Improved Particle Swarm optimization Base on the Combination of Linear Decreasing and Chaotic Inertia Weights
Thamsanqa Bongani Nkwanyana, Zenghui Wang · 2020
Particle swarm optimization (PSO) is one of the uncomplicated optimization algorithm, but it also has its disadvantages, such as premature convergence, it is difficult to get the globally optimal solution and it easily falls into local extremes. In this paper, a new PSO is proposed by combining two types of inertia weights. In order to find a solution for above mentioned disadvantages, the linear decreasing inertia weight is combined with the chaotic inertia weight. The control factor is introduced as an exponential function. The following benchmark functions: Ackley Function, Rastrigin Function, Schwefel Function, Cigar function, Sphere Function, and Booth Function are being used to validate the effectiveness of the improved PSO and the simulation results show that the proposed PSO can achieve promising performance.