No abstract

This paper is a review of literature with an analysis on a selection of scientific studies for detection of non-technical losses. Non-technical losses occurring in the electric grid at level of transmission or of distribution have negative impact on economies, affecting utilities, paying consumers and states. The paper is concerned with the lines of research pursued, the main techniques used and the limitations on current solutions. Also, a typology for the categorization of solutions for detection of non-technical losses is proposed and the sources and possible attack/vulnerability points are identified. The selected literature covers a wide range of solutions associated with non-technical losses. Of the 103 selected studies, 6 are theoretical, 25 propose hardware solutions and 72 propose non-hardware solutions. Data based classification models and data from consumption with high resolution are respectively required in about 47% and 35% of the reported solutions. Available solutions cover a wide range of cases, with the main limitation found being the lack of an unified solution, which enables the detection of all kinds of non-technical losses.

This paper proposes a process for the classification of new residential electricity customers. The current state of the art is extended by using a combination of smart metering and survey data and by using model-based feature selection for the classification task. Firstly, the normalized representative consumption profiles of the population are derived through the clustering of data from households. Secondly, new customers are classified using survey data and a limited amount of smart metering data. Thirdly, regression analysis and model-based feature selection results explain the importance of the variables and which are the drivers of different consumption profiles, enabling the extraction of appropriate models. The results of a case study show that the use of survey data significantly increases accuracy of the classification task (up to 20%). Considering four consumption groups, more than half of the customers are correctly classified with only one week of metering data, with more weeks the accuracy is significantly improved. The use of modelbased feature selection resulted in the use of a significantly lower number of features allowing an easy interpretation of the derived models.