大模型在电力行业的应用与挑战

doi:10.12096/j.2096-4528.pgt.25251

发电技术 ›› 2025, Vol. 46 ›› Issue (4): 637-650.DOI: 10.12096/j.2096-4528.pgt.25251

• 新型电力系统 • 下一篇

大模型在电力行业的应用与挑战

严新荣¹^,², 高翔¹, 林达², 郑建², 游源², 陶志伟², 吴昊², 丁正桃²

^1.浙江大学能源工程学院，浙江省杭州市 310007
^2.华电电力科学研究院有限公司，浙江省杭州市 310030

收稿日期:2025-06-04 修回日期:2025-07-18 出版日期:2025-08-31 发布日期:2025-08-21
作者简介:严新荣(1972)，男，硕士，正高级工程师，长期从事能源电力数字化、智能化技术研究，xinrong-yan@chder.com；
高翔(1968)，男，博士，中国工程院院士，主要研究方向为新型电力系统及人工智能技术等， xgao1@zju.edu.cn；
林达(1990)，男，硕士，高级工程师，主要研究方向为大语言模型技术、知识工程及计算机应用等，da-lin@chder.com；
郑建(1990)，男，硕士，高级工程师，主要研究方向为大语言模型技术及计算机应用等， jian-zheng@chder.com；
游源(1984)，男，博士，高级工程师，主要研究方向为大语言模型技术及计算机应用等， yuan-you@chder.com；
陶志伟(1984)，男，硕士，工程师，主要研究方向为大语言模型技术及计算机应用等， zhiwei-tao@chder.com；
吴昊(1994)，男，硕士，工程师，主要研究方向为人工智能、大语言模型及计算机应用等， hao-wu@chder.com；
丁正桃(1964)，男，博士，正高级工程师，主要研究方向为控制理论及应用、新型电力系统一体化调控及人工智能技术等， zhengtao-ding@chder.com。
基金资助:
国家重点研发计划项目(2024YFB4206500)

Application and Challenges of Large Models in Power Industry

Xinrong YAN¹^,², Xiang GAO¹, Da LIN², Jian ZHENG², Yuan YOU², Zhiwei TAO², Hao WU², Zhengtao DING²

^1.College of Energy Engineering, Zhejiang University, Hangzhou 310007, Zhejiang Province, China
^2.Huadian Electric Power Research Institute Co. , Ltd. , Hangzhou 310030, Zhejiang Province, China

Received:2025-06-04 Revised:2025-07-18 Published:2025-08-31 Online:2025-08-21
Supported by:
National Key Research and Development Program of China(2024YFB4206500)

摘要/Abstract

摘要：

目的随着可再生能源接入日益增多，新型电力系统的复杂性大大增强，电力行业需要基于更大规模的多源数据融合、更复杂的分析决策，并通过更智能化的手段提高系统的灵活性和适应性。以大语言模型为代表的大模型因其强大的自然语言处理能力及其在多种复杂任务中的推理能力而受到极大关注。基于此，从大语言模型在电力行业应用的实现技术出发，归纳总结相关成果，为后续大模型技术应用提供借鉴。方法首先，介绍了大语言模型应用落地的关键技术，包括提示词工程、检索增强生成、模型微调和智能体开发，这些技术确保大语言模型在实际应用中更准确实用，拓宽了应用场景。其次，介绍了大语言模型在电力知识服务、电力辅助决策、设备故障诊断、电力系统预测等领域应用的研究进展。最后，分析了大语言模型在电力行业应用的挑战。结论大模型在电力行业的应用主要集中在以大语言模型为基础的场景且较为成熟，而基于多模态大模型、时序大模型及大小模型协同的更复杂场景的应用仍处于探索和快速发展阶段。

关键词: 电力行业, 新型电力系统, 人工智能(AI), 大语言模型, 知识服务, 辅助决策, 故障诊断, 预测

Abstract:

Objectives With the growing integration of renewable energy, the complexity of new power system has significantly increased. The power industry requires the integration of large-scale multi-source data, more complex analysis and decision-making processes, and more intelligent approaches to enhance system flexibility and adaptability. Large models represented by large language models have attracted significant attention due to their robust natural language processing capabilities and reasoning abilities across various complex tasks. Based on this, the study reviews implementation technologies for applying large language models in the power industry and summarizes relevant achievements to inform future applications. Methods Firstly, key technologies for implementing large language models are introduced, including prompt engineering, retrieval-augmented generation, model fine-tuning, and the development of intelligent agents. These technologies enhance the accuracy and practicality of large language models in real-world applications and broaden their range of use cases. Secondly, the study outlines the research progress of large language models in areas such as power knowledge services, assisted decision-making, equipment fault diagnosis, and power system prediction. Lastly, the challenges in applying large language models in the power industry are analyzed. Conclusions The application of large models in the power industry is currently focused on the cenarios based on large language models, which are relatively mature. In contrast, applications involving multimodal models, time-series models, and large-small model collaboration remain in the exploratory and rapidly evolving stage.

Key words: power industry, new power system, artificial intelligence (AI), large language model, knowledge services, assisted decision-making, fault diagnosis, prediction

中图分类号:

TK 01

严新荣, 高翔, 林达, 郑建, 游源, 陶志伟, 吴昊, 丁正桃. 大模型在电力行业的应用与挑战[J]. 发电技术, 2025, 46(4): 637-650.

Xinrong YAN, Xiang GAO, Da LIN, Jian ZHENG, Yuan YOU, Zhiwei TAO, Hao WU, Zhengtao DING. Application and Challenges of Large Models in Power Industry[J]. Power Generation Technology, 2025, 46(4): 637-650.

图/表 8

图1 LLM应用的实现技术

Fig. 1 Implementation technologies for LLM application

图2 RAG流程基本架构

Fig. 2 Basic architecture of RAG process

图3 RAG流程改进框架

Fig. 3 Improved framework of RAG process

图4 智能体设计范式

Fig. 4 Intelligent agent design paradigm

图5 知识服务应用的技术路线

Fig. 5 Technical route for knowledge service applications

图6 辅助决策应用的技术路线

Fig. 6 Technical route for application in assisted decision-making

图7 故障诊断应用的技术路线

Fig. 7 Technical route for application in fault diagnosis

图8 电力系统预测应用的技术路线

Fig. 8 Technical route for application in power system prediction

参考文献 94

[1]	刘传洋，吴一全，刘景景．无人机航拍图像中绝缘子缺陷检测的深度学习方法研究进展[J]．电工技术学报，2025，40(9)：2897-2916．
	LIU C Y， WU Y Q， LIU J J ．Research progress of deep learning methods for insulator defect detection in UAV based aerial images[J]．Transactions of China Electrotechnical Society，2025，40(9)：2897-2916．
[2]	田华，张玮，冯斌，等．5G+智慧电厂机器人自主巡检系统设计与开发[J]．南方能源建设，2023，10(6)：34-42．
	TIAN H， ZHANG W， FENG B，et al ．Design and development of 5G+ robot autonomous patrol inspection system in intelligent power plant[J]．Southern Energy Construction，2023，10(6)：34-42．
[3]	康璐，段玖祥，张文杰，等．基于视觉激光融合的新能源发电智能巡检技术[J]．电力科技与环保，2023，39(2)：173-181．
	KANG L， DUAN J X， ZHANG W J，et al ．Research on intelligent inspection technology of new energy power generation based on vision and laser[J]．Electric Power Technology and Environmental Protection，2023，39(2)：173-181．
[4]	徐涛，李互刚，杨龙雨，等．注意力机制和多目标粒子群混合驱动的配电网无功优化[J]．电网与清洁能源，2024，40(7)：146-154．
	XU T， LI H G， YANG L Y，et al ．Hybrid-driven reactive power optimization for distribution networks driven by attentional mechanisms and multi-objective particle swarms[J]．Power System and Clean Energy，2024，40(7)：146-154．
[5]	曹祎，张莉，郭静，等．基于大语言模型的低碳电力市场发展应用前景[J]．智慧电力，2024，52(2)：8-16．
	CAO Y， ZHANG L， GUO J，et al ．Prospects for development of low-carbon electricity markets based on large language models[J]．Smart Power，2024，52(2)：8-16．
[6]	杨至元，陈晖，李沛．基于生成对抗网络和迁移学习的电力碳流耦合特征数据生成与评估[J]．电力建设，2024，45(3)：126-136．
	YANG Z Y， CHEN H， LI P ．Acquisition and evaluation of the coupled featuring data of power system and carbon emissions flows using generative adversarial networks and transfer learning method[J]．Electric Power Construction，2024，45(3)：126-136．
[7]	RADFORD A， WU J， CHILD R，et al ．Language models are unsupervised multitask learners[J]．OpenAI Blog，2019，1(8)：9．
[8]	徐浩然，张瑾昀，马歆，等．基于大语言模型的图检索增强生成技术在核电领域的应用与展望[J]．发电技术，2025，46(3)：454-466．
	XU H R， ZHANG J Y， MA X，et al ．Applications and prospects of graph retrieval-augmented generation technology based on large language models in the nuclear power field[J]．Power Generation Technology，2025，46(3)：454-466．
[9]	DUBEY A， JAUHRI A， PANDEY A，et al ．The Llama 3 herd of models[EB/OL]．(2024-11-23)[2025-05-01]．．
[10]	LIU A， FENG B， WANG B，et al ．Deepseek-v2：a strong，economical，and efficient mixture-of-experts language model[EB/OL]．(2024-06-19)[2025-05-01]．．
[11]	LIU A， FENG B， XUE B，et al ．Deepseek-v3 technical report[EB/OL]．(2025-02-18)[2025-05-01]．．
[12]	李鹏，余涛，李立浧，等．电力人工智能的演变与展望：从专业智能走向通用智能[J]．电力系统自动化，2024，48(16)：1-17．
	LI P， YU T， LI L C，et al ．Retrospect and prospect of artificial intelligence for electric power system：from domain intelligence to general intelligence[J]．Automation of Electric Power Systems，2024，48(16)：1-17．
[13]	REYNOLDS L， MCDONELL K ．Prompt programming for large language models：beyond the few-shot paradigm[C]//Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems．Yokohama Japan：ACM，2021：1-10． doi:10.1145/3411763.3451760
[14]	张祖菡，刘敦楠，凡航，等．基于大语言模型的电力系统预测技术研究综述[J]．发电技术，2025，46(3)：438-453．
	ZHANG Z H， LIU D N， FAN H，et al ．Review of power system prediction technologies based on large language models[J]．Power Generation Technology，2025，46(3)：438-453．
[15]	BSHARAT S M， MYRZAKHAN A， SHEN Z Q ．Principled instructions are all you need for questioning LLaMA-1/ 2，GPT-3.5/4[EB/OL]．(2024-01-18)[2025-05-01]．．
[16]	杨虹，孟晓凯，俞华，等．基于BERT模型的主设备缺陷诊断方法研究[J]．电力系统保护与控制，2025，53(7)：155-164．
	YANG H， MENG X K， YU H，et al ．Research on primary equipment defect diagnosis method based on the BERT model[J]．Power System Protection and Control，2025，53(7)：155-164．
[17]	WEI J， WANG X， SCHUURMANS D，et al ．Chain of thought prompting elicits reasoning in large language models[EB/OL]．(2023-01-10)[2025-05-01]．．
[18]	YAO S， YU D， ZHAO J，et al ．Tree of thoughts：deliberate problem solving with large language models[EB/OL]．(2023-12-03)[2025-05-01]．．
[19]	BESTA M， BLACH N， KUBICEK A，et al ．Graph of thoughts：solving elaborate problems with large language models[J]．Proceedings of the AAAI Conference on Artificial Intelligence，2024，38(16)：17682-17690． doi:10.1609/aaai.v38i16.29720
[20]	ZHOU Y C， MURESANU A I， HAN Z W，et al ．Large language models are human-level prompt engineers[EB/OL]．(2023-03-10)[2025-05-01]．．
[21]	BANG Y， CAHYAWIJAYA S， LEE N，et al ．A multitask，multilingual，multimodal evaluation of chatgpt on reasoning，hallucination，and interactivity[EB/OL]．(2023-11-28)[2025-05-01]．． doi:10.18653/v1/2023.ijcnlp-main.45
[22]	CHEN C， LIU K， CHEN Z，et al ．INSIDE：LLMs’ internal states retain the power of hallucination detection[EB/OL]．(2024-10-21)[2025-05-01]．．
[23]	ZHOU Y， CUI C， YOON J，et al ．Analyzing and mitigating object hallucination in large vision-language model[EB/OL]．(2024-03-16)[2025-05-01]．． doi:10.18653/v1/2023.emnlp-main.20
[24]	LIU F X， LIN K， LI L J，et al ．Mitigating hallucination in large multi-modal models via robust instruction tuning[EB/OL]．(2024-03-19)[2025-05-01]．．
[25]	LEWIS P， PEREZ E， PIKTUS A，et al ．Retrieval-augmented generation for knowledge-intensive NLP tasks[EB/OL]．(2021-04-12)[2025-05-01]．．
[26]	JIMENO YEPES A， YOU Y， MILCZEK J，et al ．Financial report chunking for effective retrieval augmented generation[EB/OL]．(2024-03-16)[2025-05-01]．．
[27]	KOO H， KIM M， HWANG S J ．Optimizing query generation for enhanced document retrieval in RAG[EB/OL]．(2024-07-17)[2025-05-01]．．
[28]	SAWARKAR K， MANGAL A， SOLANKI S R ．Blended RAG：improving RAG (retriever-augmented generation) accuracy with semantic search and hybrid query-based retrievers[C]//2024 IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR)．San Jose，CA，USA：IEEE，2024：155-161． doi:10.1109/mipr62202.2024.00031
[29]	门业堃，钱梦迪，于钊，等．基于检索重排序模型的文本差异化研究[J]．电测与仪表，2023，60(1)：57-63．
	MEN Y K， QIAN M D， YU Z，et al ．Research of text differentiation based on retrieval reordering model[J]．Electrical Measurement & Instrumentation，2023，60(1)：57-63．
[30]	MUENNIGHOFF N ．SGPT：GPT sentence embeddings for semantic search[EB/OL]．(2022-08-05)[2025-05-01].．
[31]	JIANG H， WU Q， LIN C Y，et al ．LLMLingua：compressing prompts for accelerated inference of large language models[EB/OL]．(2023-12-06)[2025-05-01]．． doi:10.18653/v1/2023.emnlp-main.825
[32]	LING C， ZHAO X， LU J，et al ．Beyond one-model-fits-all：a survey of domain specialization for large language models[EB/OL]．(2024-03-29)[2025-05-01]．．
[33]	HU E J， SHEN Y， WALLIS P，et al ．LoRA：low-rank adaptation of large language models[EB/OL]．(2021-10-16)[2025-05-01]．．
[34]	DETTMERS T， PAGNONI A， HOLTZMAN A，et al ．QLoRA：efficient finetuning of quantized LLMs[EB/OL]．(2021-10-16)[2025-05-01]．．
[35]	LIU X， ZHENG Y， DU Z，et al ．GPT understands，too[J]．AI Open，2024，5：208-215． doi:10.1016/j.aiopen.2023.08.012
[36]	LIU X， JI K， FU Y，et al ．P-tuning v2：prompt tuning can be comparable to fine-tuning universally across scales and tasks[EB/OL]．(2022-03-20)[2025-05-01]．． doi:10.18653/v1/2022.acl-short.8
[37]	SHUTTLEWORTH R， ANDREAS J， TORRALBA A，et al ．LoRA vs full fine-tuning：an illusion of equivalence[EB/OL]．(2025-06-23)[2025-07-01]．．
[38]	CHEN Y， LIEBAU U， GURUPRASAD S M，et al ．Advancing life cycle assessment of sustainable green hydrogen production using domain-specific fine-tuning by large language models augmentation[J]．Machine Learning and Knowledge Extraction，2024，6(4)：2494-2514． doi:10.3390/make6040122
[39]	ZHANG J， ZHANG C， LU J，et al ．Domain-specific large language models for fault diagnosis of heating，ventilation，and air conditioning systems by labeled-data-supervised fine-tuning[J]．Applied Energy，2025，377：124378． doi:10.1016/j.apenergy.2024.124378
[40]	韩佶，邓钰婷，耿子越，等．大规模风电场协调控制架构及算法综述[J]．电力科学与技术学报，2025，40(1)：1-18．
	HAN J， DENG Y T， GENG Z Y，et al ．Review of coordinated control architectures and algorithms for large-scale wind farms[J]．Journal of Electric Power Science and Technology，2025，40(1)：1-18．
[41]	LIU B， JIANG Y， ZHANG X，et al ．LlM+ P：empowering large language models with optimal planning proficiency[EB/OL]．(2023-09-27)[2025-07-01]．．
[42]	YAO S， ZHAO J， YU D，et al ．ReAct：synergizing reasoning and acting in language models[EB/OL]．(2023-03-09)[2025-07-01]．．
[43]	LI M， ZHAO Y， YU B，et al ．API-bank：a comprehensive benchmark for tool-augmented LLMs[EB/OL]．(2023-10-25)[2025-07-01]．． doi:10.18653/v1/2023.emnlp-main.187
[44]	FEI X， ZHENG X， FENG H ．MCP-zero：proactive toolchain construction for LLM agents from scratch[EB/OL]．(2025-06-01)[2025-07-01]．．
[45]	HOU X， ZHAO Y， WANG S，et al ．Model context protocol (MCP)：landscape，security threats，and future research directions[EB/OL]．(2025-03-30)[2025-07-01]．．
[46]	CHENG Y， ZHANG C， ZHANG Z，et al ．Exploring large language model based intelligent agents：definitions，methods，and prospects[EB/OL]．(2024-01-07)[2025-07-01]．．
[47]	廖美英，胡列豪，张勇军，等．人工智能技术在发电厂智能化建设中的应用与挑战[J]．广东电力，2024，37(11)：109-119．
	LIAO M Y， HU L H， ZHANG Y J，et al ．Applications and challenges of AI technology in power plant intelligent construction[J]．Guangdong Electric Power，2024，37(11)：109-119．
[48]	任晓龙，陈曦，司恒斌，等．基于Neo4j图数据库的电力系统与综合能源系统知识图谱研究[J]．电力科学与技术学报，2025，40(3)：211-221．
	REN X L， CHEN X， SI H B，et al ．Power system and comprehensive energy knowledge graph based on Neo4j graph database[J]．Journal of Electric Power Science and Technology，2025，40(3)：211-221．
[49]	张昆，张永伟，吴永城，等．基于大模型的设备故障知识图谱自动构建方法[J]．计算机与现代化，2024(11)：46-53．
	ZHANG K， ZHANG Y W， WU Y C，et al ．An LLM-based method for automatic construction of equipment failure knowledge graphs[J]．Computer and Modernization，2024(11)：46-53．
[50]	张金营，王哲峰，谢华，等．基于知识图谱与大语言模型的电力行业知识检索分析系统研发与应用[J]．中国电力，2024，57(12)：198-205．
	ZHANG J Y， WANG Z F， XIE H，et al ．Development and application of a knowledge retrieval and analysis system for the power industry based on knowledge graph and large language model[J]．Electric Power，2024，57(12)：198-205．
[51]	CHEN L， ZHOU Y， WEI Q，et al ．ELPGPT：large language models enhancing link prediction in electrical knowledge graph[J]．International Journal of High Speed Electronics and Systems，2025，34：2540115． doi:10.1142/s0129156425401159
[52]	李敬如，李红军，马良，等．基于人工智能的配电网规划技术研究现状与展望[J]．电力建设，2025，46(4)：1-15．
	LI J R， LI H J， MA L，et al ．Research status and prospects of distribution network planning technology based on artificial intelligence[J]．Electric Power Construction，2025，46(4)：1-15．
[53]	CHATTERJEE J， DETHLEFS N ．Automated question-answering for interactive decision support in operations & maintenance of wind turbines[J]．IEEE Access，2022，10：84710-84737． doi:10.1109/access.2022.3197167
[54]	赵松燕，曲朝阳，郭晓利，等．基于Map Reduce的输电监测数据智能检索模型[J]．电力系统保护与控制，2023，51(22)：177-187．
	ZHAO S Y， QU Z Y， GUO X L，et al ．Intelligent retrieval model of power transmission monitoring data based on Map Reduce[J]．Power System Protection and Control，2023，51(22)：177-187．
[55]	孙其航，荆晓远，舒磊．基于检索增强的故障诊断知识问答模型[J]．广东石油化工学院学报，2024，34(4)：100-103．
	SUN Q H， JING X Y， SHU L ．Retrieval augmented fault diagnosis knowledge question answering model[J]．Journal of Guangdong University of Petrochemical Technology，2024，34(4)：100-103．
[56]	闫云凤，陈汐，金浩远，等．基于计算机视觉的电力作业人员行为分析研究现状与展望[J]．高电压技术，2024，50(5)：1842-1854．
	YAN Y F， CHEN X， JIN H Y，et al ．Research status and development of computer-vision-based power workers’ behavior analysis[J]．High Voltage Engineering，2024，50(5)：1842-1854．
[57]	中国电力报．发电领域首个！中国华电重磅发布[N/OL]．(2025-05-29)[2025-07-01]．．
[58]	WALKER C， ROTHON C， ASLANSEFAT K，et al ．SafeLLM：domain-specific safety monitoring for large language models：a case study of offshore wind maintenance[EB/OL]．(2024-10-06)[2025-07-01]．． doi:10.1088/1742-6596/2875/1/012025
[59]	CHATTERJEE J， DETHLEFS N ．A dual transformer model for intelligent decision support for maintenance of wind turbines[C]//2020 International Joint Conference on Neural Networks (IJCNN)．Glasgow，UK：IEEE，2020：1-10． doi:10.1109/ijcnn48605.2020.9206839
[60]	FAN Y， SONG T， FENG C，et al ．Fine-tuning pre-trained large time series models for prediction of wind turbine SCADA data[EB/OL]．(2024-11-30)[2025-07-01]．． doi:10.1016/j.apenergy.2025.126535
[61]	WALKER C， ROTHON C， ASLANSEFAT K，et al ．Using large language models to recommend repair actions for offshore wind maintenance[J]．Journal of Physics：Conference Series，2024，2875(1)：012025． doi:10.1088/1742-6596/2875/1/012025
[62]	XIAN M， WANG T， ZHANG S，et al ．A knowledge-informed large language model framework for U.S. nuclear power plant shutdown initiating event classification for probabilistic risk assessment[EB/OL]．(2024-09-30)[2025-07-01]．. doi:10.1023/a:1010650624155
	00929． doi:10.1023/a:1010650624155
[63]	任娟，荆晓远，于军，等．基于大语言模型和提示工程的机械故障诊断问答研究[J]．信息技术与信息化，2024(9)：114-119．
	REN J， JING X Y， YU J，et al ．Research on question answering of mechanical fault diagnosis based on large language model and hint engineering[J]．Information Technology and Informatization，2024(9)：114-119．
[64]	XU T， TANG X S ．Electrical equipment fault diagnosis：a technique combining fuzzy logic and large language models[C]//2023 IEEE International Symposium on Product Compliance Engineering-Asia (ISPCE-ASIA)．Shanghai，China：IEEE，2023：1-4． doi:10.1109/ispce-asia60405.2023.10365878
[65]	ZHANG D， LI S， HONG T，et al ．Enhanced fault prediction for synchronous condensers using LLM-optimized wavelet packet transformation[J]．Electronics，2025，14(2)：308． doi:10.3390/electronics14020308
[66]	MALDONADO-CORREA J， TORRES-CABRERA J， MARTÍN-MARTÍNEZ S，et al ．Wind turbine fault detection based on the transformer model using SCADA data[J]．Engineering Failure Analysis，2024，162：108354． doi:10.1016/j.engfailanal.2024.108354
[67]	WANG J， LI M， LUO H，et al ．Power-LLaVA：large language and vision assistant for power transmission line inspection[C]//2024 IEEE International Conference on Image Processing (ICIP)．Abu Dhabi，United Arab Emirates：IEEE，2024：963-969． doi:10.1109/icip51287.2024.10648271
[68]	WANG Q， ZHANG J， DU J，et al ．A fine-tuned multimodal large model for power defect image-text question-answering[J]．Signal，Image and Video Processing，2024，18(12)：9191-9203． doi:10.1007/s11760-024-03539-w
[69]	QI B， SUN J， SUI Z，et al ．Multimodal learning using large language models to improve transient identification of nuclear power plants[J]．Progress in Nuclear Energy，2024，177：105421． doi:10.1016/j.pnucene.2024.105421
[70]	YAN Z， DU Z， XU Y，et al ．Probabilistic PV power forecasting by a multi-modal method using GPT-agent to interpret weather conditions[C]//2024 IEEE 19th Conference on Industrial Electronics and Applications (ICIEA)．Kristiansand，Norway：IEEE，2024：1-6． doi:10.1109/iciea61579.2024.10665072
[71]	TIAN F， FAN X， WANG R，et al ．A power forecasting method for ultra-short-term photovoltaic power generation using transformer model[J]．Mathematical Problems in Engineering，2022(1)：9421400． doi:10.1155/2022/9421400
[72]	QU K， SI G， SHAN Z，et al ．Short-term forecasting for multiple wind farms based on transformer model[J]．Energy Reports，2022，8：483-490． doi:10.1016/j.egyr.2022.02.184
[73]	MA D， GAO Y， DAI Q ．LFformer：an improved Transformer model for wind power prediction[J]．PLoS One，2024，19(10)：e0309676． doi:10.1371/journal.pone.0309676
[74]	WANG L， HE Y， LI L，et al ．A novel approach to ultra-short-term multi-step wind power predictions based on encoder-decoder architecture in natural language processing[J]．Journal of Cleaner Production，2022，354：131723． doi:10.1016/j.jclepro.2022.131723
[75]	JIN M， WANG S， MA L，et al ．Time-LLM：time series forecasting by reprogramming large language models[EB/OL]．(2024-01-29)[2025-07-01]．． doi:10.1007/979-8-8688-1276-7_4
[76]	GAO M， ZHOU S， GU W，et al ．LFPLM：a general and flexible load forecasting framework based on pre-trained language model[EB/OL]．(2024-09-03)[2025-07-01]．． doi:10.1016/j.apenergy.2025.125965
[77]	汤卓凡，赵希超，郑庆荣，等．一种基于时序大模型的区域空调负荷预测方法及系统：CN119129838A[P]．2024-12-13．
	TANG Z F， ZHAO X C， ZHENG Q R，et al ．A regional air conditioning load forecasting method and system based on time series large model：CN119129838A[P]．2024-12-13．
[78]	XUE H， SALIM F D ．Utilizing language models for energy load forecasting[EB/OL]．(2023-10-26)[2025-07-01]．． doi:10.1145/3600100.3623730
[79]	LIAO W， YANG Z， JIA M，et al ．Zero-shot load forecasting with large language models[EB/OL]．(2024-11-18)[2025-07-01]．．
[80]	LIAO W， WANG S， YANG D，et al ．TimeGPT in load forecasting：a large time series model perspective[J]．Applied Energy，2025，379：124973． doi:10.1016/j.apenergy.2024.124973
[81]	LIU G， BAI Y， WEN K，et al ．LfLLM：a robust large language model for short-term load forecasting in smart grids[EB/OL]．(2024-12-22)[2025-07-01]．． doi:10.2139/ssrn.5070252
[82]	L’HEUREUX A， GROLINGER K， CAPRETZ M A M ．Transformer-based model for electrical load forecasting[J]．Energies，2022，15(14)：4993． doi:10.3390/en15144993
[83]	QIU Z H， LI C J， WANG Z Y，et al ．EF-LLM：energy forecasting LLM with AI-assisted automation，enhanced sparse prediction，hallucination detection[EB/OL]．(2024-12-24)[2025-07-01]．． doi:10.2139/ssrn.5217709
[84]	RUAN J， LIANG G， ZHAO H，et al ．Applying large language models to power systems：potential security threats[J]．IEEE Transactions on Smart Grid，2024，15(3)：3333-3336． doi:10.1109/tsg.2024.3373256
[85]	付志远，陈思宇，陈骏帆，等．大语言模型安全的挑战与机遇[J]．信息安全学报，2024，9(5)：26-55．
	FU Z Y， CHEN S Y， CHEN J F，et al ．Challenges and opportunities of large language model security[J]．Journal of Cyber Security，2024，9(5)：26-55．
[86]	何克成，贾宏杰，穆云飞，等．面向交通-电力融合能源系统的建模技术研究综述[J]．全球能源互联网，2023，6(5)：473-489．
	HE K C， JIA H J， MU Y F，et al ．A review of modeling approaches for integrated transportation-power energy systems[J]．Journal of Global Energy Interconnection，2023，6(5)：473-489．
[87]	KIBRIYA H， KHAN W Z， SIDDIQA A，et al ．Privacy issues in large language models：a survey[J]．Computers and Electrical Engineering，2024，120：109698． doi:10.1016/j.compeleceng.2024.109698
[88]	XU Z， LIU F， LIU H ．Bag of tricks：benchmarking of jailbreak attacks on LLMs[EB/OL]．(2024-12-24)[2025-07-01]．．
[89]	谢萱萱，李俊娥，李福阳，等．面向新型电力系统的智能终端后门检测方法[J]．电力建设，2024，45(1)：45-55．
	XIE X X， LI J E， LI F Y，et al ．A backdoor detection method for intelligent terminal in modern power system[J]．Electric Power Construction，2024，45(1)：45-55．
[90]	YANG H， XIANG K， GE M，et al ．A comprehensive overview of backdoor attacks in large language models within communication networks[J]．IEEE Network，2024，38(6)：211-218． doi:10.1109/mnet.2024.3367788
[91]	陈羽飞，赵琦，何永君，等．人工智能在电力系统中的应用综述[J]．分布式能源，2023，8(6)：49-57．
	CHEN Y F， ZHAO Q， HE Y J，et al ．An overview of the application of artificial intelligence in power systems[J]．Distributed Energy，2023，8(6)：49-57．
[92]	MAJUMDER S， DONG L， DOUDI F，et al ．Exploring the capabilities and limitations of large language models in the electric energy sector[J]．Joule，2024，8(6)：1544-1549． doi:10.1016/j.joule.2024.05.009
[93]	赵俊华，文福拴，黄建伟，等．基于大语言模型的电力系统通用人工智能展望：理论与应用[J]．电力系统自动化，2024，48(6)：13-28．
	ZHAO J H， WEN F S， HUANG J W，et al ．Prospect of artificial general intelligence for power systems based on large language model：theory and applications[J]．Automation of Electric Power Systems，2024，48(6)：13-28．
[94]	李刚，方鸿，刘云鹏，等．新型电力系统中的大模型驱动技术：现状、机遇与挑战[J]．高电压技术，2024，50(7)：2864-2878．
	LI G， FANG H， LIU Y P，et al ．Large-model drive technology in new power system：status，challenges and prospects[J]．High Voltage Engineering，2024，50(7)：2864-2878．

大模型在电力行业的应用与挑战

Application and Challenges of Large Models in Power Industry

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

图/表 8

参考文献 94

相关文章 15

编辑推荐

Metrics

[1]	闫朝阳, 李蓝青, 徐浩嘉, 庄锁, 张振华, 戎子睿. 基于白鲨算法与改进长短期记忆网络的光伏出力预测[J]. 发电技术, 2025, 46(4): 778-787.
[2]	刘佳佳, 巨星. 弃电热储能光伏-光热复合发电系统技术经济性分析[J]. 发电技术, 2025, 46(4): 807-817.
[3]	张俊, 蒲天骄, 高文忠, 刘友波, 裴玮, 许沛东, 高天露, 白昱阳. 电力系统智能计算的关键技术及应用展望[J]. 发电技术, 2025, 46(3): 421-437.
[4]	张祖菡, 刘敦楠, 凡航, 杨柳青, 段赟杰, 李赟, 马振宇. 基于大语言模型的电力系统预测技术研究综述[J]. 发电技术, 2025, 46(3): 438-453.
[5]	徐浩然, 张瑾昀, 马歆, 雷文强, 曹杰铭. 基于大语言模型的图检索增强生成技术在核电领域的应用与展望[J]. 发电技术, 2025, 46(3): 454-466.
[6]	陈艺璇, 王嘉阳, 卓映君, 卢斯煜, 周保荣. 人工智能在电力系统运行模拟加速中的应用综述[J]. 发电技术, 2025, 46(3): 467-481.
[7]	杨博, 张子健. 基于人工智能的可再生能源电解水制氢关键技术及发展前景分析[J]. 发电技术, 2025, 46(3): 482-495.
[8]	刘宿城, 栾李, 李龙, 洪涛, 刘晓东. 基于人工智能的直流微电网大信号稳定性评估方法研究[J]. 发电技术, 2025, 46(3): 496-507.
[9]	闫正义, 赵康, 王凯. 基于强化学习的新型电力系统优化策略应用综述[J]. 发电技术, 2025, 46(3): 508-520.
[10]	席磊, 王艺晓, 熊雅慧, 董璐. 基于改进深度极限学习机的电网虚假数据注入攻击定位检测[J]. 发电技术, 2025, 46(3): 521-531.
[11]	于子涵, 王赫鸣, 王建凯, 朱胜强, 孟祥忠. 基于无人机巡检的输电线路绝缘子及其异物检测算法[J]. 发电技术, 2025, 46(3): 532-540.
[12]	郑如意, 杨博, 周率, 蒋林, 李鸿彪, 郜登科. 基于人工智能的质子交换膜燃料电池状态估计及故障诊断[J]. 发电技术, 2025, 46(3): 541-555.
[13]	张鹏新, 高明明, 解沛然, 于浩洋, 张洪福, 黄中. 基于数据驱动的循环流化床机组深度调峰NO _x 预测[J]. 发电技术, 2025, 46(3): 627-636.
[14]	张扬帆, 李奕霖, 叶林, 付雪姣, 王正宇, 王耀函. 低温天气下考虑风机运行状态聚类的短期风电功率预测方法[J]. 发电技术, 2025, 46(2): 326-335.
[15]	郑杨, 任禹丞, 王雨薇, 徐丁吉, 杨慧敏. 基于改进云模型的区域电网电能替代综合效益评价[J]. 发电技术, 2025, 46(2): 399-408.