摘要
闪变源定位是解决闪变引起的供用电双方矛盾的关键。本文提出一种基于多重判据的闪变源智能定位法。首先分析了4种典型的闪变源定位方法并提取相应的闪变特征量。然后采用线性支持向量机算法对数据样本进行智能学习,有效利用定性特征量与定量特征量形成互补,在多维特征空间中构建上下游最优分类面,进而判断闪变源的位置。该方法通过智能学习代替了人工经验,将电力系统网络架构信息存储在线性支持向量机的权值中,可适用于多种情况下闪变源定位。最后采用33节点网络仿真对该模型进行验证。结果显示,与传统单一定位方法相比,该法具有更高的定位正确率,且能在附加一定白噪声条件下准确定位闪变源。
Flicker source location is the key to solving the contradiction between power supply and users.In this paper,an intelligent flicker source location method based on multiple criterions is proposed.First,four typical methods of flicker source location are analyzed,and the corresponding flicker features are extracted.Then,the linear support vector machine(LSVM)algorithm is used to intelligently learn the data samples,and the qualitative and quantitative features are used to complement each other effectively.The upstream and downstream optimal hyper-plane is constructed in the multi-dimensional feature space to determine the location of the flicker source.This method replaces artificial experiences by intelligent learning,and stores the network architecture information of power system in the weights of LSVM,which can be applied to the location of flicker source in various situations.Finally,a 33-node network is used to verify the proposed model through simulations.Results show that compared with the traditional single-criterion location method,the proposed method has higher location accuracy,and it can locate the flicker source even under some white noises.
作者
吴启宇
吕干云
吴晨媛
吴洁
俞明
魏鹏
WU Qiyu;LüGanyun;WU Chenyuan;WU Jie;YU Ming;WEI Peng(School of Electric Power Engineering,Nanjing Institute of Technology,Nanjing 211167,China;Lishui District Power Supply Branch,State Grid Jiangsu Electric Power Co.,Ltd,Nanjing 211200,China;State Grid Shaanxi Electric Power Company,Xi’an 710048,China)
出处
《电力系统及其自动化学报》
CSCD
北大核心
2019年第12期95-100,共6页
Proceedings of the CSU-EPSA
基金
国家自然科学基金资助项目(51577086)
江苏“六大人才高峰”、江苏高校“青蓝工程”项目配电网智能技术与装备协同中心开放基金资助项目(XTCX201611).
关键词
闪变源定位
智能定位
多重判据
线性支持向量机
flicker source location
intelligent location
multiple criterions
linear support vector machine(LSVM)
