Anomaly Detection Algorithm of Meter Reading Messages for Power Line Communication Networks

Regarding the issue of abnormal data mining of electricity meters in the PLC application area, an intelligent measurement network architecture integrating protocol message interaction and an anomaly detection module has been designed. Based on an improved convolutional neural network (ICNN), abnormal messages during the transmission and reception process are monitored to enhance the reliability of power information collection data. Firstly, common anomalies during the meter reading operation are analyzed using protocol analysis tools, including abnormal power data, excessive delay, message out of order, etc. Subsequently, a dataset containing these anomalies with a preset proportion is constructed, and through data splicing and matrix processing, it is transformed into a two-dimensional image set to optimize the recognition effect of the convolutional neural network. Ultimately, an anomaly detection algorithm based on the ICNN is developed. Gray wolf optimization (GWO) is adopted to improve the algorithm’s performance, and the algorithm is integrated into the anomaly detection module. The experimental results demonstrate that, compared with the CNN-LSTM and CNN-SVM algorithms, the proposed algorithm offers an advantage in terms of complexity while achieving an accuracy rate of 98.8%, providing a reliable anomaly detection solution for metering network measurement systems.