Random neighbor elite guided differential evolution for global numerical optimization

Abstract

Optimization problems not only become more and more ubiquitous in various fields, but also become more and more difficult to optimize nowadays, which seriously challenge the effectiveness of existing optimizers like different evolution (DE). To effectively solve this kind of problems, this paper proposes a random neighbor elite guided differential evolution (RNEGDE) algorithm. Specifically, to let individuals explore and exploit the solution space properly, a novel random neighbor elite guided mutation strategy named “DE/current-to-rnbest/1” is first proposed to mutate individuals. In this mutation strategy, several individuals randomly selected from the population for each individual to be updated along with the individual itself form a neighbor region, and then the best one in such a region is adopted as the guiding exemplar to mutate the individual. Due to the random selection of neighbors and the directional guidance of elites, this strategy is expected to direct individuals to promising areas fast without serious loss of diversity. Notably, it is found that two popular mutation strategies, namely “DE/current-to-best/1” and “DE/current-to-pbest/1”, are two special cases of the proposed “DE/current-to-rnbest/1”. Further, to alleviate the sensitivity of the proposed algorithm to the involved parameters, this paper utilizes the Gaussian distribution and the Cauchy distribution to adaptively generate parameter values for each individual with the mean value of the Gaussian distribution and the position value of the Cauchy distribution adaptively adjusted based on the evolutionary information of the population. With the above two techniques, the proposed algorithm is expected to effectively search the solution space. At last, extensive experiments conducted on one widely used benchmark function set with three different dimension sizes demonstrate that the proposed algorithm achieves highly competitive or even much better performance than several compared state-of-the-art peer methods.