arXiv · 2611.13694
Decision-Focused Learning via Neural Optimization Layers for Battery-Assisted Grid-Import Smoothing in AI Data Centers
Abstract
Rapid AI data-center power fluctuations challenge grid integration. Sustained grid-import smoothing requires allocating limited battery power and energy under uncertain demand. We formulate risk-aware BESS scheduling that coordinates advance reserve commitments and demand-responsive dispatch, accounting for operating costs, grid-ramp penalties, and their conditional value-at-risk. We develop battery scheduling decision-focused learning (BS-DFL) with a constraint-aware neural optimization layer trained directly from this objective without optimal-solution labels. The trained layer is then frozen to guide demand-predictor learning through scheduling costs and ramping risk, enabling solver-free rolling-horizon scheduling. In a 10,000-minute simulation using loads derived from measured AI workloads, BS-DFL reduces mean absolute minute-to-minute grid-import changes by 71.70% and total scheduling cost by 18.01% relative to an MSE-trained predictor coupled with a mixed-integer linear programming solver, with an average decision time of 18.77 ms.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Xinda Zheng, Canchen Jiang, Frits de Nijs, Edward Lam, Markus Wagner. 2026-11-10. Decision-Focused Learning via Neural Optimization Layers for Battery-Assisted Grid-Import Smoothing in AI Data Centers. https://searcharxiv.com/abs/2611.13694
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.