摘要
传统农灌负荷的使用具有集中性和无序性,显著加剧电力系统的供需不平衡与运行成本。为提升农业园区运行的经济性和光伏资源的消纳能力,通过刻画农灌负荷特性,结合作物生长用能需求,提出一种基于大语言模型(largelanguagemodel,LLM)场景生成和双层优化的多农业园区优化调度模型。该模型利用LLM时序分析能力进行光伏短期发电功率预测,然后通过LLM知识推理能力构建农业用水知识图谱,知识图谱中丰富的语义关系辅助LLM推理和预测,生成更符合实际情况的农业供电-灌溉-蓄水场景。双层优化调度模型在生成场景基础上,以园区经济运行为优化目标,对多农业园区供电-灌溉-蓄水进行耦合优化调度。最后,通过仿真验证,本文所提出的方法显著提升了农业园区电力系统运行稳定性,并有效降低了系统运行成本。
The traditional agricultural irrigation load exhibits concentration and disorder,significantly exacerbating the imbalance between supply and demand and increasing operational costs in power systems.To enhance the economic effi-ciency of agricultural parks and the absorption capacity of photovoltaic resources,this study proposes a multi-agricultural park optimization scheduling model based on scenario generation using a large language model(LLM)and bi-level opti-mization.By characterizing the agricultural irrigation load and considering the energy demands of crop growth,the model forecasts the temporal analysis capabilities of the LLM for short-term photovoltaic power generation.Additionally,the knowledge inference capabilities of the LLM are employed to construct an agricultural water use knowledge graph.The rich semantic relationships within the knowledge graph assist the LLM in reasoning and prediction,generating more real-istic scenarios for agricultural power supply,irrigation,and water storage.The bi-level optimization scheduling model,based on the generated scenarios,aims to optimize the economic operation of the parks by coupling the power supply,ir-rigation,and water storage across multiple agricultural parks.Finally,simulations demonstrate that the proposed method can be adopted to significantly enhance the stability of the power system operations in agricultural parks and effectively reduce operational costs.
作者
董俊
束洪春
刘瑞
龙文桢
张广斌
DONG Jun;SHU Hongchun;LIU Rui;LONG Wenzhen;ZHANG Guangbin(Faculty of Electric Power Engineering,Kunming University of Science and Technology,Kunming 650500,China;Yunnan Key Laboratory of Green Energy and Digital Power Measurement Control and Protection,Kunming 650504,China;State Key Labora-tory of Collaborative Innovation Center for Smart Grid Fault Detection Protection and Control Jointly,Kunming University of Science and Technology,Kunming 650500,China)
出处
《高电压技术》
EI
CAS
CSCD
北大核心
2024年第7期2906-2917,I0007-I0009,共15页
High Voltage Engineering
基金
云南省重大科技专项计划项目(202302AF080006)。
关键词
农灌负荷特性
大语言模型
知识抽取
知识图谱
双层优化模型
characteristics of agricultural irrigation load
large language model
knowledge extraction
knowledge graphs
bi-level optimization model
作者简介
董俊1977-,男,博士生,副教授研究方向为配电网故障检测、保护与自愈,E-mail:dongjun_kust@sina.com;通信作者:束洪春1961-,男,博士,教授,博导从事电力系统新型继电保护与故障测距、故障录波、数字信号处理及DSP应用等方面的研究,E-mail:kmshc@sina.com.cn。
