Utilizing Unlabeled Data to Detect Electricity Fraud in AMI: A Semisupervised Deep Learning Approach

As nontechnical losses in power systems have recently become a global concern, electricity fraud detection models attracted increasing academic interest. The wide application of smart meters has offered more possibility to detecting fraud from user’s consumption patterns. However, the performances of existing consumption-based electricity fraud detection models are still not satisfactory enough for practice, partly due to their limited ability to handle high-dimensional data. In this paper, a deep-learning-based model is developed for detecting electricity fraud in the advanced metering infrastructure, namely, the multitask feature extracting fraud detector (MFEFD). The deep architecture has brought MFEFD a powerful ability to handle high-dimensional input, through which consumption patterns inside load profiles can be effectively extracted. Another challenge is that the insufficiency of labeled data has restricted the generalization of existing models since they are mostly based on supervised learning and labeled data. MFEFD is trained in a semisupervised manner, in which multitask training was implemented to combine the supervised and unsupervised training, so that both the knowledge from unlabeled and labeled data can be made use of. Real-world-data-based case studies have demonstrated MFEFD’s high detection performance, robustness, privacy preservation, and practicability.

I. Introduction

Losses in power system can mainly be categorized into two groups: technical losses and nontechnical losses (NTL) [1]. Technical losses are caused by network resistance or energy transformation process among different forms, which are predictable but inevitable. NTL, namely, commercial losses, are mainly caused by the illegal or dishonest usage of electricity for the purpose of reducing payments, namely, electricity fraud. NTL have recently become a global concern: the total NTL all over the world in 2014 is estimated to reach $89.3 billion [2], and the commercial losses ratios were very high, especially in emerging markets, such as India from 20% to 40%, China at 10%, Brazil from 0.5% to 25% [3]. Electricity fraud has increased the utilities’ expenses (they were ultimately paid by customers through higher electricity prices) as well as the burden and risk of distribution systems [43]. Thus, eliminating the electricity fraud will benefit both customers and utilities.