Abstract
Recently, a growing interest has been observed in HVAC control systems based on Artificial Intelligence, to improve comfort conditions while avoiding unnecessary energy consumption. In this work, a model-free algorithm belonging to the Deep Reinforcement Learning (DRL) class, Soft Actor-Critic, was implemented to control the supply water temperature to radiant terminal units of a heating system serving an office building. The controller was trained online, and a preliminary sensitivity analysis on hyperparameters was performed to assess their influence on the agent performance. The DRL agent with the best performance was compared to a rule-based controller assumed as a baseline during a three-month heating season. The DRL controller outperformed the baseline after two weeks of deployment, with an overall performance improvement related to control of indoor temperature conditions. Moreover, the adaptability of the DRL agent was tested for various control scenarios, simulating changes of external weather conditions, indoor temperature setpoint, building envelope features and occupancy patterns. The agent dynamically deployed, despite a slight increase in energy consumption, led to an improvement of indoor temperature control, reducing the cumulative sum of temperature violations on average for all scenarios by 75% and 48% compared to the baseline and statically deployed agent respectively.
Highlights
Buildings are rated among the most energy-intensive uses, consuming approximately 40% of the worldwide energy demand, with CO2 emissions of up to 36% [1]
A model-free algorithm belonging to the Deep Reinforcement Learning (DRL) class, Soft ActorCritic, was implemented to control the supply water temperature to radiant terminal units of a heating system serving an office building
Thespecetrifoonrm. aInnicteiaollfyt,htehDe RpLerafogremntainnctehoefotnhlienDe tRraLinaignegnpt hinastehwe aosnclionme-training phase was pared with the baselcionme.pAafrteedrwwairthdst,hdeubrainseglitnhee. sAceftnearwrioaradnsa, ldyusirsin, tghtehreescuelntsaoribotaainnaeldysfiosr, the results obtained the agents deployedfostratthiceaallgyeanntsdddeypnloaymeidcasltlaytiacraellhyiganhdligdhytnedam. ically are highlighted
Summary
Buildings are rated among the most energy-intensive uses, consuming approximately 40% of the worldwide energy demand, with CO2 emissions of up to 36% [1]. Researchers have focused their attention on innovative control strategies for HVAC systems, capable of maintaining indoor thermal comfort conditions and, at the same time, reducing their energy consumption. These strategies need to be able to handle signals from the electrical grid in order to meet power requirements and improve the grid reliability and stability [3,5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
