Balancing comfort and energy consumption of a heat pump using batch reinforcement learning with fitted Q-iteration

Vázquez-Canteli, José (University of Texas at Austin, Austin, TX, USA) ; Kaempf, Jérôme (School of Engineering and Architecture (HEIA-FR), HES-SO // University of Applied Sciences Western Switzerland) ; Nagy, Zoltán (University of Texas at Austin, Austin, TX, USA)

In this study, a heat pump satisfies the heating and cooling needs of a building, and two water tanks store heat and cold respectively. Reinforcement learning (RL) is a model-free control approach that can learn from the behaviour of the occupants, weather conditions, and the thermal behaviour of the building in order to make near-optimal decisions. In this work we use of a specific RL technique called batch Q-learning, and integrate it into the urban building energy simulator CitySim. The goal of the controller is to reduce the energy consumption while maintaining adequate comfort temperatures.


Keywords:
Article Type:
scientifique
Faculty:
Ingénierie et Architecture
School:
HEIA-FR
Institute:
Energy - Institut de recherche appliquée en systèmes énergétiques
Date:
2017-09
Pagination:
6 p.
Published in:
Energy Procedia
Numeration (vol. no.):
2017, vol. 122, pp. 415-420
DOI:
ISSN:
18766102
Appears in Collection:



 Record created 2021-05-18, last modified 2021-05-28

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)