Anomaly Traffic Detection Model Based on Hybrid Network

With the rapid development of global informatization, the network has given us convenience, especially promoting the rapid upgrading of the power grid, but at the same time, the power network is also facing increasingly serious security problems. To reduce unnecessary losses and make early warning protection, it is necessary to detect the abnormal flow generated by the power system in operation in time. In this regard, a network traffic anomaly detection method based on a hybrid network of CNN (convolutional neural network) and MGU (minimum gated unit) network is proposed. The hybrid network obtains a higher detection rate by extracting the temporal and spatial features of network traffic data respectively. Experiments show that the proposed method can effectively improve the accuracy and efficiency of network anomaly traffic detection.