Identifying Irregular Power Usage by Turning Predictions into Holographic Spatial Visualizations

Abstract

Abstract-Power grids are critical infrastructure assets that face non-technical losses (NTL) such as electricity theft or faulty meters. NTL may range up to 40% of the total electricity distributed in emerging countries. Industrial NTL detection systems are still largely based on expert knowledge when deciding whether to carry out costly on-site inspections of customers. Electricity providers are reluctant to move to large-scale deployments of automated systems that learn NTL profiles from data due to the latter's propensity to suggest a large number of unnecessary inspections. In this paper, we propose a novel system that combines automated statistical decision making with expert knowledge. First, we propose a machine learning framework that classifies customers into NTL or non-NTL using a variety of features derived from the customers' consumption data. The methodology used is specifically tailored to the level of noise in the data. Second, in order to allow human experts to feed their knowledge in the decision loop, we propose a method for visualizing prediction results at various granularity levels in a spatial hologram. Our approach allows domain experts to put the classification results into the context of the data and to incorporate their knowledge for making the final decisions of which customers to inspect. This work has resulted in appreciable results on a real-world data set of 3.6M customers. Our system is being deployed in a commercial NTL detection software.

On the reduction of biases in big data sets for the detection of irregular power usage

“…We previously found a random forest (RF) classifier to perform the best on this data compared to decision tree, gradient boosted tree and support vector machine classifiers. 12 It is for this reason that in the following experiments, we only train RF classifiers. When training a RF, we perform model selection by doing randomized grid search, for which the parameters are detailed in Table 2.…”

Improving Smart Grids Security: An Active Learning Approach for Smart Grid-Based Energy Theft Detection

“…Dataoriented strategies increase the efficiency of doubted energy theft detection and evaluation by concentrating solely on the data generated by smart meters and neglecting network models or further devices. Thus, data-driven methods of predicting power theft have become increasingly popular recently [5].…”

Efficient Power Theft Detection for Residential Consumers Using Mean Shift Data Mining Knowledge Discovery Process

“…Monitoring of consumer load profiles for energy theft detection can be found in the literature [17]- [20]. The most common methods for fraud detection are Support Vector Machines ( [21]- [23]), Artificial Neural Networks ( [24], [39]), Bayesian Networks and Decision Trees [25], Extreme Learning Machines [26], Optimum-Path Forest [27], Fuzzy Clustering [28], Anomaly Detection [29] and Deep Learning which has recently achieved unprecedented performance in many areas of computer applications [30]- [32].…”