Public defence in Automation and Control Engineering, M.Sc. Rakshith Subramanya

The title of the thesis: Exploiting distributed energy resources with a virtual power plant: Intelligent market participation based on forecasts 

Doctoral student: Rakshith Subramanya
Opponent: Prof. Mo-Yuen Chow, Joint Institute, University of Michigan-Shanghai Jiao Tong University
Custos: Prof. Valeriy Vyatkin, Aalto University School of Electrical Engineering, Department of Electrical Engineering and Automation

Rakshith Subramanya’s doctoral study focused on improving the integration of renewable energy sources, battery storage, and distributed energy resources (DERs) into the power grid through Virtual Power Plants (VPPs). VPPs act as an alternative to traditional power plants and aim to optimize profit by collectively managing these DERs. 

The research aimed to achieve a more efficient, resilient, and environmentally friendly energy system. It addressed challenges faced in VPP integration with DERs, market participation, forecasting energy needs, and implementing cloud-based VPP systems. This research adds to existing knowledge by proposing an architecture for VPPs that utilizes various industry standards. This architecture incorporates functionalities like: • DER capacity and reserve market forecasting to optimize VPP operations and profitability. • Reinforcement learning for making bidding decisions in the reserve market. • Cloud-based implementation for seamless operation and scalability. • Multi-tenant architecture to enable easy integration of various DERs and SaaS (Software as a Service) functionalities like forecasting into the VPP system. 

The study also highlights the importance of incorporating Machine Learning Operations (MLOps) and Cloud Design Patterns (CDPs) for building robust software practices within VPPs. The findings from this research can be applied to real-world VPP implementations. The proposed architecture can be a foundation for building more efficient VPP systems that can participate effectively in energy markets while promoting a greener energy infrastructure. Overall, the study successfully demonstrates the potential of VPPs for optimizing DER integration and concludes that this approach can significantly contribute to a more efficient, reliable, and sustainable energy future. 

Keywords: virtual power plant, electricity market, battery energy storage systems, frequency containment reserve, artificial intelligence, reinforcement learning, cloud computing, SaaS, MLOps

Thesis available for public display 10 days prior to the defence at: https://aaltodoc.aalto.fi/doc_public/eonly/riiputus/

Contact:

Doctoral theses in the School of Electrical Engineering: https://aaltodoc.aalto.fi/handle/123456789/53