eess.SYNov 17, 2026

Solver-Free and Cost-Aware Online Scheduling of AI Data Center Tasks

Authors: Xin Qin, Dawei Qiu, Fei Teng

Organizations: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · Department of Electrical and Electronic Engineering, Imperial College London, London, UK

Abstract

AI data centers receive computing tasks continuously, whereas solver-based optimization takes time to run and electricity is priced per settlement period. This paper bridges this timing gap through a solver-free online optimization rule inspired by dual decomposition. The rule assigns each task a start period upon arrival to optimize energy cost subject to operational constraints, shifting flexible tasks toward low-price periods while keeping high-priority tasks on schedule. Simulations on the A100 GPU trace (3,456 GPUs, 1,343 tasks) show that the proposed rule keeps GPU and CPU use within capacity while scheduling tasks at low cost. Compared with a multi-timescale optimization benchmark, it achieves a lower cost and, because it needs no solver, much less computation time.

Figures & tables

Explore similar work

CardsList
  1. Power- and Fragmentation-aware Online Scheduling for GPU Datacenters

    Dec 23, 2024Francesco Lettich, Emanuele Carlini, Franco Maria Nardini +2Online Resource AllocationData Center Energy Management

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

    Nov 10, 2026Xinda Zheng, Canchen Jiang, Frits de Nijs +2Data Center Energy ManagementPower Systems

  3. Scheduling Parallel Optical Circuit Switches for AI Training

    Mar 7, 2026Kevin Liang, Litao Qiao, Isaac Keslassy +1