Journal
AUTOMATION IN CONSTRUCTION
Volume 135, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.autcon.2022.104128
Keywords
Deep reinforcement learning; Model predictive control; HVAC control; Building energy consumption; Energy savings; Building energy management
Funding
- Enerbrain s.r.l.
Ask authors/readers for more resources
This paper compares the application of online and offline Deep Reinforcement Learning (DRL) with a Model Predictive Control (MPC) architecture in energy management. The results show that although the initially trained DRL agent performs relatively poorly, it is able to converge to a control policy that is almost as effective as the model-based strategies. This provides a promising solution to overcome the modelling requirement barriers of MPC and offline-trained DRL approaches.
This paper proposes a comparison between an online and offline Deep Reinforcement Learning (DRL) formulation with a Model Predictive Control (MPC) architecture for energy management of a cold-water buffer tank linking an office building and a chiller subject to time-varying energy prices, with the objective of minimizing operating costs. The intrinsic model-free approach of DRL is generally lost in common implementations for energy management, as they are usually pre-trained offline and require a surrogate model for this purpose. Simulation results showed that the online-trained DRL agent, while requiring an initial 4 weeks adjustment period achieving a relatively poor performance (160% higher cost), it converged to a control policy almost as effective as the model-based strategies (3.6% higher cost in the last month). This suggests that the DRL agent trained online may represent a promising solution to overcome the barrier represented by the modelling requirements of MPC and offline-trained DRL approaches.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available