PowerChain：一个用于自动化配电网分析的可验证智能体 AI 系统
PowerChain: A Verifiable Agentic AI System for Automating Distribution Grid Analyses
查看机构详情
- Dept. of Electrical and Biomedical Engineering, The University of Vermont（维珍尼亚大学电气与生物医学工程系）
- Dept. of Electrical and Computer Engineering, The University of Texas at Austin（德克萨斯大学奥斯汀分校电气与计算机工程系）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对配电网分析工作流难自动化、难泛化的问题，本文提出 PowerChain 智能体系统，利用电力系统工具监督信号与专家验证推理轨迹动态生成上下文，在真实数据上较基线最高提升144%。
中文摘要 AI 辅助
快速电气化和脱碳正在增加配电网（DG）运行与规划的复杂性，因此需要先进的计算分析来确保可靠性和韧性。这些分析依赖于彼此分散的工作流，其中包含复杂模型、函数调用和数据管道，需要大量专家知识，并且仍然难以自动化。人力和预算限制进一步制约了公用事业公司大规模应用此类分析的能力。为弥补这一差距，我们构建了智能体系统 PowerChain，它能够自主执行复杂的电网分析。现有智能体 AI 系统通常采用自底向上方式开发，并为预定义分析任务定制上下文；因此，它们无法泛化到智能体从未见过的任务。相比之下，为泛化到未见过的 DG 分析任务，PowerChain 利用来自自包含电力系统工具（例如 GridLAB-D）的监督信号，以及一组经过专家标注和验证的优化推理轨迹，动态生成结构化上下文。对于以自然语言定义的复杂 DG 任务，在真实公用事业数据上的实证结果表明，PowerChain 相比基线的性能提升最高达 144%。
英文摘要
Rapid electrification and decarbonization are increasing the complexity of distribution grid (DG) operation and planning, necessitating advanced computational analyses to ensure reliability and resilience. These analyses depend on disparate workflows comprising complex models, function calls, and data pipelines that require substantial expert knowledge and remain difficult to automate. Workforce and budget constraints further limit utilities' ability to apply such analyses at scale. To address this gap, we build an agentic system PowerChain, which is capable of autonomously performing complex grid analyses. Existing agentic AI systems are typically developed in a bottom-up manner with customized context for predefined analysis tasks; therefore, they do not generalize to tasks that the agent has never seen. In comparison, to generalize to unseen DG analysis tasks, PowerChain dynamically generates structured context by leveraging supervisory signals from self-contained power systems tools (e.g., GridLAB-D) and an optimized set of expert-annotated and verified reasoning trajectories. For complex DG tasks defined in natural language, empirical results on real utility data demonstrate that PowerChain achieves up to a 144/% improvement in performance over baselines.
