An embedded intrusion detection and prevention system for home area networks in advanced metering infrastructure

With the widespread adoption of smart metres in the power sector, anomaly detection has become a critical tool for analysing customers' unusual consumption patterns and network traffic. Detecting anomalies in power consumption and communication is primarily a real-time big data analytics issue regarding data mining along with a vast number of parallel streaming data from smart metres. In this study, an embedded Intrusion Detection and Prevention System (IDPS) is proposed as a Wifi-based smart metre for Home Area Networks (HANs) in the Advanced Metering Infrastructure (AMI) network. So, the proposed system employs one machine learning model based on IDPS to guard the HAN network from various attacks that utilise the Message Queueing Telemetry Transport protocol between the smart metre and IoT sensors. Also, it uses two machine learning models to detect the abnormality in periodic and daily data metering respectively. So, multiple algorithms have been used to find the suitable algorithm for each of the three anomaly detection models. These models have been evaluated and tested using real data sets regarding resources usage and detection performance to demonstrate the efficiency and effectiveness of using machine learning algorithms in the built anomaly detection models. The experiments show that the anomaly detection models performed well for various abnormalities.