Study On Self-adjusting Parameter Method Of Heuristic Algorithm

Heuristic algorithm is a hot issue both at home and abroad, heuristic algorithm has been widely used in various fields. The cuckoo algorithm, the firefly algorithm is the rapid rise of the heuristic algorithm in recent years. The parameter settings of the heuristic algorithm, many of which have been tried many times, but have defects.The setting of parameters directly affects the performance of the algorithm, so the optimal parameter setting is a problem worthy of studying.In this paper choose the cuckoo algorithm and the firefly algorithm to adjust the parameters. so can improve the algorithm, and promote the development of heuristic algorithm. The main research results are as follows:(1) Introduce the background of the heuristic algorithm, research significance and current situation of research at home and abroad, and simply introduces the research foundation, namely the cuckoo search algorithm and firefly algorithm. And through the research on the parameters of the heuristic algorithm, the method of adjusting the parameters is summarized.(2) A new algorithm which introduce the simulated annealing idea to cuckoo search algorithm and Gaussian disturbance to the individuals is proposed. A cuckoo search algorithm based on simulated annealing and Gaussian disturbance, simulation results show that the new algorithm can search for global optimization more quickly and precisely.(3) A new algorithm which introduce the cooperative evolutionary idea to self-adaptive firefly algorithm is proposed. A self-adaptive firefly algorithm based on multi-swarm cooperative evolutionary, specifically, the population is divided into 2 subgroup and adopt different strategies for 2 subgroup evolution at the same time. Finally the simulation results show that the new algorithm can search for global optimization more quickly and precisely.