A New Evolutionary Algorithm Based on Self-Adaptive Grouping and Efficient Resource Allocation

Abstract

To solve large scale optimization problem, a new evolutionary algorithm using variable grouping and allocating computational resource based on contribution is proposed in this paper. First, we propose a new grouping scheme in which we adopt an existing and effective one called FBG for separable problems and design a new grouping scheme called a self-adaptive grouping (SAG) method for non-separable problems. By using these two schemes, any large scale problem can be effectively divided into small scale sub-problems. Second, in order to solve the sub-problems efficiently by making full use of limited computational resource, we design an efficient resource allocation method (ERA) which can reasonably allocate the resource to each sub-problem according to its contribution. The more contribution a sub-problem gives to whole problem, the more resource the sub-problem will get. Based on these, a new evolutionary algorithm is proposed. Finally, the experiments are conducted on widely used benchmark suite CEC'2010, and the proposed algorithm is compared with some state-of-the-art algorithms. The experimental results show the competitive performance of the proposed algorithm to solve these problems.