Non-technical losses detection in energy consumption focusing on energy recovery and explainability

• Published in: Machine learning Vol. 111; no. 2; pp. 487 - 517
• Main Authors: Coma-Puig, Bernat, Carmona, Josep
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2022; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Classification; Coma; Computer Science; Control; Customers; Energy consumption; Energy industry; Energy recovery; Machine Learning; Mechatronics; Natural Language Processing (NLP); Neural networks; Public utilities; Regression; Robotics; Simulation and Modeling; Special Issue: Foundations of Data Science; Support vector machines; Regression; Robustness; Non-technical losses; Explainability; Classification
• ISSN: 0885-6125; 1573-0565
• DOI: 10.1007/s10994-021-06051-1

Non-technical losses (NTL) is a problem that many utility companies try to solve, often using black-box supervised classification algorithms. In general, this approach achieves good results. However, in practice, NTL detection faces technical, economic, and transparency challenges that cannot be easily solved and which compromise the quality and fairness of the predictions. In this work, we contextualise these problems in an NTL detection system built for an international utility company. We explain how we have mitigated them by moving from classification into a regression system and introducing explanatory techniques to improve its accuracy and understanding. As we show in this work, the regression approach can be a good option to mitigate these technical problems, and can be adjusted in order to capture the most striking NTL cases. Moreover, explainable AI (through Shapley Values) allows us to both validate the correctness of the regression approach in this context beyond benchmarking, and improve the transparency of our system drastically.