Recent Progress of Anomaly Detection in Energy Applications: A Systematic Literature Review
Joan Valls Pérez, Mayra Ramírez Chávez, Miguel Delgado-Prieto, L. Martínez · Artificial intelligence · 2025
Over the past few years, the anomaly detection problem has been intensively researched within different areas and applications. From a data-based analysis point of view, anomalies can be defined as data points that represent non-typical events, that is, abnormalities, with respect to the rest of the considered observations. The importance of anomaly detection relies on the fact that abnormal data highlights potentially undesirable situations in regard to the underlying physical phenomena under observation, which can have severe consequences for human beings, nature, infrastructures or information. This review article intends to provide a comprehensive overview of recent work on anomaly detection in a critical sector that is experiencing a deep digital transformation: the energy sector. With that, 52 articles have been reviewed, most of which focus on renewable energy generation, building energy consumption and energy storage. Interestingly, artificial intelligence-based approaches are found in ensemble schemes, where different models are combined for the maximization of the anomaly detection performance, oftentimes including deep learning (DL) models. However, under-represented trends and knowledge gaps are also identified, underscoring the lack of articles referring to specific energy application domains, such as critical infrastructures and electric vehicle (EV) charging infrastructure, and open issues for specific methodologies, such as explainability and applicability for deep learning anomaly detection solutions. Further, emerging concepts are highlighted and future research directions are identified.