Identification and detection of electricity customer behaviour irregularities

The present case study focusing on TNB, Malaysia's largest power utility, concentrates on load profiles as manifestations of customer behaviour. The main objective here is to base the investigation on comparing the efficacy of the Support Vector Machine (SVM) technique with the newly emerging techniques of Extreme Learning Machine (ELM) and its OS-ELM variant as means of classification and prediction in this context. Non-technical Losses (NTL) represent a significant proportion of electricity losses in both developing and developed countries. The ELM-based approach presented here uses customer load-profile information to expose abnormal behaviour that is known to be highly correlated with NTL activities. This approach provides a method of data mining for this purpose and it involves extracting patterns of customer behaviour from historical kWh consumption data. The results yield classification classes that are used to reveal whether any significant behaviour that emerges are due to irregularities in consumption. In this paper, ELM and online sequential-ELM (OS-ELM) algorithms are both used to achieve an improved classification performance and to increase accuracy of results. A comparison of this approach with other classification techniques, such as the Support Vector Machine (SVM) algorithm, is also undertaken and the ELM performance and accuracy in NTL analysis is shown to be superior.