eess.SYNov 10, 2026

Decision-Focused Learning via Neural Optimization Layers for Battery-Assisted Grid-Import Smoothing in AI Data Centers

Authors: Xinda Zheng, Canchen Jiang, Frits de Nijs, Edward Lam, Markus Wagner

Organizations: Department of Data Science and AI, Faculty of Information Technology, Monash University, Australia

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.

Figures & tables

Explore similar work

CardsList
  1. Power-Flexible AI Data Centers: A New Paradigm for Grid-Responsive Compute

    Jun 23, 2026Chris Williams, Philip Colangelo, Ayse Coskun +15Demand ResponseCarbon-Aware Computing

  2. PowerAtlas: Feasibility-Aware Language Models for Electricity-Computing Co-Scheduling

    Jul 29, 2026Kaiwen Jiang, Siya Xu, Ziyue Zhu +4LLM AgentsPower Systems

  3. OpenG2G: A Simulation Platform for AI Datacenter-Grid Runtime Coordination

    May 6, 2026Jae-Won Chung, Zhirui Liang, Yanyong Mao +3Demand ResponsePower Systems