|
|
リ カセイ
Ri Kasei 李 嘉誠 所属 神奈川大学 情報学部 システム数理学科 職種 助教 |
|
言語種別 | 英語 |
発行・発表の年月 | 2022/10 |
形態種別 | 学術雑誌 |
査読 | 査読あり |
招待論文 | 招待あり |
標題 | A dynamic mutation particle swarm optimization algorithm |
執筆形態 | 共著 |
掲載誌名 | RACS '22: Proceedings of the Conference on Research in Adaptive and Convergent Systems |
掲載区分 | 国外 |
出版社・発行元 | ACM |
巻・号・頁 | pp.33-38 |
著者・共著者 | Yang Zhang, Jiacheng Li, Lei Li |
概要 | In view of the drawbacks of the conventional particle swarm optimization algorithm, such as the ease of falling into local extreme values, poorer diversity, and slower convergence speed in subsequent optimization, a dynamic mutation particle swarm optimization algorithm (DMPSO) is proposed. On the basis of the characteristics of the particle swarm optimization algorithm, such as a fast convergence speed and simple mechanism, the mutation mechanism of the genetic algorithm is introduced. We redesigned the dynamic inertia weight and mutation rate, and we added a ratio adjustment formula for speed, which accelerates the convergence speed of the algorithm and improves its optimization performance. In an experiment, six benchmark functions were selected for an optimization test, and the results show that the proposed method has a faster convergence speed and better optimization performance. |