基于免疫进化的蚁群算法在梯级水库优化调度中的应用研究  

Application of Ant Colony Optimization Based on Immune Evolutionary Algorithm for Cascade Reservoirs Optimal Operation

作　　者：原文林[1] 黄强[1] 万芳[1] 

机构地区：[1]西安理工大学西北水资源与环境生态教育部重点实验室,陕西西安710048

出　　处：《西安理工大学学报》2008年第4期395-400,共6页Journal of Xi'an University of Technology

基　　金：国家自然科学基金资助项目(50779053);陕西省自然科学基金资助项目(2006D09)

摘　　要：针对蚁群算法在求解过程中出现初期信息素匮乏、易陷入局部最优解的问题,结合梯级水库优化调度的特点,提出了基于免疫进化的蚁群算法。该混合算法充分利用了免疫进化算法的全局快速收敛性和蚁群算法的正反馈性,提高了求解效率。实例计算表明该混合算法在求解梯级水库优化调度问题时,与逐次逼近动态规划相比较,结果合理、可靠,计算效率较高,从而为求解高维、复杂的梯级水库优化调度提供了一条新的求解思路。Aiming at the problems of lack of pheromone at initial stage and trapping in locally optimal solution of ant colony optimization, a hybrid algorithm that ant colony optimization based on immune evolu- tionary algorithm is presented according to the Characteristics of Cascade Reservoirs Optimal Operation. This new hybrid algorithm can combine the characteristics of global searching ability of immune evolutionary algorithm with positive feedback of ant colony optimization so as to improve solution efficiency. A practical example calculation shows that the results of this new hybrid algorithm is rational and reliable and high efficient when it is used to solve the problem of optimal operation of cascade reservoirs and to compare with dynamic programming successive approximation, whereby a new way for searching the solution to the optimal oparation of cascade reservoirs with high demension and complexity is provided.

关 键 词：梯级水库 优化调度 蚁群算法 免疫进化算法 逐次逼近动态规划 

分 类 号：TV697.4[水利工程—水利水电工程]