Parameter tuning of ant system using fuzzy logic controller

Abstract

This paper examines the tuning of ant system's (AS's) parameters using fuzzy logic controller (FLC). Particularly, four basic parameters of the AS algorithm are tuned using FLC, i.e. number of ants, pheromone information parameter, heuristic information parameter and evaporation rate. The algorithm with FLC is tested using several unequal area facility layout problems which are modelled as flexible bay structures. The results are compared with the ones obtained from manual parameter tuning. The comparison shows that the AS algorithm can benefit from the use of FLC by omitting the need to specify its parameter values. It also shows that FLC can potentially lead to better results.