Differential Evolution Algorithm with Winner Mutation Strategy

• Main Authors: HUANG, PO-JUNG, 黃柏融
• Other Authors: YEH,MING-FENG
• Format: Others
• Language: zh-TW
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/46903997150840027616

碩士 === 龍華科技大學 === 電機工程系碩士班 === 101 === Inspired by 2-opt algorithm, this thesis proposes a new mutation strategy, namely winner mutation strategy, for differential evolution (DE) algorithm. The proposed winner mutation strategy could provide a different chance to find a better solution and avoid the algorithm trapping into local minimum. Such a DE algorithm is termed DE/winner hereafter. In addition, the linearly decreasing mutation factor and crossover rate are also applied to DE/winner so as to maintain both local and global search ability throughout the entire evolution process. DE/winner with linearly decreasing mutation factor and crossover rate could further improve the solution accuracy of DE algorithm and prevent the premature convergence in the evolution process. The proposed DE/winner is applied to solve the optimization problems of twelve unimodal and multimodal benchmark functions for demonstrating its search performance. Besides, DE/winner algorithm is also applied to optimize the parameters of proportional-integral-derivative (PID) controller. Simulation and experiment results demonstrate the search ability and control performance of DE/winner algorithm.