arXiv cs.MA· Carlos Mart\'in-Abell\'an, Mark Kr\"oll·· 11 小时前AI 评分24
OpenMeter：面向工业智能电表数据的隐私保护自然语言查询多智能体系统
Enabling Privacy-Preserving Natural Language Access to Industrial Smart Meter Data
AI 导读
OpenMeter 是一个模式无关的多智能体系统（MAS），可将自然语言查询翻译为可执行代码和人类可读的洞察，让非技术人员无需 SQL 专业知识即可访问工业智能电表数据，同时避免敏感数据经由云端 LLM 处理。
正文 · 原文
Abstract:Energy management officers and grid operators increasingly rely on smart meter data for anomaly detection, performance monitoring, and strategic decision-making. However, extracting actionable insights from large-scale, heterogeneous telemetry databases requires advanced SQL and data engineering expertise, creating a critical bottleneck for non-technical personnel. Furthermore, the strict data privacy regulations and security constraints inherent to critical energy infrastructure often prohibit the routing of sensitive consumer data through cloud-based Large Language Models (LLMs). To address these challenges, we present OpenMeter, a schema-agnostic Multi-Agent System (MAS) designed to translate natural language queries into executable code and human-readable insights. This architecture lowers the technical barrier for day-to-day utility operations by empowering non-expert personnel to interact with complex databases through intuitive natural language dialogue, transforming raw telemetry into a highly valuable tool for routine grid workflows and strategic decisions. Multi-scenario ablation studies over this environment demonstrate that full multi-agent orchestration shows its largest observed accuracy gains on resource-constrained local hardware (+6.1 pp EX-R over the strongest single-agent configuration); at frontier scale, individual components retain value but should be enabled selectively, indicating that the cost of full orchestration is justified specifically where privacy demands local execution.
| Comments: | 9 pages, 1 figure, 6 tables |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Databases (cs.DB); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.09372 [cs.AI] |
| (or arXiv:2611.09372v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.09372 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Carlos Martín-Abellán [view email]
[v1]
Fri, 6 Nov 2026 12:11:34 UTC (22 KB)
来源：arXiv cs.MA · arxiv.org