{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/acd-de-an-adaptive-cluster-division","title":"ACD-DE: An adaptive cluster division Differential Evolution for mitigating population diversity deficiency","arxiv_id":null,"date":"2024-06-26","proceeding":"journal 2024 6","authors":["Xin Lin"],"abstract":"Differential Evolution (DE) is a simple but powerful population based evolutionary algorithm, which was widely used to solve various complex optimization problems. However, even recently proposed state-of-the-art DE variants tend to get trapped in local minima due to insufficient population diversity in the later stages of evolution. In this paper, an Adaptive Cluster Division Differential Evolution (ACD-DE) algorithm was proposed to mitigate population diversity deficiency. The main highlights are summarized as follows: Firstly, a novel cluster division based mutation strategy was proposed to enhance the diversity of difference vectors during the mutation operation. Secondly, a population diversity detection indicator was used to assess the stagnation level of individuals, enabling stagnation management to be launched based on different stagnation levels. Thirdly, an effective evolution guidance mechanism was proposed by adjusting certain parameters in the 𝐷-dimensional vectors of outlier individuals that significantly deviate from the current population. Fourthly, novel parameter adaptations were employed to dynamically adjust the control parameters, including the scale factor 𝐹 , crossover rate 𝐶𝑅, and population size 𝑃𝑆, during evolution. To validate the ACD-DE algorithm, extensive experiments were conducted on 88 benchmark functions from the CEC2013, CEC2014, and CEC2017 test suites, focusing on the optimization accuracy, convergence speed, time complexity, and component effectiveness. The results demonstrate the superiority of our ACD-DE algorithm compared to state-of-the-art DE variants.","url_abs":"https://www.sciencedirect.com/science/article/abs/pii/S0020025524010053","url_pdf":"https://www.sciencedirect.com/science/article/abs/pii/S0020025524010053","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"acd-de-an-adaptive-cluster-division","repo_url":"https://github.com/yiran-luu/ACD-DE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}