Power grid intrusion detection system and method based on CNN architecture and parameter parallel optimization

The invention discloses a CNN architecture and parameter parallel optimization-based power grid intrusion detection system and method, and the method comprises the steps: collecting the historical monitoring data of a power grid operation state from a measurement data management system of a smart power grid, analyzing the data, obtaining the reading information of each sensor, and carrying out the standard processing based on a standard score; according to the method, a CNN model is used as an input data set of an intelligent power grid intrusion detection offline optimization training module, a CNN model topology framework, convolution module parameters and training parameters are coded, a CNN model framework and parameter parallel optimization platform based on a genetic algorithm is designed, and framework and parameter information of an optimal CNN model is obtained. For power grid real-time monitoring data collected by a measurement data management system of the smart power grid, an optimal CNN model is