Key points are not available for this paper at this time.
The transition toward smarter, more sustainable power systems has positioned data analytics at the core of modern electricity distribution network operations. Enabled by widespread smart meter deployment and advanced sensing technologies, distribution network operators now have access to high-resolution data that supports real-time monitoring, forecasting, and control. This paper presents a comprehensive review of state-of-the-art applications of data analytics in distribution networks, focusing on operational areas such as demand forecasting, electricity theft detection, outage identification, anomaly detection, topology identification, and integration of electric vehicles and energy storage systems. It highlights how advanced techniques, including machine learning, clustering, and deep learning, are being applied to transform raw smart meter data into actionable intelligence. Additionally, the paper discusses the enabling role of digital twins, fog computing, and network intelligence in managing grid complexity, improving system resilience, and supporting decarbonisation goals. Challenges related to data quality, scalability, and interpretability are also explored, emphasizing the need for coordinated technical, regulatory, and institutional responses. The findings underline the critical role of data intelligence in building adaptive, data-driven distribution networks capable of supporting the evolving demands of a low-carbon, decentralized energy future.
Khafaf et al. (Fri,) studied this question.