Anomaly detection methods for cable condition data currently encounter issues such as single consideration. This study presents an anomaly detection approach for power cables based on local outlier factor (LOF) and random forest (RF), designed to enhance the accuracy and reliability of anomaly identification. The method rapidly identifies cable anomaly data by analyzing the spatial and temporal characteristics of cable state data. The approach’s effectiveness is validated through experiments on characterization data from two cables in Beijing, comparing it with existing anomaly detection algorithms. Results indicate that the method achieves high precision and recall in detecting cable anomalies.