Preprint
Aug 2026
Refined Thompson Learning for Adaptive Bandits: Power-Efficient Flexibility Scheduling Across Data Centers
A contextual restless multi-armed bandit (CRMAB) framework in which a grid operator requests load reductions without observing internal job-scheduling decisions is proposed, demonstrating the economic potential of data-center flexibility as a grid service and highlighting the importance of high-quality, open-source AI...
Zi-Xi Chen, Yifu Ding, Rui-Cheng Ao et al.
· 0 citations