A self-tuning firefly algorithm to tune the parameters of ant colony system

摘要: Ant colony system (ACS) is a promising approach which has been widely used in problems such as travelling salesman (TSP), job shop scheduling (JSP) and quadratic assignment (QAP). In its original implementation, parameters of the algorithm were selected by trial error approach. Over last few years, novel approaches have proposed on adapting ACS improving performance. The aim this paper to use framework introduced for self-tuning optimisation algorithms combined with firefly (FA) tune solving symmetric TSP problems. FA optimises problem specific while are tuned itself. With approach, user neither work nor FA. Using common we demonstrate that fits well ACS. A detailed statistical analysis further verifies goodness new over existing also other techniques