Performance Estimation of Differential Evolution, Particle Swarm Optimization and Cuckoo Search Algorithms

Most design optimization problems in engineering are in general extremely nonlinear and deal with various design variables under complex restrictions. Traditional mathematical optimization procedure may fail to find the optimum solution to real-world problems. Evolutionary Algorithms (EAs) can serve as an efficient approach for these types of optimization problems. In this paper, Particle Swarm Optimization (PSO), Differential Evolution (DE) and Cuckoo Search (CS) algorithms are used to find the optimal solution for some typical unimodal and multimodal benchmark functions. The source codes of all these algorithms are developed using C language and tested on a core i5, 2.4 GHz processor with 8 GB internal RAM. PSO algorithm has a simplicity of implementation and good convergence speed. In contrast, CS algorithm has good ability to find a global optimum solution. To use the advantages of CS and PSO algorithms, a hybrid algorithm of CS and PSO (CSPSO) is implemented and tested with the same benchmark functions. The experimental simulation results obtained by all these algorithms show that hybrid CSPSO outperforms with PSO, DE and CS algorithms.