逆变器动态模型辨识的递归自改进LLM智能体
Recursive Self-Improvement LLM Agents for Inverter Dynamic Model Identification
浏览论文内容
中文总结 AI 辅助
本文提出利用递归自改进LLM智能体在标准控制模块组成的框图搜索空间中辨识逆变器动态模型，以频域导纳数据为引导，通过程序进化框架ThetaEvolve实现，在GFL基准上将NRMSE从0.470降至0.0435，识别出接近真实控制器的15模块闭环结构。
中文摘要 AI 辅助
本文是一篇立场论文。我们论证了递归自改进（RSI）大语言模型（LLM）智能体是逆变器资源（IBRs）动态模型辨识的一种天然搜索引擎，这些逆变器资源的内部控制通常是专有的，对电网运营商隐藏。白盒模型提供物理透明性，但需要供应商披露；黑盒模型避免这一要求，但牺牲可解释性；现有的灰盒方法，包括稀疏回归和符号回归，不适合发现反馈控制架构或纳入控制工程先验知识。我们的立场是，这一差距可以通过以下方式缓解：（1）将搜索空间限制为类型化词汇表的标准控制模块，包括PI控制器、锁相环（PLLs）、低通滤波器等，在框图语法规则下组合；（2）使用RSI LLM智能体对候选框图模型执行程序搜索，以公共耦合点（PCC）的测量频域导纳数据为指导，同时通过非线性最小二乘法拟合每个候选模型的自由参数。我们通过改编ThetaEvolve（一个支持上下文内进化和测试时学习的开源程序进化框架）来实例化这一立场，用于逆变器模型发现。在一个电网跟随（GFL）逆变器基准的概念验证研究中，RSI循环将朴素开环模型的归一化均方根误差（NRMSE）从0.470降低到0.0435，并识别出一个15模块的闭环结构，该结构与隐藏的真实GFL控制器非常相似。
英文摘要
This is a position paper. We demonstrate that recursive self-improvement (RSI) large language model (LLM) agents are a natural search engine for dynamic model identification of inverter-based resources (IBRs) whose internal controls are often proprietary and hidden from grid operators. White-box models provide physical transparency but require vendor disclosure; black-box models avoid this requirement but sacrifice interpretability; and existing grey-box approaches, including sparse and symbolic regression, are poorly suited to discovering feedback control architectures or incorporating control-engineering priors. Our position is that this gap can be alleviated by (1) restricting the search space to a typed vocabulary of standard control modules, including PI controllers, phase-locked loops (PLLs), low-pass filters, etc., composed under block-diagram grammar rules, and (2) using an RSI LLM agent to perform program search over candidate block-diagram models, guided by measured frequency-domain admittance data at the point of common coupling (PCC), while fitting the free parameters of each candidate by nonlinear least squares. We instantiate this position by adapting ThetaEvolve, an open-source program-evolution framework supporting in-context evolution and test-time learning, to inverter model discovery. In a proof-of-concept study on a grid-following (GFL) inverter benchmark, the RSI loop reduces the normalized root mean square error (NRMSE) of a naive open-loop model from 0.470 to 0.0435 and identifies a 15-module closed-loop structure that closely resembles the hidden ground-truth GFL controller.
发表机构
- University of California San Diego（加州大学圣地亚哥分校）
- Texas A&M University（德克萨斯农工大学）
机构由 AI 辅助整理，请以论文原文为准。
