改进粒子群优化算法在电力负荷组合预测模型中的应用  

Application of Improved Particle Swarm Optimization in Power Load Combination Forecasting Model

作　　者：吴昌友[1] 王福林[1] 董志贵[2] 索瑞霞[1] 

机构地区：[1]东北农业大学工程学院,黑龙江省哈尔滨市150030 [2]沈阳东方钛业有限公司,辽宁省沈阳市110016

出　　处：《电网技术》2009年第2期27-30,共4页Power System Technology

基　　金：国家863高技术基金项目(2006AA10A310-1)~~

摘　　要：提出了改进的粒子群优化算法:通过改进初始粒子种群的产生方法,加快其产生速度;在新的粒子种群产生过程中引入自适应步长,可以在该速度梯度方向上找到较优的粒子,进而加速了收敛速度;借鉴遗传算法中的变异操作增加了粒子的多样性,减小了算法陷入局部极值的可能。通过应用实例证明,将改进的粒子群优化算法应用到电力负荷组合预测模型的权重求解是可行的。In this paper an improved particle swarm optimization （PSO） is proposed. By means of improving initial particle population, its generation velocity is accelerated; through leading the adaptive step-length into the generation process of particle population, better particle can be found in this velocity gradient direction, thus the convergence can be speeded up; drawing on the experience of genetic algorithm （GA）, the possibility that the algorithm falls into local extremum is decreased. Application examples show that it is feasible to apply the improved PSO to the weight solution of power load combination forecasting model.

关 键 词：粒子群优化算法 变异 电力负荷 组合预测 

分 类 号：TM734[电气工程—电力系统及自动化]