摘要
以准确检测电力系统调度数据异常模式为目的,提出基于支持向量机的电力系统调度数据异常检测方法。在分析电力自动化调度运行结构的基础上,构建调度数据的时间序列模型,识别并去除异常数据时间序列中的噪声数据与缺失数据。针对处理后的数据集合,利用孤立森林提取其异常特征,再将提取出的特征输入到支持向量机中,识别其中的异常特征模式,从而完成对电力系统调度数据异常的检测。实验结果验证:该方法在检测异常数据时,能够充分发挥数据预处理、数据特征提取、异常特征模式识别三大功能,具有较好的应用效果。
In order to accurately detect the abnormal patterns of power system dispatching data,an abnormal detection method of power system dispatching data based on support vector machine(SVM) is proposed.Based on the analysis of automatic dispatching operation structure of electric power,a time series model of dispatching data is constructed to identify and remove noise data and missing data in abnormal data time series.For the processed data set,the isolated forest is used to extract its abnormal features,and then the extracted features are input into the support vector machine to identify the abnormal feature patterns,so as to complete the abnormal detection of power system scheduling data.Experimental results show that this method can give full play to the three functions of data preprocessing,data feature extraction and abnormal feature pattern recognition when detecting abnormal data,and has a good application effect.
作者
刘震宇
LIU Zhen-yu(State Grid Jibei Electric Power Co.,Ltd.,Chengde Power Supply Company,Chengde 067000 China)
出处
《自动化技术与应用》
2023年第6期24-27,37,共5页
Techniques of Automation and Applications
关键词
支持向量机
电力系统调度
数据异常检测
特征提取
孤立森林
Support Vector Machine
power system dispatching
data anomaly detection
feature extraction
isolated forest
作者简介
刘震宇(1976-),男,硕士,高级工程师,研究方向:电力系统自动化控制、继电保护、电网运行等。
