点击次数：

论文类型：会议论文

发表时间：2016-08-13

收录刊物：EI、CPCI-S、Scopus

页面范围：87-94

摘要：Cooperative coevolution is effective for solving high-dimensional optimization problems. This paper proposes an adaptive hybrid differential evolution with circular sliding window to tackle the high-dimensional optimization problems. A circular sliding window strategy is proposed to solve the task of the decomposition of the original problem, where the "window" size represents the size of the group, which can be adjusted according to the separability of the problem. Meanwhile, the "window" sliding step can be adjusted according to the activeness of different regions of the problem, thus adjusting the density of the variables. Moreover, we use an adaptive hybrid differential evolution optimization operator that adjusted the parameters adaptively so that the search can move and converge to the global optimum. Simulated experiments were conducted on CEC2008 and CEC2010 benchmarks. The results demonstrate the effectiveness of the proposed algorithm in solving separable and non-separable problems. The results also indicate that it has good scalability.