A Hybrid Evolutionary Algorithm Based on Alopex and Estimation of Distribution Algorithm and Its Application for Optimization

Alopex is a correlation-based algorithm, which shares characteristics of both gradient descent approach and simulated annealing. It has been successfully applied to continuous and combinatorial optimization problems for years. Estimation of Distribution Algorithms (EDAs) is a class of novel evolutionary algorithms (EAs) proposed in recent years. Compared with the traditional EAs, it possesses unique evolutionary characteristics. In this paper, a hybrid evolutionary algorithm (EDA-Alopex) is proposed, which integrates the merits of both Alopex and EDA, and obtains more evolutionary information than these two approaches. The new algorithm is tested with several benchmark functions; numerical case study results demonstrate that EDA-Alopex outperforms both EDA and AEA, especially for the complex multi-modal functions. Finally, the proposed algorithm is investigated on high-dimensional and multi-peaks benchmark functions, and it also achieves satisfactory results.