A rule engine based classification algorithm for detection of illegal consumption of electricity

Total losses in transmission and distribution (T&D) of electricity includes nontechnical losses (NTL). Illegal consumption of electricity constitutes a major portion of NTL. NTL affects good interests of utility companies and its customers. In this context, importance of customer load profile evaluation for detection of illegal consumers has been explained. In this paper, an encoding technique has been implemented to reduce the number of data points to be evaluated by the rule engine. In addition, rule engine algorithm has been proposed and implemented to classify customers based on their energy consumption. This paper presents synopsis of those rules, and elucidates the overall encoding and classification procedure. From the obtained results, it is evident that the rule engine yielded appreciable classification accuracy in significantly less CPU time. Results demonstrate the robustness and accuracy of this procedure in identifying illegal consumers.