一种基于微粒群思想的蚁群参数自适应优化算法

A kind of ant colony parameter adaptive optimization algorithm based on particle swarm optimization thought

利用微粒群优化(particle swarm optimization,PSO)思想对蚁群优化(ant colony optimization,ACO)算法的参数取值进行优化选择。通过微粒群粒子搜索,自适应选取参数值的优质组合,使ACO算法的参数取值不必依靠人工经验或反复试验。经过该算法求取的参数组合显著提高了ACO算法的优化性能,并且参数的取值具有连续性,随机性和精确性。利用这种算法获得的参数值的优质组合反馈回ACO算法中,在解决货郎问题(traveling sales-man problem,TSP)时具有优异的效果。

The parameter values of the ant colony optimization（ACO） algorithm was optimized based on particle swarm optimization（ PSO） thought .Through the high-quality combination of the particles search and adaptive selection of param-eter values,the ACO algorithm parameter values could be selected without relying on human experience or trial and error of artificial selection.The parameter combination obtained from the algorithm could significantly improve the performance of the ACO algorithm and give parameter values in continuity,randomness and accuracy.By using the high-quality combi-nation of parameter values feedback to the ACO algorithm,this algorithm can work well in solving traveling salesman prob-lem（TSP） with excellent results.