This paper presents a laboratory study of Offline-trained Reinforcement Learning (RL) control of a Heating Ventilation and Air-Conditioning (HVAC) system. We conducted the experiments on a radiant floor heating system consisting of two temperature zones located in Denmark. The buildings are subjected to real-world weather. A previous paper describes the algorithm we tested, which we summarize in this paper. First, we present a benchmarking test which we conducted during spring 2021 and winter 2021/2022. This data is used in the Offline RL framework to train and deploy the RL policy, which we then tested during winter 2021/2022 and spring 2022. An analysis of the data shows that the RL policy showed predictive control-like behavior, and reduced the oscillations of the system by a minimum of 40%. Additionally, we show that the RL policy is minimum 14% more cost-effective than the traditional control policy used in the benchmarking test.
A Laboratory Test of an Offline-trained Multi-Agent Reinforcement Learning Algorithm for Heating Systems
2023-05-01
Blad , C , Bøgh , S , Kallesøe , C & Raftery , P 2023 , ' A Laboratory Test of an Offline-trained Multi-Agent Reinforcement Learning Algorithm for Heating Systems ' , Applied Energy , vol. 337 , 120807 . https://doi.org/10.1016/j.apenergy.2023.120807
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Reinforcement Learning , Heating , HVAC , Energy , Buildings , Artificial Intelligence (AI) , Multi-agent deep reinforcement learning , Heating and cooling , /dk/atira/pure/sustainabledevelopmentgoals/affordable_and_clean_energy , name=SDG 7 - Affordable and Clean Energy , /dk/atira/pure/sustainabledevelopmentgoals/sustainable_cities_and_communities , name=SDG 11 - Sustainable Cities and Communities , /dk/atira/pure/sustainabledevelopmentgoals/climate_action , name=SDG 13 - Climate Action
DDC: | 629 |
Europäisches Patentamt | 2022
|AUTONOMOUS VEHICLE TESTING OPTIMIZATION USING OFFLINE REINFORCEMENT LEARNING
Europäisches Patentamt | 2024
|