← 返回
LLM协调的频率调节自动竞价：交叉注意力分布强化学习智能体框架
LLM-coordination in auto-bidding of frequency regulation: Cross-attention distributional reinforcement agentic learning
| 作者 | Borui Zhang · Chaojie Lia · Guo Chena · Zhao Xub · Zhaoyang Dongc |
| 期刊 | Applied Energy |
| 出版日期 | 2025年1月 |
| 卷/期 | 第 401 卷 |
| 技术分类 | 储能系统技术 |
| 技术标签 | 储能系统 调峰调频 |
| 相关度评分 | ★★★★★ 5.0 / 5.0 |
| 关键词 | An LLM-coordination auto-bidding system for BESS in Australia’s energy and FCAS markets is developed leveraging an LLM-agentic coordination framework for user instruction response bidding automation and interpretable feedback. |
语言:
中文摘要
摘要 电池储能系统（BESS）涉及大量资本投入，因此盈利能力成为关键关注点。在澳大利亚国家电力市场（NEM）中，频率控制辅助服务（FCAS）市场已成为BESS的主要收入来源。然而，FCAS市场的高波动性和复杂动态特性使得捕捉潜在市场机会并制定盈利性竞价策略极具挑战性。为应对这些挑战，本文提出了一种面向联合电能与FCAS市场的电池储能系统的大语言模型（LLM）协调式自动竞价系统。该系统引入了一种LLM驱动的智能体协调框架，通过多智能体工作流以及基于心智理论（ToM）推理的交互机制，实现自动化且可解释的竞价决策。为了识别关键市场模式，本文提出一种交叉注意力架构，联合建模趋势特征与周期性特征，以增强对市场动态的表征能力。随后，设计了一种基于软演员-评论家（Soft Actor-Critic, SAC）的分布强化学习（dDRL）算法，通过持续学习回报分布，在FCAS市场固有的认知不确定性和随机不确定性下优化竞价策略。所提系统利用澳大利亚南部实际市场数据进行了验证，实验结果表明，无论是在盈利能力方面，还是相较于传统的“先预测后优化”（PTO）方法及其他基线深度强化学习算法，本文提出的方法均表现出持续优越的性能。
English Abstract
Abstract Battery energy storage systems (BESSs) involve substantial capital investment, making profitability a critical concern. In Australia’s National Electricity Market (NEM), Frequency Control Ancillary Services (FCAS) markets have become a primary revenue source for BESSs. However, the high volatility and complex dynamics of FCAS markets make it highly challenging to capture potential market opportunities and formulate profitable bidding strategies. To address these challenges, this paper develops a large language model (LLM)-coordinated auto-bidding system for BESS in the joint energy and FCAS markets. The system introduces an LLM-agentic coordination framework to support automated and interpretable bidding through a multi-agent workflow and theory of mind (ToM) reasoning-based interaction. To recognize critical market patterns, a cross-attention architecture is proposed to jointly model trend and periodic features for enhanced representation of market dynamics. Then, a Soft Actor-Critic (SAC)-based distributional deep reinforcement learning (dDRL) algorithm is developed to optimize bidding strategies under epistemic and aleatoric uncertainties inherent in FCAS markets by continuously learning return distributions. The system is validated using actual South Australian market data, and the experimental results demonstrate that the proposed approach consistently outperforms traditional predict-then-optimize (PTO) methods and other baseline DRL algorithms in terms of profitability.
S
SunView 深度解读
该LLM协同自动竞价技术对阳光电源ST系列储能变流器及PowerTitan系统在澳洲等调频市场具有重要应用价值。论文提出的交叉注意力机制可增强市场动态识别,分布式深度强化学习算法能优化FCAS市场不确定性下的竞价策略,可集成至iSolarCloud平台实现储能资产智能竞价。该方法显著优于传统预测优化方法,为阳光电源储能系统在辅助服务市场的收益最大化提供AI决策支持,提升储能投资回报率,特别适用于高波动性电力市场的自动化交易场景。