《計算機應用研究》|Application Research of Computers

基于分解和多策略變異的多目標差分進化算法

Multi-objective differential evolution algorithm based on decomposition and multi-strategy mutation

免費全文下載 (已被下載 次)  
獲取PDF全文
作者 童旅楊,董明剛,敬超
機構 桂林理工大學 a.信息科學與工程學院;b.廣西嵌入式技術與智能系統重點實驗室,廣西 桂林 541004
統計 摘要被查看 次,已被下載
文章編號 1001-3695(2019)07-008-1955-05
DOI 10.19734/j.issn.1001-3695.2018.01.0028
摘要 差分進化是一種有效的優化技術,已成功應用于多目標優化問題,但也存在Pareto最優集合的收斂慢和多樣性差等問題。針對上述不足,提出了一種基于分解和多策略變異的多目標差分進化算法(MODE/DMSM)。該算法利用基于分解的方法將多目標優化問題分解為多個單目標優化問題;通過高效的非支配排序方法選擇具有良好收斂性和多樣性的解來指導差分進化過程;采用了多策略變異方法來平衡進化過程中的收斂性和多樣性。在ZDT和DTLZ的10個測試函數上的仿真結果表明,所提算法在Parato最優集合的收斂性和多樣性方面優于其他六種代表性多目標優化算法。
關鍵詞 多目標優化; 差分進化; 分解; 多策略變異
基金項目 國家自然科學基金資助項目(61563012,61203109)
廣西自然科學基金資助項目(2014GXNSFAA118371,2015GXNSFBA139260)
廣西嵌入式技術與智能系統重點實驗室基金資助項目
本文URL http://www.oirznw.live/article/01-2019-07-008.html
英文標題 Multi-objective differential evolution algorithm based on decomposition and multi-strategy mutation
作者英文名 Tong Lyuyang, Dong Minggang, Jing Chao
機構英文名 a.College of Information Science & Engineering,b.Guangxi Key Laboratory of Embedded Technology & Intelligent System,Guilin University of Technology,Guilin Guangxi 541004,China
英文摘要 Differential evolution algorithm is an efficient optimization technique that has been successfully applied to multiobjective optimization problems. However, there are also some defects, i. e. the slow convergence and poor diversity of the Pareto optimal set. Addressing these issues, this paper presented a multi-objective differential evolution algorithm based on decomposition and multi-strategy mutation(MODE/DMSM). MODE/DMSM utilized the decomposition-based approach to decompose a multi-objective optimization problem into multiple single-objective optimization problems. Moreover, MODE/DMSM adopted the efficient non-dominated sorting approach to select solutions which had both good convergence and diversity to guide the differential evolutionary process. Eventually, MODE/DMSM employed the multi-strategy mutation approach to balance the convergence and diversity in the evolutionary process. The results of simulations on 10 test functions of ZDT and DTLZ show that MODE/DMSM outperforms than the other six representative multi-objective optimization algorithms in terms of the good convergence and diversity of the Pareto optimal set.
英文關鍵詞 multi-objective optimization; differential evolution(DE); decomposition; multi-strategy mutation
參考文獻 查看稿件參考文獻
 
收稿日期 2018/1/17
修回日期 2018/3/9
頁碼 1955-1959,1990
中圖分類號 TP18;TP301.6
文獻標志碼 A
水果机返水