sparsity due to inaccurate location of nonzero decision variables and lack of interaction between the locating process and optimizing process. To address this, a dynamic sparse grouping evolutionary algorithm (DSGEA) is proposed, which groups decision variables with comparable numbers of nonzero variables and applies improved evolutionary operators for optimization. DSGEA outperforms current EAs in experiments on real-world and benchmark problems, achieving sparser Pareto optimal solutions with precise locations of nonzero decision variables.
INFORMATION SCIENCES
(2023)
Article
Automation & Control Systems
Pei-Qiu Huang, Yong Wang, Kezhi Wang, Qingfu Zhang
Summary: This article studies an intelligent reflecting surface (IRS)-aided communication system under the time-varying channels and stochastic data arrivals. It proposes a method called LETO that combines Lyapunov optimization with evolutionary transfer optimization (ETO) to solve the optimization problem. LETO decouples the long-term optimization problem into deterministic optimization problems in short time slots, ensuring queue stability, and then solves the optimization problem in each time slot using the evolutionary transfer method to achieve real-time decisions.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Retraction
Mycology
Yi Kuang, Kirstin Scherlach, Christian Hertweck, Shengxiang Yang, Diego A. Sampietro, Petr Karlovsky
MYCOTOXIN RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Zedong Zheng, Shengxiang Yang, Yinan Guo, Xiaolong Jin, Rui Wang
Summary: This paper reviews the application of meta-heuristics in microgrid management, summarizes the contributions and influences of different methods, and provides further insights and suggestions for future research.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Jinhua Zheng, Qishuang Wu, Juan Zou, Shengxiang Yang, Yaru Hu
Summary: Responding quickly to environmental changes is crucial in solving dynamic multi-objective optimization problems (DMOPs). Most existing methods perform well on predicting individuals but struggle with improving the accuracy of the predicted population. This paper proposes an approach called RVCP, which combines an adjusted reference vector with a multi-objective evolutionary algorithm to predict the population and effectively tackle DMOPs.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Kaixi Yang, Jinhua Zheng, Juan Zou, Fan Yu, Shengxiang Yang
Summary: This paper proposes a dual-population algorithm called dp-ACS to balance constraint satisfaction and objective optimization. The algorithm introduces a dominance relation and an adaptive constraint strength strategy to improve convergence and consider excellent infeasible solutions. Experimental results show that the proposed algorithm outperforms seven state-of-the-art CMOEAs on constrained test suites and real-world CMOPs.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Jinhua Zheng, Zhenfang Du, Juan Zou, Shengxiang Yang
Summary: In researching multi-objective evolutionary algorithms, a preference-based MOEA called MOEA/D-ND is proposed. It uses a normal distribution to generate a weight vector and incorporates the decision-maker's preference information to guide convergence. An angle-based niche selection strategy is adopted to prevent falling into local optima. Experimental results show that this algorithm outperforms in various benchmark problems with 2 to 15 goals.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Information Systems
Juan Zou, Jian Luo, Yuan Liu, Shengxiang Yang, Jinhua Zheng
Summary: The core element in solving CMOPs is to balance objective optimization and constraint satisfaction. We propose a flexible two-stage evolutionary algorithm based on automatic regulation (ARCMO) to adapt to complex CMOPs.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Weixiong Huang, Juan Zou, Yuan Liu, Shengxiang Yang, Jinhua Zheng
Summary: This paper proposes a constrained multi-objective evolutionary algorithm framework based on global and local feasible solutions search to address the complexity of feasible regions caused by constraints. The framework is divided into three stages and an adaptive method is used to decide when to switch the search state. The experimental results show that the proposed framework is highly competitive for solving CMOPs.
INFORMATION SCIENCES
(2023)
Article
Automation & Control Systems
Jie Chen, Zhu Wang, Shengxiang Yang, Hua Mao
Summary: This article proposes a two-stage sparse representation clustering (TSSRC) method based on sparse representation techniques to address the critical issues in data stream clustering. The TSSRC algorithm evaluates the effective relationship among data objects in landmark windows with an accurate number of clusters and efficiently passes previously learned knowledge to the current landmark window. Experimental results demonstrate the effectiveness and robustness of TSSRC.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)