无重访遗传算法及其在输电网络规划中的应用.pdfVIP

第 33 卷 第 4 期 中 国 电 机 工 程 学 报 Vol.33 No.4 Feb.5, 2013 110 2013 年 2 月 5 日 Proceedings of the CSEE ©2013 Chin.Soc.for Elec.Eng. 0258-8013 (2013) 04-0110-08 TM 71 A 470 40 文章编号： 中图分类号： 文献标志码： 学科分类号： ⋅ 无重访遗传算法及其在输电网络规划中的应用 高元海，王淳 (南昌大学电气与自动化系，江西省 南昌市 330031) Non-revisiting Genetic Algorithm and Its Application in Transmission Network Planning GAO Yuanhai, WANG Chun (Department of Electrical and Automatic Engineering, Nanchang University, Nanchang 330031, Jiangxi Province, China) ABSTRACT: A non-revisiting genetic algorithm (NrGA) was 遗传算法；自适应变异 used to solve power transmission network planning problem. 0 引言 By advocating binary space partitioning (BSP) and employing a novel binary space partitioning tree (BSP tree) archive to 模拟自然现象和生产过程的人工智能算法同 store all the solutions that have been explored before, NrGA 时具备了深度有哪些信誉好的足球投注网站解空间和广度有哪些信誉好的足球投注网站解空间的能 can quickly check whether there is a revisit when a new 力[1]，提供了求解复杂系统优化问题的一种通用方 solution is generated by GA, and can mutate an unvisited 法。其优点是不依赖于问题的具体领域，对问题的 solution through a novel adaptive mutation operator that based on BSP while a revisit has occurred, which achieves a 种类有很强的鲁棒性[2]，且允许所求解的问题是非 non-revisiting search. Moreover, according to the 线性的和不连续的。但是人工智能算法的一个主要 characteristics of the transmission network planning problem, 问题是计算收敛速度慢，且有可能限于局部最优而 some measure was proposed to improve encoding, crossover 不能跳出。造成这一问题的主要原因之一是算法自 operator and barrier terms. Finally, a typical example was