An embedded and intelligent anomaly power consumption detection system based on smart metering. (10th March 2023)

• Record Type: Journal Article
• Authors: Lazim Qaddoori, Sahar; Ali, Qutaiba Ibrahim
• Is Part Of: IET wireless sensor systems. Volume 13:Number 2(2023)
• Page Start: 75
• Page End: 90
• Publication Date: 2023-03-10
• Subjects: Advanced Metering Infrastructure (AMI) -- clustering algorithms -- data aggregator -- firewall -- machine learning -- metering sensors -- MQTT protocol -- unsupervised algorithms; Wireless sensor networks -- Periodicals; 681.2
• DOI: 10.1049/wss2.12054
• Languages: English
• ISSNs: 2043-6386

Abstract

Abstract: User behaviour, human mistakes, and underperforming equipment contribute to wasted energy in buildings and industries. Identifying anomalous consumption power behaviour can help to reduce peak energy usage and change undesirable user behaviour. Furthermore, decreasing energy consumption in buildings is difficult because usage patterns vary from one building to the next. So, the main contribution in this manuscript is to propose a lightweight architecture for smart meter to identify abnormalities in power consumption for each building individually using machine learning (ML) models and implement on a Single Board Computer. To detect daily and periodic pattern anomalies, two models of anomaly detection based on supervised and unsupervised ML algorithms are built and trained where numerous algorithms were utilised to select the best algorithm for each model. Also, the proposed approach enables iterative procedure modifications by retraining the two anomaly detection models on data aggregator server based on the received data meter from the specific smart meter to give better power service to clients while minimising provider losses. The effectiveness and efficiency of the suggested approach have been proven through extensive analysis. Abstract : This research offered a lightweight architecture for identifying abnormalities in power consumption that would work for each building separately. To detect daily and periodic pattern anomalies, the suggested framework uses supervised and unsupervised learning‐based machine learning algorithms where numerous algorithms were utilised to select the best algorithm.