I am a Research AI Engineer at EnergyWise. Our current mission at EnergyWise is to make buildings more energy efficient, avoiding massive energy waste while keeping spaces comfortable and healthy. In this framework, my work is related to the implementation of Artificial Intelligence based strategies for enhancing energy efficiency and indoor conditions for occupants in buildings.
I am an Energy and Nuclear Engineer, PhD Candidate in Energetics at BAEDA Lab at the Department of Energy of Politecnico di Torino.
My PhD research deals with the exploitation of transfer learning techniques to enhance the scalability of advanced control strategies in buildings.
Check my Publications
JOURNAL PUBLICATIONS:
Silvestri, A.; Coraci, D.; Brandi, S.; Capozzoli, A.; Borkowski, E.; Köhler, J.; Wu, D.; Zeilinger, M.N.; Schlueter, A. Real building implementation of a deep reinforcement learning controller to enhance energy efficiency and indoor temperature control. Applied Energy, 368, 123447 (2024). https://doi.org/10.1016/j.apenergy.2024.123447.
Coraci, D.; Brandi, S.; Hong, T.; Capozzoli, A. An innovative heterogeneous transfer learning framework to enhance the scalability of deep reinforcement learning controllers in buildings with integrated energy systems. Building Simulation 17 (5), 739-770 (2024). https://doi.org/10.1007/s12273-024-1109-6.
Coraci, D.; Brandi, S.; Capozzoli, A. Effective pre-training of a deep reinforcement learning agent by means of long short-term memory models for thermal energy management in buildings. Energy Conversion and Management, 291, 117303 (2023). https://doi.org/10.1016/j.enconman.2023.117303.
Coraci, D.; Brandi, S.; Hong, T.; Capozzoli, A. Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings. Applied Energy, 333, 120598 (2023). https://doi.org/10.1016/j.apenergy.2022.120598.
Deltetto, D.; Coraci, D.; Pinto, G.; Piscitelli, M.S.; Capozzoli, A. Exploring the Potentialities of Deep Reinforcement Learning for Incentive-Based Demand Response in a Cluster of Small Commercial Buildings. Energies, 14, 2933 (2021). https://doi.org/10.3390/en14102933.
Coraci, D.; Brandi, S.; Piscitelli, M.S.; Capozzoli, A. Online Implementation of a Soft Actor-Critic Agent to Enhance Indoor Temperature Control and Energy Efficiency in Buildings. Energies, 14, 997 (2021). https://doi.org/10.3390/en14040997.
CONFERENCES PUBLICATIONS:
Silvestri, A.; Coraci, D.; Brandi, S.; Capozzoli, A; Schlueter, A. Practical deployment of Reinforcement Learning for building controls using an Imitation Learning approach. Accepted at 19th Conference on Sustainable Development of Energy, Water and Environment Systems (SDEWES) (2024).
Silvestri, A.; Coraci, D.; Wu, D.; Borkowski, E; Schlueter, A. Comparison of two deep reinforcement learning algorithms towards an optimal policy for smart building thermal control. Journal of Physics: Conference Series (CISBAT 23), vol 2600, 7, 072011 (2023). https://dx.doi.org/10.1088/1742-6596/2600/7/072011
Coraci, D.; Brandi, S.; Capozzoli, A. Effective pre-training of a Deep Reinforcement Learning agent by means of Long Short-Term Memory models for thermal energy management in buildings. In: 17th Conference on Sustainable Development of Energy, Water and Environment Systems (SDEWES) (2022).
Brandi, S.; Coraci, D.; Borello, D.; Capozzoli, A. Energy Management of a Residential Heating System Through Deep Reinforcement Learning. In: Littlewood, J.R., Howlett, R.J., Jain, L.C. (eds) Sustainability in Energy and Buildings 2021.
Smart Innovation, Systems and Technologies, vol 263 (2022) Springer, Singapore. https://doi.org/10.1007/978-981-16-6269-0_28
