A Multi-swarm Competitive Algorithm Based on Dynamic Task Allocation Particle Swarm Optimization

Abstract

This paper presents a novel multi-swarm competitive algorithm based on the dynamic task allocation particle swarm optimization (MSCPSO-DTA) to solve global optimization problems. The MSCPSO-DTA consists of three main steps. Firstly, we propose a multi-swarm competitive (MSC) schedule to help the stagnant sub-swarm to jump out of local optima. When a certain condition is matched, the stagnant sub-swarm will be reinitialized with a chaotic strategy to begin a new search process in a different part of the search space. Secondly, in order to serve the MSC strategy which will reinitialize the stagnant sub-swarms and need the inertia weight to be increased correspondingly, a novel adaptive inertia weight strategy is proposed based on the maximum distance between the particles. Thirdly, a modified dynamic task allocation (DTA) strategy is adopted to make a better control of the balance between exploitation and exploration; specifically, with the help of the cumulative distribution function of normal distribution, the swarm is automatically divided into two labors to serve different tasks according to the position diversity. A set of benchmark functions are employed to test the performance of the proposed algorithm, as well as the contribution of each strategy employed in improving the performance of the algorithms. Experimental results demonstrate that, compared with other seven well-established optimization algorithms, the MSCPSO-DTA significantly performs the greatest improvement in terms of searching reliability, searching efficiency, convergence speed, and searching accuracy on most of the problems.