Rahul Sharma

My research focuses on a central challenge in the energy transition: how to make increasingly inverter-dominated and renewable-rich power systems intelligent, reliable and controllable.

I work at the intersection of control systems, AI and renewable energy, with applications in utility-scale solar farms, grid-connected inverters, battery systems and distributed energy resources. Our work spans the full research pathway—from mathematical modelling and control theory through simulation and AI development to field validation and commercial deployment.

A distinctive feature of my research is its connection with real energy systems and industry. I have led translational research projects and founded SolarisAI, which is commercialising research in solar-farm monitoring and underperformance diagnosis.

I am particularly interested in PhD candidates who want to work on:

• AI for utility-scale solar farms - fault detection, underperformance diagnosis, predictive analytics and reliability.
• Control of inverter-dominated power systems - advanced control of grid-connected inverters, batteries and distributed energy resources.
• AI and optimisation for smart grids - demand-side management and coordinated control of flexible loads and storage.
• Digital twins and physics-informed/hybrid modelling - combining physical models, operational data and machine learning for energy-system monitoring and prediction.
• PV circular economy and end-of-life systems - optimisation, logistics and decision-making for sustainable management of retired PV assets.

I particularly welcome students with backgrounds in electrical, mechanical, control, mechatronics, power or energy engineering, applied mathematics, optimisation, or machine learning. Strong candidates interested in combining rigorous technical research with real-world energy applications are encouraged to contact me with a CV, transcripts and a brief description of their research interests.