Wind power data anomaly detection method and system based on federated learning mechanism

The invention relates to the field of anomaly detection, and provides a wind power data anomaly detection method and system based on a federated learning mechanism. The method comprises the following steps: generating a guide node based on a federal multi-scale graph contrast learning feature generation model; selecting a neighbor node set to be aggregated; obtaining a high-value information relation subgraph of the target node; aggregating information of neighbor nodes under each relationship in the high-value information relationship sub-graph by using a GNN based on a message passing mechanism; after neighbor information aggregation is completed locally, a multi-layer perceptron is used as a classifier to predict the anomaly of data; calculating classification loss, and forming a local model through loss training; and performing iteration on the global model by using a local model weighted average mode to obtain a federated wind power data anomaly detection model, and performing real-time detection on the