Particle swarm optimization with adaptive elite opposition-based learning for large-scale problems

Abstract

A novel particle swarm optimization with elite opposition-based learning algorithm is proposed in an attempt to improve the performance on solving large-scale optimization problems (LSOP) in maximum power point tracking (MPPT) of photovoltaic system. The standard particle swarm optimization (PSO) algorithm shows its weakness on LSOP, such as easily falling into local optimum, slow convergence and low accuracy at later evolution process. Therefore, this paper develops a modified PSO algorithm based on elite opposition-based learning mechanism and adaptive multi-context cooperatively coevolving (AM-CC) framework. In every iteration, the current high-priority individuals execute dynamic generalized opposition-based learning to generate their opposite solutions which enhance the ability of local exploration and help the particles escape from local optimum. The simulation experiments are conducted on a comprehensive set of benchmarks (up to 2000 real-valued variables), as well as on a large-scale MPPT application. Compared with some state-of-the-art variants of PSO and differential evolution (DE), the results show that the improved algorithm has higher convergence speed and accuracy. Besides, it can avoid premature phenomenon effectively and is suitable to solve the large-scale optimization problem.