自适应混沌整体退火遗传算法在水电站群优化调度中的应用  

Application of self-adaptive chaos whole annealing genetic algorithm to optimal operation of hydropower station groups

作　　者：王森[1,2] 程春田[1] 武新宇[1] 李保健[1] 

机构地区：[1]大连理工大学水电与水信息研究所,辽宁大连116024 [2]珠江水利科学研究院,广州510611

出　　处：《水力发电学报》2014年第5期63-71,共9页Journal of Hydroelectric Engineering

基　　金：国家重点基础研究发展计划("973"计划)(2013CB035906);国家自然科学基金(51109024)

摘　　要：提出了一种基于标准遗传算法(SGA)的自适应混沌整体退火遗传算法(SCWAGA)求解梯级水电站群长期发电优化调度问题。该算法通过混沌优化生成初始解,提高初始解的质量;采用父代参与竞争的整体退火选择方式,避免种群早熟及过早收敛;利用参数自适应函数调整交叉算子和变异算子,提高算法的收敛速度以及避免算法陷入局部最优。以红水河流域水电站群为计算实例的研究结果表明,SCWAGA比SGA具有更快的收敛速度,且搜索到的全局最优解优于SGA与逐步优化算法(POA),为大规模水电系统优化调度求解提供了一种新的有效途径。A self-adaptive chaos whole annealing genetic algorithm （SCWAGA） based on simple genetic algorithm （SGA） is presented to solve long-term optimal operation problems of power generation. In SCWAGA, chaos optimization is used for improving the quality of initial solutions and the Boltzmann probability selection is adopted to avoid population precocity. In addition, crossover probability and mutation probability are adjusted constantly with a self-adaptive function to improve convergence speed and avoid local trapping. Application to a hydropower station group on the Hongshui River shows that SCWAGA converges faster than SGA and gives better searching for global solution than SGA or POA. This method provides a new approach to solution of optimal operation problem for large-scale hydropower system.

关 键 词：水电工程 水电站群 发电优化调度 自适应 混沌 整体退火遗传算法 

分 类 号：TV976.1[水利工程—水利水电工程]