Anomaly detection based on joint spatio-temporal learning for building electricity consumption

•The ADJST realizes users' anomalous electricity consumption behaviors detection.•The MS-GCN achieves extracting spatial features and preventing feature coupling.•The MS-TCN module reduces the loss of time sequence information in long sequences.•Enhance the model’s stability and generalization by joint spatio-temporal learning. The use of electric energy is an integral part of people's daily life. Anomaly detection of electricity consumption data, as a classification problem, has always been a hot research topic of scholars. Anomaly detection can not only reduce energy waste, but also prevent small problems from becoming overwhelming problems. At present, most anomaly detection algorithms mainly focus on the time series information of electricity consumption data, while ignoring the spatial feature of electricity consumption data. To fill this research gap, the paper proposes an Anomaly Detection based on Joint Spatio-Temporal learning (ADJST) method for building electricity consumption. First, a Multi-Scale Graph Convolutional Network (MS-GCN) is proposed to learn the spatial features of building electricity consumption data. Specifically, two types of graphs are constructed to extract short-term correlation features and long-term regularity features of building electricity consumption data. Second, a Multi-Scale Temporal Convolutional Network (MS-TCN) is proposed to learn the temporal features of building electricity consumption data. Adopt a multi-scale vanilla convolution structure to extract multi-scale time series information from building electricity consumption data. Third, the combination of temporal features and spatial features detects anomalous electricity consumption of marked users. Final, taken the user electricity consumption data collected by the State Grid Corporation's smart meter as examples, compared with a variety of classical anomaly detection algorithms, the results of F1-score and AUC of the proposed method are 0.935 and 0.977 respectively, which proves the superiority of the method. The model shows good stability in dealing with extreme imbalance of data, and is proved to be generalized by experiments and can be transferred to other datasets.