Application of deep reinforcement learning to intelligent distributed humidity control system

Guo, Da; Luo, Danfeng; Zhang, Yong; Zhang, Xiuyong; Lai, Yuyang; Sun, Yunqi

doi:10.1007/s10489-022-04320-7

Cited by 3 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The naive RL approaches in HVAC were explored by 21,22 . Releasing the expressive capability of deep neural networks, fitted Q iteration and deep Q learning (DQN) were implemented in the HVAC systems with discrete action space 23,24 and indoor humidity control system 25 . Deep deterministic policy gradient (DDPG) was applied to optimize HVAC systems in green data center 26 , energy distribution system 27 and multi-zone residential HVAC systems 28,29 .…”

Section: Introductionmentioning

confidence: 99%

Efficient Multi-Agent Reinforcement Learning HVAC Power Consumption Optimization

Miao,

Cui,

et al. 2024

Preprint

View full text Add to dashboard Cite

Intelligent and energy-efficient heating, ventilation, and air conditioning (HVAC) system plays an important role in reducing energy consumption and protecting our environment. In this work, we focus on exploring suitable power optimization strategies using reinforcement learning (RL) without relying on human prior knowledge. A novel RL approach, multi-stabilization network(MADDPG-MSN) is proposed to tackle the sample-efficiency issue of current RL-based approaches for HVAC systems. Employing the multi-stabilization network trick, MADDPG-MSN efficiently learns to balance temperature control and power consumption with a limited number of interactions. Evaluated by the simulated data center scenario, it reduced 28% powerusage without compromising temperature control capability compared with the traditional model-predictive controller. In the real-world air conditioner testing, it demonstrated superior control performances than the built-in controller with 35% less power consumption and 21% smaller standard deviation of the indoor temperature after 72 hours’ learning. These results demonstrate the superior effectiveness and practicality of MADDPG-MSN in HVAC power consumption optimization, expanding the potential of RL as an emerging direction to more energy-saving systems.

show abstract