A Differential Evolution with Replacement Strategy for Real-Parameter Numerical Optimization

Differential Evolution (DE) has been widely used as a continuous optimization technique for several problems like electromagnetic optimization, bioprocess system optimization and so on. However, during the optimization process, DE´s population may stagnate local optima where the algorithm has to spend a large number of function evaluations to get rid of them. This paper presents an improved DE algorithm (denoted as RSDE) which combines two Replacement Strategies (RS). The motivation of RS is that replacing an unimproved individual and replacing a premature population using RS which can enhance the DE exploitation performance and exploration performance respectively. We tested the RSDE performance using the newly Single Objective Real-Parameter Numerical Optimization problems provided by the CEC 2014 Special Session and Competition. Moreover, computational results, convergence figures and the performance of these two RS will be presented to discuss the feature of RSDE.