A set-based locally informed discrete particle swarm optimization

This paper proposed an efficient discrete PSO algorithm. Following the general process of the recently proposed locally informed particle swarm (LIPS), the velocity update of each particle in the proposed algorithm depends on the pbests of its nearest neighbors. However, in order to achieve optimization in discrete space, the related arithmetic operators and the concept of 'distance' in LIPS are redefined based on set theory. Thus, the proposed algorithm is termed Set-based LIPS (S-LIPS). Moreover, a reset scheme is embedded in S-LIPS to further improve population diversity in S-LIPS. By using the locally informed update mechanism and the reset scheme, the proposed algorithm is able to have both high convergence speed and good global search ability. S-LIPS is compared with a set-based comprehensive learning PSO on TSP benchmark instances. The experimental result shows that S-LIPS is a very promising algorithm for solving discrete problems, especially in the case where the scale of the problem is large.