Anomaly detection of electric energy meter data based on deep network

Abstract

In order to ensure the privacy and security of user data transmission, when SM sends the user's power consumption characteristic data to the intelligent distribution transformer terminal, the distributed data model is used to aggregate the data. This paper proposes a study on improving the security of data information. The deep belief network (DBN) is introduced to compare the measured data with the expected data, better obtain the data characteristics, and reduce the dimension of the data, so as to reduce the calculation time of the algorithm and obtain the abnormal data faster; The intelligent distribution transformer terminal marks the SM of all consumers from 1 to N, and sends the execution data to the energy management system of the electric meter through the deep belief network to extract the characteristics. The faulty or damaged SM is checked and replaced, and more accurate NTL detection and analysis can be obtained. The proposed method can flexibly detect the data defects and anomalies of smart meters, and improve the practicability of energy / meter irregularity detection.