Bayesian-Optimized HESS for AI Data Centers
Grid-mode-aware AI data center power smoothing via Hybrid Energy Storage Systems (IEEE TPEC, 2026).
AI training and inference workloads generate steep power ramps that degrade battery lifespan and threaten local grid stability.
This project designs a grid-mode-aware coordination framework for a Hybrid Energy Storage System (HESS)—combining high-energy Battery Energy Storage with high-power Supercapacitors—tuned via Bayesian Optimization to smooth volatile AI data center power profiles while minimizing degradation.
Publication:
- S. Mohammadi, Q.M. Hoang, V.H. Bui, W. Su (2026). “Grid-Mode-Aware AI Data Center Power Smoothing via Bayesian-Optimized Hybrid Energy Storage System,” 2027 IEEE Texas Power and Energy Conference (TPEC) (Submitted). arXiv:2611.03436