Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network

作     者：Zheng Fengming Li Shufang Guo Zhimin Wu Bo Tian Shiming Pan Mingming 

作者机构：Beijing Laboratory of Advanced Information Networks Beijing University of Posts and Telecommunications Beijing 100876 China Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing 100876 China State Grid Henan Electric Power Research Institute Zhengzhou 450052 China China Electric Power Research Institute Beijing 100192 China 

出 版 物：《The Journal of China Universities of Posts and Telecommunications》 (中国邮电高校学报（英文版）)

年 卷 期：2017年第24卷第6期

页      面：67-73页

核心收录：

学科分类：080802[工学-电力系统及其自动化] 0808[工学-电气工程] 08[工学] 

基　　金：supported by Business Integration and Data Sharing Service Technology Based on Through Information of Operation and Distribution(2016 state Grid Technology Project) 

主　　题：smart grid encoder-decoder framework anomaly detection time series mining 

摘      要：Anomaly detection in smart grid is critical to enhance the reliability of power systems. Excessive manpower has to be involved in analyzing the measurement data collected from intelligent motoring devices while performance of anomaly detection is still not satisfactory. This is mainly because the inherent spatio-temporality and multi-dimensionality of the measurement data cannot be easily captured. In this paper, we propose an anomaly detection model based on encoder-decoder framework with recurrent neural network （RNN）. In the model, an input time series is reconstructed and an anomaly can be detected by an unexpected high reconstruction error. Both Manhattan distance and the edit distance are used to evaluate the difference between an input time series and its reconstructed one. Finally, we validate the proposed model by using power demand data from University of California, Riverside （UCR） time series classification archive and IEEE 39 bus system simulation data. Results from the analysis demonstrate that the proposed encoder-decoder framework is able to successfully capture anomalies with a precision higher than 95%.