基于多目标粒子群算法的电力系统无功优化  

Power system reactive power optimization based on multi-objective particle swarm algorithm

作　　者：张聪誉[1] 陈民铀[1] 罗辞勇[1] 翟进乾[1] 姜毅[2] 

机构地区：[1]重庆大学输配电装备及系统安全与新技术国家重点实验室,重庆400030 [2]重庆市电力公司万州供电局,重庆404000

出　　处：《电力系统保护与控制》2010年第20期153-158,共6页Power System Protection and Control

基　　金：国家自然科学基金项目(50910234);国家'111计划'项目(B08036);重庆大学'211工程'三期创新人才培养计划建设项目(S09111)~~

摘　　要：针对电力系统有功损耗和电压偏差,提出一种带有变异的多目标粒子群算法。该算法采用非支配排序和拥挤距离来提高算法的多样性。通过ZDT1～ZDT4基准函数验证该算法的性能,比较它与其他多目标进化算法的优劣。将该算法应用于对多目标无功优化求解,采用IEEE30节点系统验证算法在无功优化中的优势。优化结果表明,该算法能清晰地给出电力系统有功损耗与电压偏差间的竞争关系,并能为用户提供均匀分布的多样化的备选解,让用户可以根据不同情况灵活选择。通过多次结果的叠加显示了该算法的稳定性。Considering the active power loss and voltage deviation,a multi-objective particle swarm optimization algorithm（MOPSO） is presented.MOPSO incorporates non-dominated sorting and crowding distance to improve the diversity of the Pareto solutions.Four benchmark test functions ZDT1～ZDT4 are used to test the performance of the proposed algorithm.Performance comparison between MOPSO and other typical algorithms is made.The simulation results of the standard IEEE-30-bus power system indicate that MOPSO is a good choice of power system reactive power optimization.The results show that MOPSO can provide the clear relation between active power loss and voltage deviation,and it is able to offer diverse solutions for different conditions.The stability of MOPSO has been confirmed through superposing many solutions together.

关 键 词：无功优化 多目标优化 粒子群算法 电力系统 非支配排序 拥挤距离 

分 类 号：TM714[电气工程—电力系统及自动化]