Energy Fraud Detection in Advanced Metering Infrastructure AMI

Abstract

The Smart Grid advanced metering infrastructure (AMI) is one of the key components of the smart grid. It provides a two-way communication network between smart meters and utility systems, offering interactive services for managing billing and energy consumption. However, connecting the smart grid distributed elements, also introduces new vectors for fraud and cyberattacks. In this paper, we propose a novel approach for detecting energy fraud in AMI. The proposed approach leverages the predictability property of the consumption data by applying artificial neural network to profile normal energy consumption enabling the detection of fraudulent behavior. The evaluation of the proposed system on a real publicly available dataset of smart meter consumption data shows a high performance.