基于食物链生态进化算法的多阶段输电网络规划  

Multistage Transmission Network Planning Based on Ecology Evolutionary Algorithm of Food Chain

作　　者：李翔硕[1] 王淳[1] 龚娇龙 

机构地区：[1]南昌大学信息工程学院,江西南昌330031 [2]江西宜春供电公司,江西宜春336000

出　　处：《南昌大学学报（工科版）》2012年第1期93-97,共5页Journal of Nanchang University(Engineering & Technology)

基　　金：国家自然科学基金资助项目(50747025);江西省教育厅基金资助项目(GJJ10381)

摘　　要：将模拟生物界能量传递方式的食物链生态进化算法应用于多阶段输电网络规划。根据食物链生态进化算法收敛性受初始食物链上个体分布影响较大的特点,提出了一种初始化方法。该方法使得初始种群广泛分布于搜索空间,避免了完全随机初始化群体分布不合理的缺点。根据多阶段输电网络规划的特点,提出了以待选线路为决策变量,规划阶段号为搜索域的实数编码方法,解决了决策变量维数随着规划阶段数的增加而增加的问题。根据食物链中低级种群和中级种群品质较低的特点,提出了大变异策略,使得低级种群和中级种群可以快速产生新个体,改善群体品质,避免"早熟"。将所提方法应用于19节点系统,得到了现有文献中有关该系统的最优规划方案,表明该方法的可行性和有效性。As the simulation biological energy transfer mode, ecology evolutionary algorithm of tood chain was applied to multistage transmission network planning （MTNP）. A method was put forth for initialization according to the initial populations of food chain distribution has great effect on EEAFC＇ s convergence performance. The method made the initial population distributed in the search space widely and overcame the weaknesses of unreasonable dis- tribution of populations, which was caused by completely random initialization. According to the characteristics of MTNP, a real number encoding method, which adopts the lines as the decision variables and the serial number of the planning stage as the search domain, is proposed and solved the problem that decision variables＇ dimension increases as the stage increases. According to the characteristics of lower quality of low and intermediate population, unusual mutation strategy is proposed. The strategy, which makes the low and intermediate population generate new individual quickly,improves the population quality and avoid ＂precocity＂. The test is performed on a 19-bus system. The final best planning scheme demonstrated that the method EEAFC-based MTNP is practical and effective.

关 键 词：电力系统 多阶段输电网络规划 食物链生态进化算法 最优规化 动态决策 

分 类 号：TM715[电气工程—电力系统及自动化]