A deep learning method for flow abnormity detection of an intelligent power grid server

Abstract

The invention discloses a deep learning method for flow abnormity detection of an intelligent power grid server. According to the method, on the basis of the high-dimensional time sequence data information for monitoring the flow of a power grid server, an Encoder-Dector deep neural network based on two layers of LSTM neurons is utilized to construct the flow normal state estimation, and based onthe estimated normal flow behavior, the distribution condition of the residual error between the normal flow behavior and the measured value is analyzed, and finally a confidence interval is given asa control limit for judging the abnormal behavior, thereby realizing the detection of the abnormal flow behavior of the smart grid server. According to the method, the nonlinear relation between variables can be dynamically approximated in a self-adaptive mode, the manual intervention is not needed for selecting variable characteristics, the data dimension reduction is not needed, the certain universality is achieved, and the method has very important scientific significance and application value for preventing severe faults.

Description

technical field [0001] The invention relates to a data anomaly detection method based on deep learning combined with a control chart, in particular to a deep learning method for traffic anomaly detection of a smart grid server. Background technique [0002] The smart grid realizes the digitization and informatization of electric energy in production, transmission, distribution and use through the Internet and Internet of Things technology. To a large extent, it will develop into a type of interdependent network composed of information network and power network. A new generation of power system that is "economical and efficient, flexible and interactive, friendly and open, clean and environmentally friendly". As the core lifeblood of the smart grid, the communication network has greatly improved the level of power automation, improved social production efficiency, and improved user experience, but it has also brought many hidden dangers to the safety of the power system. [...

AI Technical Summary

Problems solved by technology

For large-scale complex and strongly coupled power transmission and distribution networks, the possible losses caused by information network attacks are difficult to estimate. At the same time, with the continuous updating of network attack methods, smart grid data service centers are attacked by DDoS attacks, hijacking attacks, and data fraud and theft. likely to rise sharply

On the other hand, due to the complex and changeable working conditions of the power system, the state of its data communication network exhibits non-stationary and fast time-varying characteristics, and the corresponding network anomaly characteristics are more difficult to distinguish, which brings great challenges to anomaly detection and troubleshooting. Difficulties, network abnormalities cannot be identified in time, data communication security cannot be guaranteed, and the security of the smart grid is greatly reduced, seriously threatening the reliable and stable operation of the grid

Images