Uploaded September 2026 | Updated November 2026, 3 days ago
Speaker:
Isabela Fons, PhD researcher in Process Systems Engineering at the University of Alicante.
Abstract:
This research project aims to explore the application of the HP2C-DT and COLMENA frameworks to distributed artificial intelligence solutions for decentralized energy management in residential microgrids. The work focuses on the integration of high-performance computing, digital twins, and multi-agent reinforcement learning (MARL).
The increasing penetration of distributed energy resources is driving the need for intelligent control strategies capable of coordinating large numbers of heterogeneous agents while accounting for economic, operational, and privacy constraints. MARL has emerged as a promising approach to address these challenges, demonstrating its ability to optimize multiple objectives simultaneously and improve consumption flexibility. However, the computational complexity of training and deploying MARL systems, together with concerns regarding data sharing and scalability, continue to limit their adoption in real-world environments.
During the stay, the potential of HP2C-DT and COLMENA is investigated as enabling technologies for the development of distributed digital twins and decentralized decision-making architectures. Particular attention is given to the orchestration of learning processes across distributed computing resources, the efficient exchange of information among agents, and the deployment of privacy-preserving control strategies.
The presentation provides an overview of the research objectives, the planned methodology, and the expected contributions of the collaboration. More broadly, the project seeks to advance the application of distributed AI techniques to energy systems while contributing to the validation and extension of HP2C-DT and COLMENA in realistic distributed-laboratory settings.
Further information:
bsc.es/research-and-development/research-seminars/sorswomeninbsc-responsible-ai-moving-beyond-hype-human-centered-innovation
Speaker:
Isabela Fons, PhD researcher in Process Systems Engineering at the University of Alicante.
Abstract:
This research project aims to explore the application of the HP2C-DT and COLMENA frameworks to distributed artificial intelligence solutions for decentralized energy management in residential microgrids. The work focuses on the integration of high-performance computing, digital twins, and multi-agent reinforcement learning (MARL).
The increasing penetration of distributed energy resources is driving the need for intelligent control strategies capable of coordinating large numbers of heterogeneous agents while accounting for economic, operational, and privacy constraints. MARL has emerged as a promising approach to address these challenges, demonstrating its ability to optimize multiple objectives simultaneously and improve consumption flexibility. However, the computational complexity of training and deploying MARL systems, together with concerns regarding data sharing and scalability, continue to limit their adoption in real-world environments.
During the stay, the potential of HP2C-DT and COLMENA is investigated as enabling technologies for the development of distributed digital twins and decentralized decision-making architectures. Particular attention is given to the orchestration of learning processes across distributed computing resources, the efficient exchange of information among agents, and the deployment of privacy-preserving control strategies.
The presentation provides an overview of the research objectives, the planned methodology, and the expected contributions of the collaboration. More broadly, the project seeks to advance the application of distributed AI techniques to energy systems while contributing to the validation and extension of HP2C-DT and COLMENA in realistic distributed-laboratory settings.
Further information:
bsc.es/research-and-development/research-seminars/sorswomeninbsc-responsible-ai-moving-beyond-hype-human-centered-innovation










