Multi-swarm optimization algorithm for dynamic optimization problems using forking

Inspired by a forking mechanism, a new multi-swarm optimization algorithm is proposed for addressing dynamic optimization problems in this paper. In this algorithm, a larger main swarm is continuously responsible for searching for new peaks and a number of smaller child swarm, divided from main swarm, are used to track the achieved peaks over time. Experimental study over a benchmark dynamic problem suggests that the proposed algorithm always exhibits stronger robustness and adaptability in dynamic environments.