This paper provides an analysis of the use of Cauchy mutation and Gaussian mutation individually in a popular improved version of particle swarm optimization techniques for the improvement of convergence to final global solution. The particle swarm optimization is one of the famous techniques of swarm intelligence which has exhibited a standard performance in different real world as well as benchmark problems. But it has also some limitations, which forces the researchers to introduce some modifications for improvement of its convergence. In this paper, we propose two enhanced PSO alternate i.e. Cauchy mutated Crazy PSO and Gaussian mutated Crazy PSO, where the concept of Cauchy and Gaussian mutation are introduced respectively. Crazy PSO is one of the widely used modifications of in the earlier improved versions of PSO. Simulation results show that the Cauchy mutated crazy PSO has shown better results in comparison to the Gaussian mutated crazy PSO. The result also shown that both the modifications have exhibited better performance than the normal crazy PSO algorithm. The introduction of Cauchy mutation and Gaussian mutation helps in improvement of the performance of the crazy PSO algorithm which can be easily verified by the variation of dimensions along with population size.
[1]
Ponnuthurai Nagaratnam Suganthan,et al.
Problem Definitions and Evaluation Criteria for CEC 2015 Special Session on Bound Constrained Single-Objective Computationally Expensive Numerical Optimization
,
2015
.
[2]
Hui Wang,et al.
A Hybrid Particle Swarm Algorithm with Cauchy Mutation
,
2007,
2007 IEEE Swarm Intelligence Symposium.
[3]
Shiyou Yang,et al.
A particle swarm optimization-based method for multiobjective design optimizations
,
2005,
IEEE Transactions on Magnetics.
[4]
Lehrstuhl für Elektrische,et al.
Gaussian swarm: a novel particle swarm optimization algorithm
,
2004,
IEEE Conference on Cybernetics and Intelligent Systems, 2004..
[5]
James Kennedy,et al.
Particle swarm optimization
,
2002,
Proceedings of ICNN'95 - International Conference on Neural Networks.
[6]
Sakti Prasad Ghoshal,et al.
Design of optimal linear phase FIR high pass filter using craziness based particle swarm optimization technique
,
2012,
J. King Saud Univ. Comput. Inf. Sci..