Open Access Open Access  Restricted Access Subscription Access

Reinforcement Learning-Based Energy Management in Solar Photovoltaic Systems

Sanvi Kaushik, Dr. Manish Kumar

Abstract


The use of energy is becoming more common in multiple power systems. This is a major change because solar energy is not always available universally. Sometimes it is sunny. Sometimes it is not. This makes it hard to manage energy. Old ways of managing energy do not work well with energy. They are trained in such a way that they can be trusted with important choices. Lately reinforcement learning has become a big deal to manage energy. This is a way for systems to learn and make decisions on their own. Systems can learn by trying things and seeing what works. This helps them be more efficient and reliable. This paper is about using reinforcement learning to manage energy. It looks at how this can be used in homes, buildings and big power systems. It also looks at some ideas like using many systems together and learning from one situation to apply to another. This further elaborates on what's good and what is not so good about these ideas. It also talks about what needs to be figured out. This will help us make energy management systems, for the future. Solar energy systems are an important component of our future. Reinforcement learning and solar energy systems are two things that we need to understand. By studying these things, we can make energy management systems that're good for the future. We need to keep learning about energy systems and how to manage them.


Full Text:

PDF

References


Lee, S., & Choi, D.-H. (2019). Reinforcement learning-based energy management of smart home with rooftop solar photovoltaic system, energy storage system, and home appliances. Sensors, 19(18), 3937.

Alamro, H., Alqahtani, H., Alotaibi, F. A., Othman, K. M., Assiri, M., Alneil, A. A., & Prasad, L. N. (2023). Deep reinforcement learning-based solution for sustainable energy management in photovoltaic systems. Optik, 295, 171530.

Fu, J., Sun, D., Peyghami, S., & Blaabjerg, F. (2024). A novel reinforcement-learning-based compensation strategy for DMPC-based day-ahead energy management of shipboard power systems. IEEE Transactions on Smart Grid, 15(5), 4349–4363.

Zhang, Y., Gatsis, N., & Giannakis, G. B. (2018). Reinforcement learning-based energy management algorithm for smart energy buildings. Energies, 11(8), 2010.

Chemingui, Y., Gastli, A., & Ellabban, O. (2020). Reinforcement learning-based school energy management system. Energies, 13(23), 6354.

Xu, X., Jia, Y., Xu, Y., Xu, Z., Chai, S., & Lai, C. S. (2020). A multi-agent reinforcement learning-based data-driven method for home energy management. IEEE Transactions on Smart Grid, 11(4), 3201–3211.

Nakabi, T. A., & Toivanen, P. (2021). Deep reinforcement learning for energy management in a microgrid with flexible demand. Sustainable Energy, Grids and Networks, 25, 100413.

Alamro, H., Alqahtani, H., Alotaibi, F. A., Othman, K. M., Assiri, M., Alneil, A. A., & Prasad, L. N. (2020). Deep reinforcement learning-based solution for sustainable energy management in photovoltaic systems. Energy AI, 4, 100043.

Enhancing reinforcement learning-based energy management through transfer learning with load and PV forecasting. (2024). IEEE Transactions on Smart Grid.

Deep reinforcement learning-based energy management framework for smart grids with renewable integration. (2025). Energy AI.


Refbacks

  • There are currently no refbacks.