Intelligent substation process layer network abnormal flow detection method based on deep learning

Abstract

The invention discloses an intelligent substation process level network abnormal flow detection method based on deep learning, which comprises the following steps: collecting substation process level network time sequence flow data under different operation conditions, respectively extracting time domain and time-frequency domain features, carrying out normalization processing, and then calculating the abnormal flow of the substation process level network according to the extracted time domain and time-frequency domain features; and obtaining sample data comprising a sampling moment, a sample type, a time domain feature and a time-frequency domain feature. Training the constructed LSTM neural network by using sample data, and determining structural parameters and hyper-parameters of the model; the dimensionality of the model output vector is the network flow type number of the substation process layer. And finally, detecting the network flow data of the process layer of the transformer substation by adopting the detection model to obtain a corresponding data type result. According to the method, substation process layer network flow detection and deep learning are combined, the accuracy of substation process layer network abnormal flow detection is effectively improved, and the misjudgment rate and the omission ratio of detection are reduced.

Description

technical field [0001] The present application belongs to the technical field of network security, relates to the network security management of smart substations, and in particular relates to a method for detecting abnormal flow in the process layer network of smart substations based on deep learning. Background technique [0002] The intelligent substation communication network effectively manages and controls the substation equipment, and realizes the automation and modern management of the substation. Communication between different devices in a substation network follows the IEC 61850 standard. Among them, the process layer network covers the sampled measurement value SMV and GOOSE message information, connects the process layer and the interval layer intelligent devices, and also acts as the connection link for communicating the electrical quantity of the power system and reflecting the communication quantity of each device. It is the realization of the smart grid indu...

AI Technical Summary

Problems solved by technology

At present, there are few relevant researches on the abnormal detection of network data flow in the process layer of smart substation, most of which focus on the detection of network flow in the substation control layer, and do not involve the use of deep learning methods to detect abnormal network flow in the process layer of substations.

Images