PowerAtlas：面向电力系统的电-计算协同调度
PowerAtlas: Towards Electricity-Computing Co-Scheduling for Power Systems
浏览论文内容
中文总结 AI 辅助
PowerAtlas是用于电-计算协同调度的LLM智能体框架，整合多类约束生成可行方案，构建含2000个实例的ECBench基准，在11种LLM上验证了有效性。
中文摘要 AI 辅助
AI工作负载的快速增长正将数据中心转变为大规模、波动大但时空灵活的电网负荷，催生了对电-计算协同调度的迫切需求。在严格的电网约束下，通用大型语言模型（LLM）生成的调度方案往往不可行，会导致线路潮流越限和负荷未满足。我们提出PowerAtlas，一种用于电-计算协同调度的LLM智能体框架，它整合历史实例、领域知识和物理约束，生成同时满足电网运行规则与计算任务服务水平协议（SLA）的联合决策。我们与中国某省级电力公司合作构建了实验性电-计算网络，并基于真实数据中心数据验证了决策循环；还从去标识化的运行数据中构建了ECBench，这是一个包含2000个调度实例及最优解的基准。对11种LLM的实验表明，PowerAtlas在真实物理运行条件下有效，在三个开放权重主干模型上均实现了一致的可行性与成本收益，代码已公开。
英文摘要
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.
发表机构
- Beijing University of Posts and Telecommunications（北京邮电大学）
- State Grid Liaoning Electric Power Co., Ltd.（国网辽宁省电力有限公司）
- Nanyang Technological University（南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。
