HJADE: An Efficient Differential Evolution with Complex Nonlinear Population Size

The differential evolution with optional external archive (JADE) algorithm is a competitive improvement based on differential evolution (DE) algorithm, but it tends to converge to local optima. We propose a new enhancement based on JADE, namely HJADE, which incorporates a strategy of regulating the population size using hybrid functions to strike a more favorable balance between exploration and exploitation. We used 30 problems from the IEEE CEC 2017 benchmark set to assess its implementation and compare HJADE with other JADE-based algorithms using statistical tests. The results show that HJADE exhibits superior performance.