# PowerAtlas: Towards Electricity-Computing Co-Scheduling for Power Systems

arXiv: https://arxiv.org/abs/2607.26710 · HTML: https://mlsanity.com/paper/2607.26710/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 78 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting](https://mlsanity.com/paper/2106.12931/) (2021)
- [Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling](https://mlsanity.com/paper/2106.05223/) (2021)
- [Don't Stop Me Now: Embedding Based Scheduling for LLMs](https://mlsanity.com/paper/2410.01035/) (2024)
- [Large Language Models for Power Scheduling: A User-Centric Approach](https://mlsanity.com/paper/2407.00476/) (2024)
- [Large Language Model Powered Automated Modeling and Optimization of Active Distribution Network Dispatch Problems](https://mlsanity.com/paper/2507.21162/) (2025)
- [Powerformer: A Section-adaptive Transformer for Power Flow Adjustment](https://mlsanity.com/paper/2401.02771/) (2024)
- [Large Language Models for Power System Applications: A Comprehensive Literature Survey](https://mlsanity.com/paper/2512.13004/) (2025)
- [A Guide to Reducing Carbon Emissions through Data Center Geographical Load Shifting](https://mlsanity.com/paper/2105.09120/) (2021)
- [Evaluating the Efficacy of LLM-Based Reasoning for Multiobjective HPC Job Scheduling](https://mlsanity.com/paper/2506.02025/) (2025)
- [Optimizing Parameters of the DC Power Flow](https://mlsanity.com/paper/2310.00447/) (2023)
- [Exploring the Impacts of Power Grid Signals on Data Center Operations using a Receding-Horizon Scheduling Model](https://mlsanity.com/paper/2204.06654/) (2022)
- [A Novel Hierarchical Co-Optimization Framework for Coordinated Task Scheduling and Power Dispatch in Computing Power Networks](https://mlsanity.com/paper/2508.04015/) (2025)
- [Harnessing Flexible Spatial and Temporal Data Center Workloads for Grid Regulation Services](https://mlsanity.com/paper/2602.01508/) (2026)
- [Rethinking Scientific Modeling: Toward Physically Consistent and Simulation-Executable Programmatic Generation](https://mlsanity.com/paper/2602.07083/) (2026)
- [Watts vs. Bytes: Turning Data Centers into Grid Assets via Storage Compute Co-Optimization](https://mlsanity.com/paper/2605.16190/) (2026)
- [Data Center Spatio-Temporal Load Flexibility in Security-Constrained Unit Commitment for Enhanced Grid Efficiency and Reliability](https://mlsanity.com/paper/2605.18517/) (2026)
- [Power-Flexible AI Data Centers: A New Paradigm for Grid-Responsive Compute](https://mlsanity.com/paper/2606.25098/) (2026)

## Abstract (arXiv)

The rapid growth of AI workloads is turning data centers into large-scale, volatile, yet spatiotemporally flexible grid loads, creating an urgent need for coordinated electricity-computing scheduling. Under stringent grid constraints, schedules from general-purpose large language models (LLMs) are often infeasible, causing line-flow violations and unserved load. We present PowerAtlas, an LLM-agent framework for electricity-computing co-scheduling that integrates historical instances, domain knowledge, and physical constraints to produce joint decisions satisfying both grid operational rules and the service-level agreements (SLAs) of computing tasks. Working with a provincial power utility in China, we built an experimental electricity-computing network and validated the decision loop on real data-center data; from de-identified operational data we further constructed ECBench, a benchmark of 2,000 scheduling instances with oracle-optimal solutions. Experiments across eleven LLMs demonstrate the effectiveness of PowerAtlas under realistic physical operating conditions, with consistent feasibility and cost gains across three open-weight backbones. Our code is publicly available at https://github.com/JAVA-Jiang/PowerAtlas.