Swarm and Evolutionary Computation最新文献_第8页

Surrogate-assisted two-stage cooperative differential evolution for expensive constrained multimodal optimization problems 昂贵约束多模态优化问题的代理辅助两阶段协同微分进化

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-06-12 DOI: 10.1016/j.swevo.2025.102014

Xinfang Ji , Jingwei Jia , Xiaofeng Wang , Jiaxing Yao , Lixia Fang , Jinxin Cheng , Yong Zhang

{"title":"Surrogate-assisted two-stage cooperative differential evolution for expensive constrained multimodal optimization problems","authors":"Xinfang Ji , Jingwei Jia , Xiaofeng Wang , Jiaxing Yao , Lixia Fang , Jinxin Cheng , Yong Zhang","doi":"10.1016/j.swevo.2025.102014","DOIUrl":"10.1016/j.swevo.2025.102014","url":null,"abstract":"<div><div>The expensive calculation, constrained solution space and multimodal properties of expensive constrained multimodal optimization problems pose significant challenges for effective problem solving. Therefore, this study proposed a surrogate-assisted two-stage cooperative differential evolution algorithm, aiming to locate multiple optimal solutions at a low computational cost. The algorithm initially established a two-stage master–auxiliary problem cooperative framework to balance the search focus at various stages: the first stage emphasizes finding feasible regions, while the second stage focuses on tracking multiple modalities and locating the optimal solution within each modality. Then, to balance the feasibility, diversity, and accuracy of the solutions, a multi-indicator guided two-stage surrogate model management mechanism was proposed. Furthermore, a two-stage local search strategy for elite solutions was presented, which implements different local search schemes based on the existence of feasible solutions, in order to improve the quality of solutions while mining feasible ones. Finally, the proposed algorithm was compared with five existing expensive constrained surrogate-assisted evolutionary algorithms (SAEAs), one constrained multimodal evolutionary algorithm, and one expensive constrained multimodal SAEA. Experimental results on 21 benchmark problems and 1 rotor airfoil aerodynamic instance show that the proposed algorithm can obtain multiple highly competitive optimal solutions with less computational cost.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"97 ","pages":"Article 102014"},"PeriodicalIF":8.2,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144263875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Greedy randomized adaptive search and benders decomposition algorithms to solve the distributed no-idle permutation flowshop scheduling problem 贪婪随机自适应搜索和弯曲分解算法解决分布式无空闲排列流水车间调度问题

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-06-12 DOI: 10.1016/j.swevo.2025.102028

Alper Hamzadayı , Münevver Günay Van

{"title":"Greedy randomized adaptive search and benders decomposition algorithms to solve the distributed no-idle permutation flowshop scheduling problem","authors":"Alper Hamzadayı , Münevver Günay Van","doi":"10.1016/j.swevo.2025.102028","DOIUrl":"10.1016/j.swevo.2025.102028","url":null,"abstract":"<div><div>In today's competitive manufacturing landscape, large enterprises manage multiple production sites, leading to complex scheduling challenges. This study investigates the Distributed No-Idle Permutation Flowshop Scheduling Problem (DNIPFSP), where the objective is to minimize makespan across multiple identical factories while ensuring continuous machine utilization without idle time. To address this problem, we propose both approximation and exact methods. For the approximation method, we introduce a novel Greedy Randomized Adaptive Search Procedure (GRASP). On the exact optimization side, we develop three mathematical formulations: a sequence-based model, an improved position-based model, and a restricted version of the improved position-based model, where the upper bounds of decision variables are determined through a two-stage process. First, an initial GRASP solution is obtained, and based on this solution, an additional model is solved to compute the upper bounds of decision variables. The Benders decomposition algorithm is then applied to efficiently solve problem instances. To further improve computational efficiency, we introduce a hybrid Benders decomposition algorithm<strong>,</strong> incorporating heuristic-derived cuts alongside standard Benders cuts<strong>.</strong> Additionally, symmetry-breaking constraints are integrated to strengthen the formulations. Extensive benchmark experiments demonstrate the superiority of the proposed methods over existing approaches. The hybrid Benders decomposition algorithm with symmetry-breaking constraints significantly outperforms the best-known models in the literature, optimally solving 419 out of 420 small-sized instances with an average optimality gap of 0.011%. Additionally, the GRASP achieves the lowest average relative percentage deviation (RPD) for large-sized instances, demonstrating its effectiveness in large-scale scheduling optimization.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"97 ","pages":"Article 102028"},"PeriodicalIF":8.2,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A knowledge-based two-population optimization algorithm for distributed heterogeneous assembly permutation flowshop scheduling with batch delivery and setup times 一种基于知识的异构装配排列流水调度的双种群优化算法

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-06-10 DOI: 10.1016/j.swevo.2025.102035

Cai Zhao , Lianghong Wu , Weihua Tan , Cili Zuo

{"title":"A knowledge-based two-population optimization algorithm for distributed heterogeneous assembly permutation flowshop scheduling with batch delivery and setup times","authors":"Cai Zhao , Lianghong Wu , Weihua Tan , Cili Zuo","doi":"10.1016/j.swevo.2025.102035","DOIUrl":"10.1016/j.swevo.2025.102035","url":null,"abstract":"<div><div>Distributed heterogeneous assembly factory environment has become the mainstream of manufacturing enterprises in the real world. Constraints such as batch delivery and setup time are often involved in this distributed heterogeneous assembly environment. To address the problems of low solution quality and slow convergence due to the coupling of these constraints, this paper proposes a Knowledge-Based Two-Population Optimization algorithm (KBTPO) to solve the Distributed Heterogeneous Assembly Permutation Flowshop Scheduling Problem with Batch Delivery and Setup Time (DHAPFSP-BD-ST) with the objective of minimizing inventory and tardiness costs. The algorithm adopts a memetic algorithm as the primary search framework, with reinforcement learning algorithm assisting in collaborative search. The strategy based on knowledge representation and transfer is used to strengthen the communication between populations to accelerate the convergence and improve the efficiency of the algorithm. In addition, several local search operators specific to the problem are designed to enhance the development ability of the algorithm. Comparative experiments show that KBTPO is superior to advanced algorithms in convergence speed and quality. This algorithm is very suitable to solve the distributed heterogeneous scheduling scenarios in the real world, and has9 important significance for the actual manufacturing scheduling optimization.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"97 ","pages":"Article 102035"},"PeriodicalIF":8.2,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144253814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Pruning for efficient DenseNet via surrogate-model-assisted genetic algorithm considering neural architecture search proxies 考虑神经结构搜索代理的代理模型辅助遗传算法对高效DenseNet进行剪枝

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-06-10 DOI: 10.1016/j.swevo.2025.101983

Jingeun Kim , Yourim Yoon

{"title":"Pruning for efficient DenseNet via surrogate-model-assisted genetic algorithm considering neural architecture search proxies","authors":"Jingeun Kim , Yourim Yoon","doi":"10.1016/j.swevo.2025.101983","DOIUrl":"10.1016/j.swevo.2025.101983","url":null,"abstract":"<div><div>Recently, convolution neural networks have achieved remarkable progress in computer vision. These neural networks have a large number of parameters, which should be limited in resource-constrained environments. To address this problem, new pruning approaches have explored using neural architecture search (NAS) to determine optimal subnetworks. We propose a novel pruning framework using a surrogate model-assisted genetic algorithm considering NAS proxies (SMA-GA-NP). We applied multi-dimensional encoding and designed crossover and mutation methods. To reduce the search time of NAS, we leveraged a surrogate model to approximate the fitness value of individuals and used NAS proxies, such as reducing the number of epochs and the training set size. The DenseNet-BC (<em>k</em> <span><math><mo>=</mo></math></span> 12) model was used as the baseline. We achieved highly competitive performance on CIFAR-10 compared with other GA-based pruning methods and baselines. For CIFAR-100, we reduced the number of parameters by 11.25% to 18.75%, while achieving less than 1% performance degradation compared to the baseline model. These findings highlight SMA-GA-NP’s effectiveness in significantly reducing the number of parameters while having a negligible impact on the model’s performance. We also conducted an ablation study to explore the efficiency of the GA settings, the surrogate model, and NAS proxies in SMA-GA-NP and identified the current limitations and future potential of SMA-GA-NP.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"97 ","pages":"Article 101983"},"PeriodicalIF":8.2,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144253903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A dynamic multi-objective optimization evolutionary algorithm based on classification of decision variables and inter-layer collaborative prediction 基于决策变量分类和层间协同预测的动态多目标优化进化算法

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-06-10 DOI: 10.1016/j.swevo.2025.102012

Yu Wang, Yongjie Ma

{"title":"A dynamic multi-objective optimization evolutionary algorithm based on classification of decision variables and inter-layer collaborative prediction","authors":"Yu Wang, Yongjie Ma","doi":"10.1016/j.swevo.2025.102012","DOIUrl":"10.1016/j.swevo.2025.102012","url":null,"abstract":"<div><div>The Dynamic Multi-objective Optimization Evolutionary Algorithm (DMOEA) demonstrates outstanding performance in addressing complex Dynamic Multi-objective Optimization Problems (DMOPs). However, existing DMOEAs lack a mechanism for classifying decision variables, which makes it challenging for the population generated by the response mechanism to achieve a balance between convergence and diversity, thereby compromising the algorithm’s overall optimization performance. For this reason, this work presents a DMOEA based on decision variable classification and inter-layer collaborative prediction. First, the algorithm classifies decision variables into two types (elite decision variables and routine decision variables) by detecting their characteristics and designs corresponding response mechanisms for different variables. Second, an inter-layer collaborative prediction strategy based on the Gate Recurrent Unit (GRU) model is proposed to handle routine decision variables, while elite decision variables are optimized using a Latin Hypercube Sampling (LHS) strategy. Subsequently, the two types of optimized variables are combined to form the final predicted population. Finally, a population re-optimization strategy (including dominant solution filtering and adaptive mutation) is proposed to finely optimize the predicted population, thereby further improving prediction accuracy. Through experiments on 24 test functions with seven high-performance DMOEAs, it is demonstrated that the algorithm has significant advantages in both convergence and diversity.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"97 ","pages":"Article 102012"},"PeriodicalIF":8.2,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144253904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GEFS-AO: A novel graph-based evolutionary feature selection method from the view of auxiliary optimization GEFS-AO：一种从辅助优化角度出发的基于图的进化特征选择方法

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-06-09 DOI: 10.1016/j.swevo.2025.101995

Kaixuan Li , Ying Sun , Mingming Xia , Chao Wang , Changjun Zhou , Fan Cheng

{"title":"GEFS-AO: A novel graph-based evolutionary feature selection method from the view of auxiliary optimization","authors":"Kaixuan Li , Ying Sun , Mingming Xia , Chao Wang , Changjun Zhou , Fan Cheng","doi":"10.1016/j.swevo.2025.101995","DOIUrl":"10.1016/j.swevo.2025.101995","url":null,"abstract":"<div><div>Graph-based evolutionary feature selection (FS) algorithms attract much attention, since they can simultaneously utilize the advantages of graph and evolutionary computation for solving FS problem. Despite that, due to the encoding of evolutionary algorithms, they often need to search in a complex and large feature graph space. To this end, these algorithms develop different evolutionary operators to overcome the challenge. Unlike the existing algorithms that directly deal with complex optimization problem, this paper tackles the problem from the perspective of auxiliary optimization, where the original complex optimization problem is decomposed into two simple yet complementary auxiliary optimization subproblems. Specifically, in the proposed algorithm (GEFS-AO), a fully connected feature graph is firstly constructed, from which two simple auxiliary feature subgraphs are created. One subgraph only uses some important nodes (features) and all their edges, which ensures the latent important feature combinations could be detected. Another subgraph uses all the nodes and each node only has one edge, which guarantees all features are considered. On each subgraph, a population is evolved to obtain its feature subsets, which is viewed as one auxiliary optimization subproblem. During the evolution, a pair of information exchanging strategies is designed between two auxiliary optimizations, which can adjust the structures of two auxiliary subproblems and improve the performance of both auxiliary optimization subproblems. Moreover, a node weight update strategy is also suggested for two auxiliary subgraphs, which further enhances the quality of final feature subsets. Experimental results on different FS datasets demonstrate the effectiveness of the proposed GEFS-AO.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"97 ","pages":"Article 101995"},"PeriodicalIF":8.2,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144241384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An enhanced LSHADE-based algorithm for global and constrained optimization in applied mechanics and power flow problems 应用力学和潮流问题的全局约束优化改进lshade算法

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-06-09 DOI: 10.1016/j.swevo.2025.102032

Karam M. Sallam , Ibrahim Alrashdi , Reda Mohamed , Mohamed Abdel-Basset

{"title":"An enhanced LSHADE-based algorithm for global and constrained optimization in applied mechanics and power flow problems","authors":"Karam M. Sallam , Ibrahim Alrashdi , Reda Mohamed , Mohamed Abdel-Basset","doi":"10.1016/j.swevo.2025.102032","DOIUrl":"10.1016/j.swevo.2025.102032","url":null,"abstract":"<div><div>This study proposes a new evolutionary algorithm, namely NL-SHADE, that combines the linear population size reduction-based SHADE (L-SHADE) with the Nutcracker Optimization Algorithm (NOA) to better solve global optimization and real-world constrained optimization problems. Several optimization algorithms have been developed in the literature to address these issues. However, they still stall in local optima and exhibit slow convergence speed, which are the main limitations that motivate us to propose the NL-SHADE algorithm. In this algorithm, the SHADE algorithm is responsible for the exploration operator in the early stages of the optimization process to avoid stagnation in local optima, while NOA is responsible for improving convergence speed. Furthermore, at the end of each generation, the linear population size reduction method is used to exclude some inferior solutions that might lead to local optima and reduce convergence speed. To solve the constrained optimization problems, NL-SHADE is combined with a gradient-based repair method to propose a new variant, rNL-SHADE, which uses gradient information from the constraint set to direct infeasible solutions into feasible regions. In this study, two experiments are conducted. In the first experiment, the proposed NL-SHADE is evaluated using two unconstrained CEC benchmarks, CEC2017 and CEC2020, and compared with numerous cutting-edge algorithms using several performance metrics. In the second experiment, the performance of the proposed algorithms is also tested by solving 29 RWC optimization problems from four different domains. The experimental findings demonstrate that, for the majority of the solved RWC problems, rNL-SHADE can perform better than all compared algorithms.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"97 ","pages":"Article 102032"},"PeriodicalIF":8.2,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144241383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic instance sampling for multi-objective automatic algorithm configuration 动态实例采样的多目标自动算法配置

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-06-08 DOI: 10.1016/j.swevo.2025.102008

Yuchen Li, Handing Wang

{"title":"Dynamic instance sampling for multi-objective automatic algorithm configuration","authors":"Yuchen Li, Handing Wang","doi":"10.1016/j.swevo.2025.102008","DOIUrl":"10.1016/j.swevo.2025.102008","url":null,"abstract":"<div><div>Multi-objective automatic algorithm configuration alleviates the tedious parameter tuning for users by optimizing both the performance and efficiency of the target algorithm. Its evaluation requires performing multiple runs for each configuration on an instance set, making the computational cost expensive. Especially for real-world application problems, it is crucial to reduce computational costs under limited budgets. However, when the instance set is large, model-based approaches struggle to further reduce the high cost of configuration evaluations, which remains a significant challenge. To address this, we propose a Kriging-assisted Two_Arch2 with dynamic instance sampling algorithm, which aims to reduce the high costs of configuration evaluations by lowering the fidelity of the evaluations. Specifically, we align the number of evaluation instances with the evaluation fidelity and design a dynamic instance sampling strategy to effectively control the frequency of new instance sampling, enabling fidelity switching. Moreover, a trade-off configuration selection method is proposed to assist users in choosing configurations when preferences are unclear. The proposed method has been tested on numerous instances from the BBOB benchmark suite. The experimental results demonstrate that the performance of the proposed algorithm outperforms other state-of-the-art methods.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"97 ","pages":"Article 102008"},"PeriodicalIF":8.2,"publicationDate":"2025-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144241381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Train energy-efficient speed profile generation under various track alignments: a quantum evolutionary algorithm with cosine annealing 不同轨道对准下列车节能速度线生成：余弦退火的量子进化算法

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-06-07 DOI: 10.1016/j.swevo.2025.102027

Yang Qin , Jingwei Guo , Peijuan Xu , Duo Li , Yonggang Wang

{"title":"Train energy-efficient speed profile generation under various track alignments: a quantum evolutionary algorithm with cosine annealing","authors":"Yang Qin , Jingwei Guo , Peijuan Xu , Duo Li , Yonggang Wang","doi":"10.1016/j.swevo.2025.102027","DOIUrl":"10.1016/j.swevo.2025.102027","url":null,"abstract":"<div><div>The optimization of train speed profiles is an effective method for reducing energy consumption and operating costs for urban rail transit (URT). In recent years, numerous intelligent optimization algorithms have been employed to generate high-quality solutions for speed profile optimization models. However, most previous studies preset the train operation sequence, overlooking the complex impacts of track alignment diversity on train operation modes. This limitation hinders the applicability of these findings across multiple inter-stations within the URT network. Moreover, there has been insufficient validation of the proposed optimization algorithms under diverse train operation scenarios. This study reformulates the generation of train speed profiles as a multi-stage decision-making problem within a continuous speed space. By applying the law of conservation of energy, a dynamic model of the train operation process is established and the decision evolution of the train speed is mapped into a high-dimensional quantum space. Subsequently, an improved quantum evolutionary algorithm with adaptive rotation strategies is designed using the cosine annealing function (CA-QEA). Furthermore, a conditional quantum collapse mechanism is introduced to enhance the global search capability of the algorithm. Utilizing actual URT data from Tianjin, China, three test scenarios featuring various track alignments, including gentle slopes, energy-saving slopes, and multiple continuous steep slopes, are constructed. The results demonstrate that the proposed method can effectively reduce the traction energy consumption (TEC) in three different track alignment. The Friedman non-parametric test results indicate that the performance of CA-QEA surpasses that of several mature intelligent optimization algorithms.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"97 ","pages":"Article 102027"},"PeriodicalIF":8.2,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144231890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Front guided surrogate-assisted evolutionary algorithm with adaptive selection of three-branch infill criteria for expensive many-objective optimization 基于自适应选择三分支填充准则的前沿引导代理辅助进化算法用于昂贵的多目标优化

IF 8.2 1区计算机科学

Swarm and Evolutionary Computation Pub Date : 2025-06-07 DOI: 10.1016/j.swevo.2025.101982

Yi Jiao Xu , Sheng Xin Zhang , Jie Lin , Shao Yong Zheng , Xian Hua Dai

{"title":"Front guided surrogate-assisted evolutionary algorithm with adaptive selection of three-branch infill criteria for expensive many-objective optimization","authors":"Yi Jiao Xu , Sheng Xin Zhang , Jie Lin , Shao Yong Zheng , Xian Hua Dai","doi":"10.1016/j.swevo.2025.101982","DOIUrl":"10.1016/j.swevo.2025.101982","url":null,"abstract":"<div><div>Expensive optimization problems are those where a single function evaluation takes a large amount of time, and are typically only allowed for a finite number of function evaluations. Thus, algorithms are extremely limited in the computational resources, and need to balance their ability of promoting convergence with of maintaining diversity. Especially when coping with many-objective optimization problems where the conflict between the two demands is further exacerbated, adaptive strategies that can promptly adjust computational resources according to the state of the population are of particular importance. To effectively solve expensive many-objective optimization problems with different characteristics, we propose a front guided surrogate-assisted evolutionary algorithm with adaptive selection of three-branch infill criteria (FGSAEA). FGSAEA consists of the front guided adaptive selection strategy and three infill criteria, all of which are featured by the positional relationship between the front of the candidate population and the archive storing truly evaluated solutions. FGSAEA uses the front guided adaptive selection strategy to determine the evolutionary state. To reduce the interference from inaccurate predictions of surrogate models, the strategy always takes the front of an archive storing all evaluated solutions as a reference. Then, FGSAEA utilizes one of three infill criteria respectively focused on promoting the convergence, the diversity of population, or the accuracy of surrogate models according to the demands. Experiments on benchmark problems demonstrate that FGSAEA is very competitive compared to state-of-the-art surrogate-assisted expensive many-objective optimization algorithms.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"97 ","pages":"Article 101982"},"PeriodicalIF":8.2,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144231889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0