Federal learning-based abnormal operation data detection method for electric power Internet of Things

The invention discloses a federated learning-based power Internet of Things abnormal operation data detection method, and belongs to the field of power data detection.The method comprises the steps of constructing an anomaly detection model, and performing random assignment on model parameters of the anomaly detection model to obtain an initial model; deploying the initial model at an edge computing center and each power terminal device to obtain a global model and a local model of each power terminal device; according to the global model and the local model of each power terminal device, obtaining an optimal detection model by using transverse federation learning; and obtaining to-be-detected data, and performing detection by using the optimal detection model to obtain abnormal operation data. According to the invention, the problem of insufficient abnormal data detection precision under mass data of the power internet of things is solved. 本发明公开了一种基于联邦学习的电力物联网异常运行数据检测方法，属于电力数据检测领域，该方法包括构建异常检测模型，并对异常检测模型的模型参数