摘要
针对被动式孤岛检测方法易受电能质量扰动影响的缺陷,提出了一种基于变模式分解(VMD)与极限学习机的孤岛自动检测方法。从公共耦合点(PCC)采集逆变器输出电压信号及电流信号,进而利用VMD技术提取特征量,再通过极限学习机进行模式识别来判断是否出现孤岛现象。仿真结果表明,所提方法可以有效检测出孤岛发生,而且能防止电能质量扰动对孤岛检测准确性的影响。
Aiming at the defect of passive islanding detection that is susceptible to power quality disturbances,an islanding detection method based on variational mode decomposition(VMD)and extreme learning machine(ELM)was proposed.The current and voltage collected from the point of common coupling(PCC)are decomposed into PF component to extract the features using VMD decomposition algorithm.The islanding status of micro-grid or grid-connected PV systems are verified with the ELM.The simulation and experiment results show that this method is faster than the traditional passive methods in islanding detection,and reduces the affection of power quality disturbances.
作者
陈丽
唐圣学
徐从启
CHEN Li;TANG Shengxue;XU Congqi(State Key Laboratory of Reliability and Intelligence of Electrical Equipment,Hebei University of Technology,Tianjin 300130,China;PLA Unit 62026,Xi’an 710032,China)
出处
《电器与能效管理技术》
2018年第6期47-52,共6页
Electrical & Energy Management Technology
基金
国家自然科学基金项目(51477040)
河北自然科学基金项目(E2015202263)
关键词
孤岛检测
变模式分解(VMD)
特征提取
极限学习机
islanding detection
variational mode decomposition(VMD)
feature extraction
extreme learning machine(ELM)