化学反应蚁群优化算法  

Chemical reaction ant colony optimization algorithm

作　　者：杨振[1] 周晖[1] 朱立庆 李逶[1] 

机构地区：[1]南通大学电子信息学院,江苏南通226019

出　　处：《计算机应用研究》2014年第10期2925-2927,2946,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(61071086);江苏省教育厅资助项目(2011SJB630048);南通大学资助项目(09zw001;03080529)

摘　　要：针对化学反应优化对反馈信息利用不足导致后期求解效率低的问题,提出化学反应蚁群优化算法。该算法利用化学反应优化生成较优解,通过信息素转换策略将较优解转换为蚁群算法的初始信息素,最后由蚁群算法累积更新信息素得到最优解。以TSP为例进行仿真,结果表明,与化学反应优化、蚁群算法、模拟退火算法相比,所提算法具有更高的寻优能力、收敛效率和计算效率。Aiming at the problem of feedback information under-utilization lead to the low efficiency in the chemical reaction opti- mization, this paper presented chemical reaction ant colony optimization algorithm（CRACA）. Firstly, the hybrid algorithm gene- rated the distribution of the pheromone by chemical reaction optimization （CRO）. Then it converted the solution of chemical reac- tion optimization to the initial pheromone of ant colony optimization （ACO） via the transformation strategy. Finally it obtained the optimal solution through the cumulative update of the pheromone of ACO. It took the traveling salesman problem for example, the simulation results show, compared with the CRO, ACO, simulated annealing algorithm, the algorithm has higher convergence ability, convergence efficiency and computational efficiency.

关 键 词：自然计算 化学反应优化 蚁群算法 混合策略 旅行商问题 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]