基于GA改进算法的多目标机组优化检修计划  

Multi-objective Optimization of Unit Maintenance Scheduling Based on Improved GA

作　　者：苏慧玲[1] 王淳[1] 秦茹静 张忠诚 

机构地区：[1]南昌大学信息工程学院,南昌330031 [2]电研天地科技有限公司,北京100094 [3]广东省电网公司肇庆高要供电局,肇庆521600

出　　处：《电力系统及其自动化学报》2008年第6期27-30,123,共5页Proceedings of the CSU-EPSA

基　　金：留学回国人员基金资助项目(2005383);江西省教育厅资助项目(200541)

摘　　要：提出一种基于GA改进算法的兼顾经济性和可靠性的多目标机组检修计划UMS(unit maintenance schedu-ling)优化模型。模型分别采用研究周期内各时段的电量不足期望值EENS(energy expectation not served)之和与电力不足期望值LOLP(Loss of Load Expectation)之和为经济性目标和可靠性目标。采用改进排序适应函数法构造能够同时判断检修计划经济性和可靠性优劣的适应值函数。最后对一5机算例进行了分析,并与传统等风险度法的结果进行了比较。结果表明基于GA改进算法的多目标优化检修方案在经济性及系统可靠性方面均具有较好性能。This paper presents a multi-objective optimal model of the unit maintenance scheduling （UMS）, which takes into account the economy and reliability of UMS, and solved by an improved genetic algorithm（GA）. The sum of energy expectation not served（EENS）and the sum of loss of load expectation（LOLP） are adopted as the economic objective function and the reliable objective function respectively. The improved GA, using new fitness function of improved sort, can find an optimal solution not only economic but also reliable. Compared with method of Level Risk Simulation, the proposed method can find a feasible solution both satisfied with economy and reliability of UMS.

关 键 词：多目标函数 改进遗传算法 机组检修计划 经济性 可靠性 

分 类 号：TM715[电气工程—电力系统及自动化]