Toward physics-guided safe deep reinforcement learning for green data center cooling control

• Main Authors: Wang, Ruihang, Zhang, Xinyi, Zhou, Xin, Wen, Yonggang, Tan, Rui
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering::Computer applications::Physical sciences and engineering; Data Center; Safe Reinforcement Learning; Energy Efficiency; Thermal Safety
• Online Access: https://hdl.handle.net/10356/157736
• Institution: Nanyang Technological University

Deep reinforcement learning (DRL) has shown good performance in tackling Markov decision process (MDP) problems. As DRL optimizes a long-term reward, it is a promising approach to improving the energy efficiency of data center cooling. However, enforcement of thermal safety constraints during DRL�...