The paper introduces Decision‑Focused Learning via Neural Optimization Layers (BS‑DFL) for battery‑assisted grid‑import smoothing in AI data centers. It formulates a risk‑aware battery energy storage system scheduling problem that balances reserve commitments, demand‑responsive dispatch, operating costs, grid‑ramp penalties, and conditional value‑at‑risk. By training a constraint‑aware neural optimization layer directly on the scheduling objective, the method eliminates the need for optimal‑solution labels and enables fast, solver‑free rolling‑horizon scheduling, achieving a 71.70% reduction in minute‑to‑minute grid‑import changes and an 18.01% cost savings in a 10,000‑minute simulation.
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...
arXiv:2605. 02965v2 Announce Type: replace Abstract: Artificial intelligence-generated content (AIGC) has emerged as a transformative paradigm for automating the creation of diverse and customized content, giving rise to rapidly growing computational workloads in cloud data centers.
arXiv:2606. 00561v1 Announce Type: cross Abstract: Deep reinforcement learning (RL) offers a promising route to real-time power grid operation, yet large neural policies are costly to evaluate, hard to deploy on constrained hardware, and opaque to operators.
arXiv:2606. 30316v1 Announce Type: new Abstract: This paper studies Reinforcement Learning as an online controller for curtailment-aware workload shifting in wind-turbine-integrated high-performance computing (HPC) data centers.
arXiv:2505. 05203v3 Announce Type: replace-cross Abstract: With the increasing penetration of renewable energy and inverter-based resources, traditional physics-based power-system operation faces growing challenges in maintaining economic efficiency, security, and robustness.
arXiv:2609.37065v1 Announce Type: new Abstract: Decision-making under uncertainty often relies on predicted parameters, yet accurate prediction does not necessarily lead to good operational decisions...
The paper presents an LLM-based predictive scheduling system that forecasts execution time and energy consumption from source code, aiming to improve data center sustainability. By integrating these predictions into a real-time GPU allocation algorithm, the system reduces both energy use and queuing delays. In a collaboration with a data center, the approach achieved a 32% drop in energy consumption and a 30% reduction in waiting time.
This paper studies Reinforcement Learning as an online controller for curtailment-aware workload shifting in wind-turbine-integrated high-performance computing (HPC) data centers. We introduce a reproducible fixed-day simulation framework with synthetic wind and price signals and delayed completion feedback, designed to be extensible toward more complex scenarios.
arXiv:2606. 10600v1 Announce Type: cross Abstract: Radio frequency wireless power transfer (RF-WPT) is an enabling technology for supporting uninterrupted communications in future Internet of Things systems by reducing the need for battery replacement and mitigating battery-waste-related issues.
arXiv:2604. 25848v2 Announce Type: replace Abstract: We study city-scale control of electric-vehicle (EV) ride-hailing fleets where dispatch, repositioning, and charging decisions must respect charger and feeder limits under uncertain, spatially correlated demand and travel times.
arXiv:2607. 12856v1 Announce Type: new Abstract: Buildings are expected to shift cooling loads in response to grid conditions.
arXiv:2609.15389v1 Announce Type: cross Abstract: As artificial intelligence systems increasingly rely on distributed and collaborative training, the energy footprint of these processes becomes a sha...