Reducing non-technical losses in electricity distribution networks: Leveraging explainable AI and three lines of defence model to manage operational staff-related factors

• Published in: e-Prime 2024-09, Vol.9, p.100748, Article 100748
• Main Authors: Nwafor, Obumneme, Nwafor, Chioma, Aboushady, Ahmed, Solyman, Ahmed
• Format: Article
• Language: English
• Subjects: 3LoD model; Electricity distribution; Explainable artificial intelligence; Non-technical losses
• ISSN: 2772-6711; 2772-6711
• DOI: 10.1016/j.prime.2024.100748

•Utility staff-related activities are major causes of Non Technical Losses (NTL) in electricity distribution, yet they are often overlooked in empirical research.•Explainable Artificial Intelligence can be used to reveal the predictive significance of different factors causing NTL in electricity distribution networks.•Three Lines of Defence (3LoD) model can be integrated into electricity distribution operations to manage risk and reduce NTL.•Staff-related causes of NTL can be mapped into BASEL II and II risk categories.•Utility companies, policymakers and energy industry stakeholders can reduce NTL by leveraging explainable AI and 3LoD Model to address specific aspects of staff-induced NTL. This study presents a multidisciplinary approach involving Explainable Artificial Intelligence (ExAI) and operational risk management to reduce Non-Technical Losses (NTL) in electricity distribution. It empirically explores how the activities of employees of utility companies contribute to NTL, a phenomenon often overlooked in existing empirical research. An ensemble classification algorithm is used to analyse utility operations data, and the SHAP explainability technique establishes the predictive significance of staff activities for NTL. Subsequently, these staff activities are mapped into risk cells using the BASEL II and III operational risk definitions, and the Three Lines of Defence (3LoD) model is developed for optimizing electricity distribution. The paper makes three original contributions to the literature: first, it empirically links staff operations to NTL; second, it maps NTL causes to Basel II/III operational risk categories; and finally, to the best of the authors’ knowledge, it is the first study to use the 3LoD model for electricity distribution optimization.