LLM-Mediated Demand Response Coordination in Smart Microgrids

📄 arXiv: 2606.11050v1 📥 PDF

作者: J. de Curtò, I. de Zarzà

分类: cs.MA, cs.GT, eess.SY

发布日期: 2026-06-09

备注: Accepted for publication in 18th International Conference on Sustainability in Energy and Buildings (SEB-26), to appear in Springer Nature proceedings (KES Smart Innovation Systems and Technologies). The final authenticated version will be available online at Springer


💡 一句话要点

提出基于LLM的需求响应协调方法以解决微电网合作问题

🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture) 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 智能微电网 需求响应 大型语言模型 多智能体系统 博弈论 合作机制 能源管理

📋 核心要点

  1. 核心问题:现有方法在微电网中难以实现有效的合作,导致需求响应效果不佳。
  2. 方法要点:提出利用大型语言模型生成结构化指令,结合博弈论与叙述评估,促进生产者之间的合作。
  3. 实验或效果:结构化指令实现33.3%的需求削减合作,相较于无结构信息和无干预基线有显著提升。

📝 摘要(中文)

有效的需求响应在智能微电网中需要生产者自愿合作,然而这构成了一个结构上等同于重复囚徒困境的协调问题。本文提出了一种多智能体模拟方法,利用大型语言模型(LLM)影响编译器向异质生产者代理发出结构化的需求响应指令。每个代理采用混合决策架构,结合博弈论基础概率与LLM对协调信号的叙述评估。通过将战略推理与叙述评估分离,该模型在六种个性原型中生成了现实的生产者行为,合作基线接近50%。结构化指令实现了33.3%的需求削减合作,优于无结构信息和无干预基线,且在不同网络拓扑下均保持优势。

🔬 方法详解

问题定义:本文旨在解决智能微电网中生产者自愿合作的协调问题。现有方法在直接决策中使用LLM时,常表现出强烈的合作偏见,导致动态效果平坦,无法适应不同的电网条件。

核心思路:论文提出将战略推理与叙述评估分离,利用LLM生成结构化的需求响应指令,从而提高生产者的合作行为和响应效率。这样的设计能够更好地模拟现实中的决策过程。

技术框架:整体架构包括多个模块:首先是LLM影响编译器生成结构化指令,其次是异质生产者代理根据混合决策架构进行响应,最后通过网络拓扑优化指令传播。

关键创新:最重要的技术创新在于采用混合决策架构,结合博弈论与LLM的叙述评估,解决了LLM作为直接决策者时的合作偏见问题。

关键设计:在参数设置上,采用了基于收益历史、邻居模仿和利用记忆的博弈论基础概率,确保了决策的多样性与灵活性。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,结构化指令实现了33.3%的需求削减合作,相较于无结构信息的27.0%和无干预基线的28.0%有显著提升,且在不同的网络拓扑下均保持了这一优势,验证了设计的有效性。

🎯 应用场景

该研究的潜在应用领域包括智能电网、可再生能源管理和城市能源系统的需求响应协调。通过提高生产者的合作效率,能够有效降低能源消耗和提升电网的稳定性,具有重要的实际价值和未来影响。

📄 摘要(原文)

Effective demand response in smart microgrids requires prosumers to cooperate voluntarily under strategic self-interest, a coordination problem structurally equivalent to a repeated Prisoner's Dilemma on a social network. This paper presents a multi-agent simulation in which a Large Language Model (LLM) Influence Compiler issues structured demand-response directives to a population of heterogeneous prosumer agents, each governed by a hybrid decision architecture combining game-theoretic base probability (derived from payoff history, neighbour imitation, and exploitation memory) with LLM narrative evaluation of incoming coordination signals. The hybrid architecture resolves a key methodological challenge: LLMs aligned via Reinforcement Learning from Human Feedback (RLHF) exhibit strong cooperation bias when used as direct decision-makers, producing flat dynamics regardless of grid conditions. By separating strategic reasoning from grounded narrative evaluation, the model generates realistic prosumer behaviour across six personality archetypes, with baseline cooperation near 50% and clear differentiation under influence. Compiled structured directives achieve 33.3% demand-curtailment cooperation versus 27.0% for unstructured messaging and 28.0% for a no-intervention baseline ($Δ_\mathrm{comp} = +0.063$), with the advantage preserved across both grounded and idealized agent substrates ($Δ= +0.083$) and across all resistance levels ($R = 0.1$ to $0.7$). Hub-targeted dissemination via high-centrality network nodes outperforms peripheral or random targeting, confirming that grid topology provides mechanistic amplification independent of message content. These results suggest that structured LLM compilation, grounded agent reasoning, and network-aware targeting are complementary design principles for scalable, interpretable demand-response coordination in smart-city energy systems.