A Computer Immune Optimization Algorithm Based on Group Evolutionary Strategy

摘要

Computer Immune Optimization Algorithm (ClOA) has the advantages of high success rate and good individual diversity compared with other intelligent optimization algorithms. However, it also has the disadvantages of premature convergence and local optimality. To address these shortcomings, this paper proposes a new algorithm, called ESCIOA, which enhances the mutation operation in ClOA, by introducing Recombination Operator and Mutation Operator of Group Evolution Strategy (GES), to achieve more accurate local optimization and faster global optimization. At the same time, this paper describes the implementation steps of ESCIOA, proves the convergence of the algorithm, and gives the comparative experiment. The results show that ESCIOA absorbs the advantages of ClOA and ES, and has the characteristics of not being easy to fall into local extremum, high precision of solution and fast convergence.