A Hybrid Evolutionary Algorithm for Solving Function Optimization Problems

Abstract

This paper proposes a hybrid evolutionary algorithm based on DE and TLBO (HDT). The HDT algorithm independently evolved the two sub populations of DE and TLBO to preserve the diversity of population. In every generation of evolution, we first get a composite individual from current best individuals of the two sub populations, then we use search guide of composite individual to remain the variety of population and to achieve complementary advantages of DE and TLBO. Experiments have been conducted on 13 benchmark problems. Empirical results fully demonstrate the effectiveness and competitiveness of the proposed hybrid evolutionary algorithm.