An Improved-Time Varying Acceleration Coefficient Based PSO
Prince Bhatia, KK Mishra, Divya Kumar and Anoj Kumar
An improved version of Particle Swarm Optimization – Time Variant Acceleration Coefficient (PSO-TVAC) algorithm is proposed in this paper. A new strategy is introduced in this paper which further improves the performance of existing PSO algorithms. The proposed algorithm varies the parameters (decreasing cognitive acceleration coefficient, increasing social acceleration coefficient, decreasing inertia weight) nonlinearly in velocity vector equation of PSO-TVAC for each iteration. The algorithm is able to cover both the local optimum and global optimum. The performance of the improved PSO-TVAC algorithm is compared with existing PSO algorithms on five well known benchmark test functions and the experimental results prove that the proposed algorithm has better performance.
Keywords: Particle Swarm Optimization, Time-Variant Acceleration Coefficient, Parameter Tuning, Bench mark function, Local Optimum, Global Optimum.