
浏览全部资源
扫码关注微信
1.清华大学电机工程与应用电子技术系,北京市 100084
2.新型电力系统运行与控制全国重点实验室(清华大学),北京市 100084
丁俐夫(1996—),男,博士,博士后,助理研究员,主要研究方向:分布式优化、多智能体强化学习、综合能源系统优化。E-mail:dinglifu@mail.tsinghua.edu.cn
陈颖(1979—),男,通信作者,博士,研究员,博士生导师,主要研究方向:并行计算与分布式计算、电磁暂态仿真、信息物理安全、系统建模。E-mail:chen_ying@mail.tsinghua.edu.cn
肖谭南(1991—),男,博士,助理研究员,主要研究方向:电力系统稳定分析与控制、高性能计算、人工智能。E-mail:xiaotn@tsinghua.edu.cn
收稿:2023-12-17,
修回:2024-05-07,
网络出版:2024-08-15,
纸质出版:2024-10-10
移动端阅览
丁俐夫,陈颖,肖谭南等.基于大语言模型的新型电力系统生成式智能应用模式初探[J].电力系统自动化,2024,48(19):1-13.
DING Lifu,CHEN Ying,XIAO Tannan,et al.Exploration of Generative Intelligent Application Mode for New Power Systems Based on Large Language Models[J].Automation of Electric Power Systems,2024,48(19):1-13.
丁俐夫,陈颖,肖谭南等.基于大语言模型的新型电力系统生成式智能应用模式初探[J].电力系统自动化,2024,48(19):1-13. DOI: 10.7500/AEPS20231217001.
DING Lifu,CHEN Ying,XIAO Tannan,et al.Exploration of Generative Intelligent Application Mode for New Power Systems Based on Large Language Models[J].Automation of Electric Power Systems,2024,48(19):1-13. DOI: 10.7500/AEPS20231217001.
新型电力系统数字化转型需要智能化应用体系支撑。首先,文中探讨了新型电力系统智能应用构建的关键难题,提出了基于大语言模型的新型电力系统生成式智能应用模式及其逻辑框架,并探讨了此模式下实现智能应用全生命周期自动化构建的技术方案;其次,针对系统仿真需求,介绍了典型生成式智能应用案例,并说明了相关技术方案特点;最后,展望了生成式智能应用发展的趋势和研究方向,供后续研究者借鉴。
The digital transformation of new power systems needs the support of intelligent application system. Firstly
the critical challenges in the construction of intelligent application for the new power system are discussed. A generative intelligent application mode and its logical framework for new power systems based on large language models are proposed. And the technical schemes for realizing the automatic construction of intelligent application in the entire lifecycle in this mode are explored. Secondly
according to the requirements of system simulation
typical cases of generative intelligent applications are introduced
and the characteristics of the related technical schemes are explained. Finally
the development trends and research directions of generative intelligent applications are prospected
which provide reference for future researchers.
董凯 . “十四五”智能制造发展规划解读及趋势研判 [J]. 中国工业和信息化 , 2022 ( 1 ): 26 - 29 .
DONG Kai . Interpretation and trend analysis of the development plan of intelligent manufacturing in the “14th Five-Year Plan ”[J]. China Industry & Information Technology , 2022 ( 1 ): 26 - 29 .
CHOLLET F . Deep learning with Python [M]. Greenwich, UK : Manning Publications Company , 2017 .
KINGMA D P , WELLING M . An introduction to variational autoencoders [EB/OL].[ 2023-10-01 ]. https://arxiv.org/pdf/1906.02691v2 https://arxiv.org/pdf/1906.02691v2 .
OLIVER A , ODENA A , RAFFEL C , et al . Realistic evaluation of deep semi-supervised learning algorithms [C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems , December 3-8 , 2018 , Montreal, Canada : 3239 - 3250 .
SILVER D , SCHRITTWIESER J , SIMONYAN K , et al . Mastering the game of Go without human knowledge [J]. Nature , 2017 , 550 ( 7676 ): 354 - 359 .
ZHUANG F , LIU S , YANG Y , et al . Complementary transfer learning for unsupervised domain adaptation [J]. IEEE Transactions on Image Processing , 2020 , 29 : 1266 - 1278 .
SILVER D , HUANG A , MADDISON C J , et al . Mastering the game of Go with deep neural networks and tree search [J]. Nature , 2016 , 529 : 484 - 489 .
王明俊 . 我国电网调度自动化的发展:从SCADA到EMS [J]. 电网技术 , 2004 , 28 ( 4 ): 43 - 46 .
WANG Mingjun . Development of power grid dispatching automation in china:from SCADA to EMS [J]. Power System Technology , 2004 , 28 ( 4 ): 43 - 46 .
TAJER A . Load forecasting via diversified state prediction in multi-area power networks [J]. IEEE Transactions on Smart Grid , 2017 , 8 ( 6 ): 2675 - 2684 .
DING L F , LIN Z Y , SHI X S , et al . Target-value-competition-based multi-agent deep reinforcement learning algorithm for distributed nonconvex economic dispatch [J]. IEEE Transactions on Power Systems , 2023 , 38 ( 1 ): 204 - 217 .
庄颖睿 , 肖谭南 , 程林 , 等 . 基于时空图卷积网络的电力系统暂态稳定评估 [J]. 电力系统自动化 , 2022 , 46 ( 11 ): 11 - 18 .
ZHUANG Yingrui , XIAO Tannan , CHENG Lin , et al . Transient stability assessment of power system based on spatio-temporal graph convolutional network [J]. Automation of Electric Power Systems , 2022 , 46 ( 11 ): 11 - 18 .
张雷 , 李晓影 , 张沛 , 等 . 基于组合神经网络的配电网故障定位方法 [J]. 电力系统及其自动化学报 , 2023 , 35 ( 9 ): 87 - 94 .
ZHANG Lei , LI Xiaoying , ZHANG Pei , et al . Fault location method for distribution network based on combined neural network [J]. Proceedings of the CSU-EPSA , 2023 , 35 ( 9 ): 87 - 94 .
KINGMA D P , WELLING M . Auto-encoding variational Bayes [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/1312.611 4 http://arxiv.org/abs/1312.6114 .
GOODFELLOW I J , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial nets [C]// Proceedings of the 27th International Conference on Neural Information Processing Systems , December 8-13 , 2014 , Montreal, Canada : 2672 - 2680 .
ROMBACH R , BLATTMANN A , LORENZ D , et al . High-resolution image synthesis with latent diffusion models [C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , June 21-23 , 2022 , New Orleans, USA : 10674 - 10685 .
RADFORD A , NARASIMHAN K , SALIMANS T , et al . Improving language understanding by generative pre-training [EB/OL]. [ 2023-12-01 ]. https://www.mikecaptain.com/resources/pdf/GPT-1.pdf https://www.mikecaptain.com/resources/pdf/GPT-1.pdf .
BROWN T B , MANN B , RYDER N , et al . Language models are few-shot learners [C]// Proceedings of the 34th International Conference on Neural Information Processing Systems , December 6-12 , 2020 , Vancouver, Canada : 1877 - 1901 .
DEVLIN J , CHANG M W , LEE K , et al . BERT: pre-training of deep bidirectional transformers for language understanding [EB/OL]. [ 2023-12-01 ]. https://arxiv.org/pdf/1810.04805 https://arxiv.org/pdf/1810.04805 .
DAI A , LE Q . Semi-supervised sequence learning [C]// Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems , December 7-12 , 2015 , Montreal,Canada : 3079 - 3087 .
VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C]// Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems , December 4-9 , 2017 , Long Beach, USA : 2 - 12 .
GRILL J B , STRUB F , ALTCHÉ F , et al . Bootstrap your own latent a new approach to self-supervised learning [C]// Proceedings of the 34th International Conference on Neural Information Processing Systems , December 6-12 , 2020 , Vancouver, Canada : 21271 - 21284 .
FU Z H , YANG H R , SO A , et al . On the effectiveness of parameter-efficient fine-tuning [C]// Proceedings of the AAAI Conference on Artificial Intelligence 2023 , February 20-27 , 2024 , Vancouver, Canada : 12799 - 12807 .
CHRISTIANO P F , LEIKE J , BROWN T B , et al . Deep reinforcement learning from human preferences [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems , December 4-9 , 2017 , Long Beach, USA : 4302 - 4310 .
LAI Z , ZHU X , DAI J , et al . Mini-DALLE3: interactive text to image by prompting large language models [EB/OL]. [ 2023-10-01 ]. https://arxiv.org/pdf/2310.07653 https://arxiv.org/pdf/2310.07653 .
YANG Z , LI L , LIN K , et al . The dawn of LMMs: preliminary explorations with GPT-4V(ision) [EB/OL]. [ 2023-10-01 ]. https://arxiv.org/pdf/2309.17421 https://arxiv.org/pdf/2309.17421 .
PEEBLES W , XIE S . Scalable diffusion models with transformers [C]// 2023 IEEE/CVF International Conference on Computer Vision (ICCV) , October 1-6 , 2023 , Paris, France : 4172 - 4182 .
徐月梅 , 胡玲 , 赵佳艺 , 等 . 大语言模型的技术应用前景与风险挑战 [J/OL]. 计算机应用 [ 2023-12-01 ]. http://kns.cnki.net/kcms/detail /51.1307.TP.20230911.1048.006.html http://kns.cnki.net/kcms/detail/51.1307.TP.20230911.1048.006.html .
XU Yuemei , HU Ling , ZHAO Jiayi , et al . Prospects and risk challenges of the application of large language models [J/OL]. Journal of Computer Applications [ 2023-12-01 ]. http://kns.cnki.net/kcms/detail/51.1307.TP.20230911.1048.006.html http://kns.cnki.net/kcms/detail/51.1307.TP.20230911.1048.006.html .
文森 , 钱力 , 胡懋地 , 等 . 基于大语言模型的问答技术研究进展综述 [J/OL]. 数据分析与知识发现 [ 2023-12-01 ]. http://kns.cnki.net /kcms/detail/10.1478.G2.20231110.1612.002.html http://kns.cnki.net/kcms/detail/10.1478.G2.20231110.1612.002.html .
WEN Sen , QIAN Li , HU Maodi , et al . Overview of research progress on question-answering techniques based on large language models [J/OL]. Data Analysis and Knowledge Discovery [ 2023-12-01 ]. http://kns.cnki.net/kcms/detail/10.1478.G2.20231110.1612.002.html http://kns.cnki.net/kcms/detail/10.1478.G2.20231110.1612.002.html .
HUANG J , CHANG K C C . Towards reasoning in large language models: a survey [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2212.10403 http://arxiv.org/abs/2212.10403 .
ZHANG S Y , DONG L F , LI X Y , et al . Instruction tuning for large language models: a survey [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2308.10792 http://arxiv.org/abs/2308.10792 .
ZVYAGIN M , BRACE A , HIPPE K , et al . GenSLMs: genome-scale language models reveal SARS-CoV-2 evolutionary dynamics [EB/OL]. [ 2023-12-01 ]. https://www.biorxiv.org/content/10.1101/2022.10.10.511571v2 https://www.biorxiv.org/content/10.1101/2022.10.10.511571v2 .
LIN Z , AKIN H , RAO R , et al . Language models of protein sequences at the scale of evolution enable accurate structure prediction [EB/OL]. [ 2023-12-01 ]. https://www.biorxiv.org/content/10.1101/2022.07.20.500902v1 https://www.biorxiv.org/content/10.1101/2022.07.20.500902v1 .
XIONG H L , WANG S , ZHU Y T , et al . Doctor GLM: fine-tuning your Chinese doctor is not a herculean task [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2304.01097 http://arxiv.org/abs/2304.01097 .
WU S J , IRSOY O , LU S , et al . Bloomberg GPT: a large language model for finance [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2303.17564 http://arxiv.org/abs/2303.17564 .
ROMERA-PAREDES B , BAREKATAIN M , NOVIKOV A , et al . Mathematical discoveries from program search with large language models [J]. Nature , 2024 , 625 : 468 - 475 .
BOIKO D A , MACKNIGHT R , KLINE B , et al . Autonomous chemical research with large language models [J]. Nature , 2023 , 624 ( 7992 ): 570 - 578 .
YAN Z M , XU Y . Real-time optimal power flow with linguistic stipulations: integrating GPT-agent and deep reinforcement learning [J]. IEEE Transactions on Power Systems , 2024 , 39 ( 2 ): 4747 - 4750 .
于硕 , 王司宇 , 王超 , 等 . 类ChatGPT大语言模型在电力系统中的应用前景 [J]. 电气时代 , 2023 ( 10 ): 50 - 53 .
YU Shuo , WANG Siyu , WANG Chao , et al . Application prospect of ChatGPT-like large language model in power system [J]. Electric Age , 2023 ( 10 ): 50 - 53 .
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初探:理论与应用 [J]. 电力系统自动化 , 2024 , 48 ( 6 ): 13 - 28 .
ZHAO Junhua , WEN Fushuan , HUANG Jianwei , et al . Preliminary research on generalized artificial intelligence for power system based on large language modeling: theory and applications [J]. Automation of Electric Power Systems , 2024 , 48 ( 6 ): 13 - 28 .
新华网 . 北京市首批10个人工智能行业大模型应用案例发布 [EB/OL]. [ 2023-12-01 ]. http://www.xinhuanet.com/tech/20230627/9e5dcb42cdd64ebaa84bba9dad936871/c.html http://www.xinhuanet.com/tech/20230627/9e5dcb42cdd64ebaa84bba9dad936871/c.html .
Xinhua Net . The first batch of 10 AI industry large model application cases released in Beijing [EB/OL].[ 2023-12-01 ]. http://www.xinhuanet.com/tech/20230627/9e5dcb42cdd64ebaa84bba9dad936871/c.html http://www.xinhuanet.com/tech/20230627/9e5dcb42cdd64ebaa84bba9dad936871/c.html .
南方电网报 . 电力行业人工智能创新平台及自主可控电力大模型发布 [EB/OL]. [ 2023-12-01 ]. https://power.in-en.com/html/power-2436803.shtml https://power.in-en.com/html/power-2436803.shtml .
Southern Power Grid News . AI innovation platform and independent controllable power large language model released in the power industry [EB/OL]. [ 2023-12-01 ]. https://power.in-en.com/html/power-2436803.shtml https://power.in-en.com/html/power-2436803.shtml .
CIMIANO P , HAASE P , HEIZMANN J , et al . Towards portable natural language interfaces to knowledge bases—the case of the ORAKEL system [J]. Data & Knowledge Engineering , 2008 , 65 ( 2 ): 325 - 354 .
WHALEN J . Expert systems versus systems for experts: computer-aided dispatch as a support system in real-world environments [M]. New York, USA : Cambridge University Press , 1995 .
CHEN M , TWOREK J , JUN H , et al . Evaluating large language models trained on code [EB/OL].[ 2023-12-01 ]. https://arxiv.org/pdf/2107.03374 https://arxiv.org/pdf/2107.03374 .
FLORE A , CLAUSEN M , USLAR M . Migration paths for smart grids and their evaluation using a case study [J]. Frontiers in Energy Research , 2019 , 7 : 134 - 154 .
沈沉 , 陈颖 , 黄少伟 , 等 . 新型电力系统仿真应用软件设计理念与发展路径 [J]. 电力系统自动化 , 2022 , 46 ( 10 ): 75 - 86 .
SHEN Chen , CHEN Ying , HUANG Shaowei , et al . Design idea and development path of simulation application software for new power system [J]. Automation of Electric Power Systems , 2022 , 46 ( 10 ): 75 - 86 .
SONG Y K , CHEN Y , YU Z T , et al . CloudPSS: a high-performance power system simulator based on cloud computing [J]. Energy Reports , 2020 , 6 : 1611 - 1618 .
XIAO T , CHEN Y , WANG J , et al . Exploration of artificial-intelligence oriented power system dynamic simulators [J]. Journal of Modern Power Systems and Clean Energy , 2023 , 11 ( 2 ): 401 - 411 .
唐跃中 , 魏晓菁 . 国家电网公司信息化“SG186” 工程实施战略研究 [J]. 电力信息化 , 2007 , 5 ( 10 ): 18 - 22 .
TANG Yuezhong , WEI Xiaojing . Research on implementation strategy of state grid corporation’s informatization “SG186” project [J]. Electric Power Information Technology , 2007 , 5 ( 10 ): 18 - 22 .
朱介北 , 徐思旸 , 李炳森 , 等 . 基于电网专家策略模仿学习的新型电力系统实时调度 [J]. 电网技术 , 2023 , 47 ( 2 ): 517 - 530 .
ZHU Jiebei , XU Siyang , LI Bingsen , et al . Real-time security dispatch of modern power system based on grid expert strategy imitation learning [J]. Power System Technology , 2023 , 47 ( 2 ): 517 - 530 .
国家市场监督管理总局 , 国家标准化管理委员会 . 电力系统安全稳定控制策略描述规则 : GB/T 40598—2021 [S]. 北京 : 中国标准出版社 , 2021 .
State Administration for Market Regulation , Standardization Administration of the People’s Republic of China . Description rules for strategy of electric power system security and stability control : GB/T 40598—2021 [S]. Beijing : Standards Press of China , 2021 .
KADDOUR J , HARRIS J , MOZES M , et al . Challenges and applications of large language models [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2307.10169 http://arxiv.org/abs/2307.10169 .
LEWIS P , PEREZ E , PIKTUS A , et al . Retrieval-augmented generation for knowledge-intensive NLP tasks [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2005.11401 http://arxiv.org/abs/2005.11401 .
WEI J , WANG X Z , SCHUURMANS D , et al . Chain of thought prompting elicits reasoning in large language models [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2201.11903 http://arxiv.org/abs/2201.11903 .
WANG X Z , WEI J , SCHUURMANS D , et al . Self-consistency improves chain of thought reasoning in language models [EB/OL].[ 2023-12-01 ]. http://arxiv.org/abs/2203.1 1171 http://arxiv.org/abs/2203.11171 .
YAO S Y , YU D , ZHAO J , et al . Tree of thoughts: deliberate problem solving with large language models [EB/OL]. [ 2023-12-01 ]. https://arxiv.org/abs/2305.10601 https://arxiv.org/abs/2305.10601 .
LONG J Y . Large language model guided tree-of-thought [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2305.08291 http://arxiv.org/abs/2305.08291 .
BESTA M , BLACH N , KUBÍČEK A , et al . Graph of thoughts: solving elaborate problems with large language models [EB/OL]. [ 2023-12-01 ]. https://arxiv.org/abs/2308.09687 https://arxiv.org/abs/2308.09687 .
YAO S , ZHAO J , YU D , et al . React: synergizing reasoning and acting in language models [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2210.03629 http://arxiv.org/abs/2210.03629 .
CHEN S Y , HOU Y T , CUI Y M , et al . Recall and learn: fine-tuning deep pretrained language models with less forgetting [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2004.12651 http://arxiv.org/abs/2004.12651 .
PFEIFFER J , VULIĆ I , GUREVYCH I , et al . MAD-X: an adapter-based framework for multi-task cross-lingual transfer [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2005.00052 http://arxiv.org/abs/2005.00052 .
HE J X , ZHOU C T , MA X Z , et al . Towards a unified view of parameter-efficient transfer learning [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2110.04366 http://arxiv.org/abs/2110.04366 .
LIU X , JI K X , FU Y C , et al . P-tuning: prompt tuning can be comparable to fine-tuning across scales and tasks [C]// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics , June 8-13 , 2022 , Dublin, Ireland : 61 - 68 .
HU E J , SHEN Y L , WALLIS P , et al . LoRA: low-rank adaptation of large language models [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2106.09685 http://arxiv.org/abs/2106.09685 .
CUI R K , HE S Y , QIU S . Adaptive low rank adaptation of segment anything to salient object detection [EB/OL]. [ 2023-12-01 ]. http://arxiv.org/abs/2308.05426 http://arxiv.org/abs/2308.05426 .
陈颖 , 高仕林 , 宋炎侃 , 等 . 面向新型电力系统的高性能电磁暂态云仿真技术 [J]. 中国电机工程学报 , 2022 , 42 ( 8 ): 2854 - 2864 .
CHEN Ying , GAO Shilin , SONG Yankan , et al . High-performance electromagnetic transient simulation for new-type power system based on cloud computing [J]. Proceedings of the CSEE , 2022 , 42 ( 8 ): 2854 - 2864 .
AHMAD A , WASEEM M , LIANG P , et al . Towards human-bot collaborative software architecting with ChatGPT [C]// Proceedings of the 27th International Conference on Evaluation and Assessment in Software Engineering , June 14-16 , 2023 , Oulu, Finland : 279 - 285 .
沈沉 , 贾孟硕 , 陈颖 , 等 . 能源互联网数字孪生及其应用 [J]. 全球能源互联网 , 2020 , 3 ( 1 ): 1 - 13 .
SHEN Chen , JIA Mengshuo , CHEN Ying , et al . Digital twin of the energy Internet and its application [J]. Journal of Global Energy Interconnection , 2020 , 3 ( 1 ): 1 - 13 .
XIAO T . Llm4power [EB/OL]. [ 2023-12-01 ]. https://github.com/xxh0523/llm4power https://github.com/xxh0523/llm4power .
0
浏览量
0
下载量
3
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621