2018/01/31 by Sheng Xin Zhang, Zhang, Sheng Xin, Li Ming Zheng +6
Computer Science · #Advanced Multi-Objective Optimization Algorithms #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Metaheuristic Optimization Algorithms Research #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.1801.10546
openalex publication_date 2018/01/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Differential Evolution (DE) is recognized as one of the most powerful\noptimizers in the evolutionary algorithm (EA) family. Many DE variants were\nproposed in recent years, but significant differences in performances between\nthem are hardly observed. Therefore, this paper suggests a multi-layer\ncompetitive-cooperative (MLCC) framework to facilitate the competition and\ncooperation of multiple DEs, which in turns, achieve a significant performance\nimprovement. Unlike other multi-method strategies which adopt a\nmulti-population based structure, with individuals only evolving in their\ncorresponding subpopulations, MLCC implements a parallel structure with the\nentire population simultaneously monitored by multiple DEs assigned to their\ncorresponding layers. An individual can store, utilize and update its evolution\ninformation in different layers based on an individual preference based layer\nselecting (IPLS) mechanism and a computational resource allocation bias (RAB)\nmechanism. In IPLS, individuals connect to only one favorite layer. While in\nRAB, high-quality solutions are evolved by considering all the layers. Thus DEs\nassociated in the layers work in a competitive and cooperative manner. The\nproposed MLCC framework has been implemented on several highly competitive DEs.\nExperimental studies show that the MLCC variants significantly outperform the\nbaseline DEs as well as several state-of-the-art and up-to-date DEs on CEC\nbenchmark functions.\n