本地 AI 智能体在电力电子仿真中的应用:部署、测量与成本
Local AI Agents in Power Electronics Simulation: Deployment, Measurements and Costs
Yuzhuo Li · Pasan Gunawardena · Yunwei Li
中文摘要
智能体人工智能(agentic AI)正在电力电子领域兴起,用于驱动过去主要由工程师手工完成的仿真闭环。在该闭环中,变换器设计或其所连网络的研究需经过构建、运行、测量与修改,直至满足规格。此类智能体可由云端 API 或本地推理设备提供服务。对于设计、客户数据或出口管制材料不能离场且仿真器在本地授权的机构,本地部署是自然选择。此时智能体成为机构自有设备上的电力负载:每次运行在本地设备上消耗功率与能量、生成 token 并占用时间。然而现有工作主要关注云端模型能实现什么,本地部署在真实仿真任务上的功率、能量、token 与时间成本及其权衡关系,在可比条件下缺乏定量研究。为填补这一空白,本文提出系统评估框架,将本地服务模型应用于从变换器级到系统级的智能体电力电子任务,测量其功率、能量、token 与时间成本,并据此刻画本地智能体在此类任务上的能力边界与每解决任务成本。结果有望为智能体 AI 在电力电子及其服务的电力系统中的应用提供实践洞见。
关键要点
- 01现有研究多关注云端模型能力,本地部署在真实仿真任务上的功率、能量、token 与时间成本缺乏定量研究
- 02提出系统评估框架,将本地服务模型用于从变换器级到系统级的智能体电力电子任务
- 03测量本地部署的功率、能量、token 与时间成本,刻画能力边界与每解决任务成本
- 04面向设计、客户数据或出口管制材料不能离场且仿真器本地授权的机构场景
解读
尚无解读。
原始英文摘要
arXiv:2611.24880v1 Announce Type: new Abstract: Agentic artificial intelligence (AI) is emerging in power electronics, where it drives the simulation loop that engineers used to close largely by hand. In this loop, a converter design, or a study of the network it connects to, is built, run, measured and revised until it satisfies its specification. Such an agent can be served from a cloud API or from an inference device on the premises. For organizations whose designs, customer data or export-controlled material cannot leave the site, and whose simulators are licensed there, local deployment is the natural choice. In such a deployment, the agent becomes an electrical load on the organization's own equipment, i.e., every run consumes power and energy on a local device, generates tokens and takes time. However, existing work focuses mainly on what the agent can achieve with cloud-hosted models. What a local deployment costs in power, energy, tokens and time on real simulation tasks, and what its choices trade against one another, has received little quantitative investigation under comparable conditions. To address this gap, a systematic evaluation framework is presented in this paper. It applies locally served models to agentic power electronics tasks, from the converter level to the system level, and measures their power, energy, token and time costs. Based on these measurements, the capability boundary of a local agent on such tasks and the cost per solved task are characterized. The results are expected to provide practical insight for the use of agentic AI in power electronics and the power systems it serves.