Deep Reinforcement Learning for Smart Home Energy Management
Nanjing University of Posts and Telecommunications · University of Leicester · +2 more institutions
Abstract
We investigate an energy cost minimization problem for a smart home in the absence of a building thermal dynamics model with the consideration of a comfortable temperature range. Due to the existence of model uncertainty, parameter uncertainty (e.g., renewable generation output, nonshiftable power demand, outdoor temperature, and electricity price), and temporally coupled operational constraints, it is very challenging to design an optimal energy management algorithm for scheduling heating, ventilation, and air conditioning systems and energy storage systems in the smart home. To address the challenge, we first formulate the above problem as a Markov decision process, and then propose an energy management…
Citation impact
- FWCI
- 18.89
- Percentile
- 100%
- References
- 50
Authors
9- LYLiang YuCorresponding
Nanjing University of Posts and Telecommunications
- WXWeiwei Xie
Nanjing University of Posts and Telecommunications
- DXDi Xie
Nanjing University of Posts and Telecommunications
- YZYulong Zou
Nanjing University of Posts and Telecommunications
- DZDengyin Zhang
Nanjing University of Posts and Telecommunications
Topics & keywords
- Computer science
- Markov decision process
- Reinforcement learning
- Robustness (evolution)
- Energy management
- Mathematical optimization
- Demand response
- Building management system
- Affordable and clean energy