A periodic intervention and strategic collaboration mechanisms based differential evolution algorithm for global optimization

Abstract

Differential Evolution (DE) algorithm is a well-known metaheuristic algorithm that features a simple structure and excellent optimization performance. However, it still suffers from premature convergence or stagnation when dealing with complex optimization problems. To avoid these dilemmas in the DE algorithm, we propose a novel DE variant, abbreviated as PISCDE, which is based on periodic intervention and strategic collaboration mechanisms. PISCDE incorporates two types of operations: routine operation and intervention operation. The routine operation employs two mutation strategies with different functional positions to drive the population toward the optimal position. In contrast, the intervention operation uses two intervention strategies with distinct functional roles to restore population diversity and is executed only when a fixed number of iterations is reached. Additionally, to achieve a better balance between global exploration and local exploitation during the optimization process, we propose several strategic collaboration mechanisms. These mechanisms are based on the positioning analysis of different strategies and the interaction analysis between strategies and their corresponding control parameters. To verify the optimization performance of PISCDE, we selected nine comparison algorithms with outstanding optimization performance that have been proposed in the last five years. We used the IEEE CEC 2014 testbed to construct comparative experiments. Based on the comparative results, three conclusions can be drawn: (1) PISCDE has the best overall optimization performance among all the algorithms. (2) PISCDE performs more significantly on complex test problems. (3) PISCDE shows more impressive optimization performance when the dimension of the test problems is increased.