Machine Learning Helps Lighting Equipment Meter Measurement Anomaly Detection and Processing
LIU Ling
TAN Yuyang
LIU Yun
HUANG Shipeng
Abstract：With the rapid development of smart grids and IoT technology,the monitoring and management of power systems have become increasingly complex.Traditional methods for anomaly detection in electricity metering mainly rely on threshold-based judgment and statistical analysis,which have low accuracy and poor real-time performance.This paper proposes a machine learning-based approach for anomaly detection in lighting equipment electricity metering.By utilizing machine learning algorithms such as Support Vector Machine(SVM),Random Forest(RF),K-Nearest Neighbors(K-NN),and Long Short-Term Memory(LSTM),we establish an anomaly detection model using features such as current,voltage,and power factor.Experimental results show that the LSTM-based model performs better in detecting abnormal fluctuations in electricity metering data,offering higher detection success rates and recall rates,effectively enhancing anomaly monitoring in power systems.This paper provides new insights for anomaly detection in smart metering and lays the foundation for intelligent operation and maintenance of power systems.
Keywords：machine learninglighting equipmentelectricity meteringanomaly detection
Publication Date：2025-06-25
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 47-52 )