A Multi-swarm Particle Swarm Optimization with Orthogonal Learning for Locating and Tracking Multiple Optimization in Dynamic Environments

Due to the specificity and complexity of the dynamic optimization problems (DOPs), those excellent static optimization algorithms cannot be applied in these problems directly. So some special algorithms only for DOPs are needed. There is a multi-swarm algorithm with a better performance than others in DOPs, which utilizes a parent swarm to explore the search space and some child swarms to exploit promising areas found by the parent swarm. In addition, a static optimization algorithm OLPSO is so attractive, which utilize an orthogonal learning (OL) strategy to utilize previous search information (experience) more efficiently to predict the positions of particles and improve the convergence speed. In this paper, we bring the essence of OLPSO called OL strategy to the multi-swarm algorithm to improve its performance further. The experimental results conducted on different dynamic environments modeled by moving peaks benchmark show that the efficiency of this algorithm for locating and tracking multiple optima in dynamic environments is outstanding in comparison with other particle swarm optimization models, including MPSO, a similar particle swarm algorithm for dynamic environments.