Advancements in digital twin technology and machine learning for energy systems: A comprehensive review of applications in smart grids, renewable energy, and electric vehicle optimisation

Abstract

The growing interest in Digital Twin (DT) Technology represents a significant advancement in academic research and industrial applications. Leveraging advancements in Internet of Things (IoT), sensors, and communication devices, DTs are increasingly utilised across different sectors, notably in the energy domain such as Power Systems and Smart Grids. DT concepts facilitate the creation of virtual models mirroring physical assets, streamlining real-time data management and analysis. Driven by the potential of DTs to revolutionise energy systems, this paper offers a comprehensive review of DT applications in the power sector, specifically within next-generation energy systems like Smart Grids. TThe integration of DT technology with Machine Learning (ML) algorithms is highlighted as a key factor in significantly enhancing the performance and capabilities of these advanced energy systems. In contrast to prior reviews, our study meticulously investigates all of the crucial components of energy systems, including forecasting, anomaly detection, and security, which are fundamental for improving the management of operational grids. In addition, the study examines the seamless incorporation of Renewable Energy into current grids and investigates how DT technology could contribute to Electric Vehicles for increased sustainability and reliability within the Smart Grid framework. This review underlines that DTs significantly enhance the management of real-time data and analysis, consequently improving operational grid management. There are ample opportunities into further research and development to design a more advanced and digital system as compared to conventional power systems. The findings are presented in clear and concise tables, highlighting current limitations, proposing effective solutions, and identifying potential future research directions in academia and industry.