The rapid integration of Distributed Energy Resources (DERs), such as solar photovoltaics (PV), is reshaping modern power grids. However, the stochastic nature, variability, and decentralised operation of DERs pose challenges to grid stability, forecasting, and energy management. Traditional modelling methods fail to capture the dynamic behaviour and real-time interactions of DERs, necessitating advanced data-driven solutions.
This project proposes the development of machine learning (ML)-based models as a Digital Twin (DT) technology to enhance predictability, control, and optimisation of DERs. The Digital Twin framework will create a real-time virtual replica of DERs, enabling continuous monitoring, simulation, and predictive analytics. The main objective is to develop high-fidelity ML models to predict DER behaviour under varying grid conditions.
By combining real-time data streams from smart meters, weather forecasts, and historical grid data, this research will enable scalable, intelligent solutions for improving DER management, strengthening grid resilience, and supporting a sustainable energy transition.
School
Electrical Engineering and Telecommunications
Research Area
Renewable energy systems | Power system modelling | Machine learning
- Research environment
- Expected outcomes
- Supervisory team
- Reference material/links
The student will be hosted at the cyber-physical smart grid lab at the school of Electrical Engineering and Telecommunications (333, G17) working alongside talented researchers and research students. The student will be supported by this team and will receive the proper training accordingly.
The project will deliver Digital Twin ML models for accurate DER behaviour forecasting under various grid conditions.
- Ana P. Talayero, Julio J. Melero, Andrés Llombart, and Nurseda Y. Yürüşen, “Machine Learning models for the estimation of the production of large utility-scale photovoltaic plants”, Solar Energy, v. 254, 2023.
- Suanpang, Pannee, and Pitchaya Jamjuntr. 2024. "Machine Learning Models for Solar Power Generation Forecasting in Microgrid Application Implications for Smart Cities" Sustainability 16, no. 14: 6087.