TY - GEN
T1 - Double deep Q-networks for optimizing electricity cost of a water heater
AU - Amasyali, Kadir
AU - Kurte, Kuldeep
AU - Zandi, Helia
AU - Munk, Jeffrey
AU - Kotevska, Olivera
AU - Smith, Robert
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/2/16
Y1 - 2021/2/16
N2 - Electric water heaters represent 14% of the electricity consumption in the residential buildings and the cost associated with domestic water heating account for a good portion of the household expenses in the United States. In this context, intelligent control of water heaters gained a lot of research attention. In recent years, a significant number of intelligent water heater controllers, with various methods and intended uses, have been proposed. However, existing studies are mostly model-based approaches that require an accurate modelling of the water heater. Towards addressing this research gap, this paper presents a model-free reinforcement learning-based controller for a day-ahead price market. The controller aims to minimize the cost of domestic water heating while maintaining the user comfort. The results showed that the developed controller can help save energy cost while maintaining the temperatures within the desired comfort band.
AB - Electric water heaters represent 14% of the electricity consumption in the residential buildings and the cost associated with domestic water heating account for a good portion of the household expenses in the United States. In this context, intelligent control of water heaters gained a lot of research attention. In recent years, a significant number of intelligent water heater controllers, with various methods and intended uses, have been proposed. However, existing studies are mostly model-based approaches that require an accurate modelling of the water heater. Towards addressing this research gap, this paper presents a model-free reinforcement learning-based controller for a day-ahead price market. The controller aims to minimize the cost of domestic water heating while maintaining the user comfort. The results showed that the developed controller can help save energy cost while maintaining the temperatures within the desired comfort band.
KW - Artificial neural networks
KW - Deep Q-networks
KW - Deep reinforcement learning
KW - Water heater
UR - http://www.scopus.com/inward/record.url?scp=85103436839&partnerID=8YFLogxK
U2 - 10.1109/ISGT49243.2021.9372205
DO - 10.1109/ISGT49243.2021.9372205
M3 - Conference contribution
AN - SCOPUS:85103436839
T3 - 2021 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2021
BT - 2021 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2021
Y2 - 16 February 2021 through 18 February 2021
ER -