Energy Frauds Characterization based on Information Theory Quantifiers

Smart grids present risks when exchanging valuable data between their systems; theft or alteration of this data could violate consumer privacy. Mainly, the non-technical losses (NTL) occur by illegal connections, meter problems (installation delays or wrong readings), dirty, defective, or mismatched meters, very low estimates of adequate consumption, faulty connections, and missing customers. According to a recent study, utilities lose $89.3 billion annually through NTL. We present an energy fraud characterization study based on Information Theory Quantifiers (ITQ) to mitigate this challenge. First, we convert the user's energy consumption time series into a Bandt-Pompe (BP) probability distribution function using a sliding window. The second step is to extract the ITQ used by the technology. We then apply each metric to the Probability Density Function (PDF) and map the layers to characterize their behavior. Our results show that users with normal and abnormal energy consumption can be distinguished using only Information Theory Quantifiers by considering the range of values for each metric.