基于改进梯度粒子群算法的无功优化  

Reactive Power Optimization Based on Improved Gradient Particle Swarm Optimization Algorithm

作　　者：杨龑亮[1] 王秀云[1] 曾淑珍 祝洪博[1] 王彬[1] 黄金稳 

机构地区：[1]东北电力大学电气工程学院,吉林吉林132012 [2]宁德电业局,福建宁德352100 [3]莆田电业局,福建莆田351100

出　　处：《现代电力》2010年第4期17-21,共5页Modern Electric Power

摘　　要：针对梯度粒子群优化算法(GPSO)收敛速度慢、容易陷入局部最优的缺点,提出改进的GPSO算法并将其应用于无功优化。改进GPSO算法不仅结合动态惯性权值方法调整惯性权重,有效地提高了算法的收敛速度,而且采用负梯度方向变异和维变异方法共同作用,更有效保证算法跳出局部最优,提高了算法的收敛精度。以网损为最小,对标准IEEE-30节点和IEEE-57节点系统进行仿真计算,结果表明改进后的算法能够获得更好的全局最优解。As to the low convergence speed and local optimization of gradient particle swarm optimization（GPSO） algorithm,the improved GPSO algorithm is presented and applied to reactive power optimization.The improved GPSO algorithm has such characteristics as fast convergence speed by dynamical inertia weight regulation method,global optimal resolution by comined action of negative gradient direction mutation and dimension mutation,and higher convergence accuracy.The model of reactive power optimization is established by taking consideration of minimizing network losses,and simulation is carried out on IEEE-30 and IEEE-57 system,better global optimum solution can be got by improved algorithm.

关 键 词：梯度粒子群 动态惯性权值 维变异 无功优化 

分 类 号：TM714.3[电气工程—电力系统及自动化]