Method and system for detecting anomaly of power data of smart grid

The invention provides a smart grid power data anomaly detection method and system, and the method comprises the steps: S1, obtaining power data collected by a sensor node, and the power data comprises multi-dimensional feature data; s2, performing local anomaly detection according to the acquired power data to obtain a local anomaly detection result; s3, if the local anomaly detection result is abnormal, outputting that the power data detection result is local anomaly; if the local anomaly detection result is normal, further performing global anomaly detection on the power data to obtain a global anomaly detection result; s4, if the global anomaly detection result is normal, outputting that the power data detection result is normal; and if the global anomaly detection result is abnormal, outputting that the power data detection result is global anomaly. By means of local anomaly detection and global anomaly detection, the reliability and robustness of power data anomaly detection based on a large-scale power