
浏览全部资源
扫码关注微信
1.华北电力大学控制与计算机工程学院,北京市102206
2.南京南瑞信息通信科技有限公司,江苏省南京市 211106
3.国网江苏省电力有限公司,江苏省南京市 210024
4.国网江苏省电力有限公司电力科学研究院,江苏省南京市 211103
王申(1999—),男,硕士研究生,主要研究方向:人工智能在电力系统中的应用。E-mail:wangshen@ncepu.edu.cn
魏兴慎(1986—)男,硕士,高级工程师,主要研究方向:网络安全、图神经网络。E-mail:weixshen@gmail.com
朱卫平(1983—),男,博士,高级工程师,主要研究方向:配电自动化。E-mail:jszhuweipin@163.com
关志涛(1979—)男,通信作者,教授,博士生导师,主要研究方向:电力信息安全。E-mail:guan@ncepu.edu.cn
收稿:2024-05-23,
修回:2024-10-25,
纸质出版:2025-06-10
移动端阅览
王申,魏兴慎,朱卫平等.基于大语言模型的配电主站日志异常检测[J].电力系统自动化,2025,49(11):178-188.
WANG Shen,WEI Xingshen,ZHU Weiping,et al.Log Abnormity Detection for Distribution Master Station Based on Large Language Models[J].Automation of Electric Power Systems,2025,49(11):178-188.
王申,魏兴慎,朱卫平等.基于大语言模型的配电主站日志异常检测[J].电力系统自动化,2025,49(11):178-188. DOI: 10.7500/AEPS20240523001.
WANG Shen,WEI Xingshen,ZHU Weiping,et al.Log Abnormity Detection for Distribution Master Station Based on Large Language Models[J].Automation of Electric Power Systems,2025,49(11):178-188. DOI: 10.7500/AEPS20240523001.
日志异常检测是监控配电主站系统运行并识别异常行为的关键技术之一。已有的基于深度学习的日志异常检测方法依赖于大量带标注的训练数据,而在配电主站系统中缺少带标注训练数据
这会导致日志异常检测性能显著下降。文中基于大语言模型的上下文推理特性,提出了一种无须训练的配电主站日志异常检测方案LogAdapt。所设计的上下文学习示例筛选算法针对不同的在线日志,从少量带标注的本地日志中动态筛选出若干高质量的上下文学习示例;结合任务描述和人类经验知识,自动构建出文本提示,以指导大语言模型完成配电主站日志异常检测任务。实验结果表明,所提方案相比现有方案性能更优。
Log abnormity detection is a critical technology for monitoring the operation of distribution master station systems and identifying anomalous behaviors. Existing deep learning-based log abnormity detection methods rely on a large amount of labeled training data
yet the lack of annotated training data in power distribution master station systems leads to significant performance degradation in log abnormity detection. Based on the contextual reasoning performances of large language model (LLM)
this paper proposes LogAdapt—a training-free log abnormity detection scheme for distribution master stations. The proposed in-context learning (ICL) example filtering algorithm is designed to dynamically select a number of high-quality ICL examples from a small amount of locally labeled online logs tailored to different types of logs. By integrating task descriptions and human expert knowledge
it automatically constructs text prompts to guide LLM in completing the task of log abnormity detection in distribution master station. The experimental results show that the proposed scheme has better performance compared to existing schemes.
刘健 , 张志华 , 陈宜凯 , 等 . 适用于含DG配电网故障处理性能测试的主站注入测试技术 [J]. 电力系统自动化 , 2017 , 41 ( 13 ): 119 - 124 .
LIU Jian , ZHANG Zhihua , CHEN Yikai , et al . Host injection test technology for fault handling performance test of power distribution network with DG [J]. Automation of Electric Power Systems , 2017 , 41 ( 13 ): 119 - 124 .
范闻博 , 关石磊 , 符金伟 , 等 . 配电自动化潮流计算测试平台设计 [J]. 电力系统保护与控制 , 2018 , 46 ( 8 ): 117 - 123 .
FAN Wenbo , GUAN Shilei , FU Jinwei , et al . Test bench design for distribution automation power flow calculation [J]. Power System Protection and Control , 2018 , 46 ( 8 ): 117 - 123 .
王宗耀 , 苏浩益 . 配网自动化系统可靠性成本效益分析 [J]. 电力系统保护与控制 , 2014 , 42 ( 6 ): 98 - 103 .
WANG Zongyao , SU Haoyi . Cost-benefit analysis model for reliability of distribution network automation system [J]. Power System Protection and Control , 2014 , 42 ( 6 ): 98 - 103 .
周劼英 , 张晓 , 邵立嵩 , 等 . 新型电力系统网络安全防护挑战与展望 [J]. 电力系统自动化 , 2023 , 47 ( 8 ): 15 - 24 .
ZHOU Jieying , ZHANG Xiao , SHAO Lisong , et al . Challenges and prospects of cyber security protection for new power system [J]. Automation of Electric Power Systems , 2023 , 47 ( 8 ): 15 - 24 .
严康 , 陆艺丹 , 于宗超 , 等 . 配电网用户侧异构电力物联设备运行安全管控分析 [J]. 电力系统自动化 , 2023 , 47 ( 8 ): 53 - 61 .
YAN Kang , LU Yidan , YU Zongchao , et al . Analysis on operation security management and control for user-side heterogeneous power internet-of-things devices in distribution network [J]. Automation of Electric Power Systems , 2023 , 47 ( 8 ): 53 - 61 .
AHMED A , KRISHNAN V V G , FOROUTAN S A , et al . Cyber physical security analytics for anomalies in transmission protection systems [J]. IEEE Transactions on Industry Applications , 2019 , 55 ( 6 ): 6313 - 6323 .
LI X Y , CHEN P F , JING L X , et al . SwissLog: robust anomaly detection and localization for interleaved unstructured logs [J]. IEEE Transactions on Dependable and Secure Computing , 2023 , 20 ( 4 ): 2762 - 2780 .
QI J X , LUAN Z Z , HUANG S H , et al . LogEncoder: log-based contrastive representation learning for anomaly detection [J]. IEEE Transactions on Network and Service Management , 2023 , 20 ( 2 ): 1378 - 1391 .
DU M , LI F F , ZHENG G N , et al . DeepLog: anomaly detection and diagnosis from system logs through deep learning [C]// Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security , October 30-November 3 , 2017 , Dallas, USA : 1285 - 1298 .
MENG W B , LIU Y , ZHU Y C , et al . Loganomaly: unsupervised detection of sequential and quantitative anomalies in unstructured logs [C]// Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence , August 10 - 16 , Macao, China : 4739 - 4745 .
LE V H , ZHANG H Y . Log-based anomaly detection without log parsing [C]// 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE) , November 15-19 , 2021 , Melbourne, Australia : 492 - 504 .
HE S L , ZHU J M , HE P J , et al . Experience report: system log analysis for anomaly detection [C]// 2016 IEEE 27th International Symposium on Software Reliability Engineering (ISSRE) , October 23-27 , 2016 , Ottawa, Canada : 207 - 218 .
万龙 . 自动化配电主站系统设计及其在工程改造中应用 [D]. 南昌 : 南昌大学 , 2019 .
WAN Long . Design of automatic distribution master station system and its application in engineering transformation [D]. Nanchang : Nanchang University , 2019 .
闫力 , 夏伟 . 基于机器学习的日志异常检测综述 [J]. 计算机系统应用 , 2022 , 31 ( 9 ): 57 - 69 .
YAN Li , XIA Wei . Survey on log anomaly detection based on machine learning [J]. Computer Systems & Applications , 2022 , 31 ( 9 ): 57 - 69 .
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 Junhua , WEN Fushuan , HUANG Jianwei , 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 .
江秀臣 , 臧奕茗 , 刘亚东 , 等 . 电力设备ChatGPT类模式与关键技术 [J]. 高电压技术 , 2023 , 49 ( 10 ): 4033 - 4045 .
JANG Xiuchen , ZANG Yiming LIU Yadong , et al . Power equipment ChatGPT-type model and key technologies [J]. High Voltage Engineering , 2023 , 49 ( 10 ): 4033 - 4045 .
孙永辉 , 孟雲帆 , 葛磊蛟 , 等 . 人工智能赋能微电网运行优化的应用及展望 [J]. 高电压技术 , 2023 , 49 ( 6 ): 2239 - 2252 .
LIU Yonghui , MENG Yunfan , GE Leijiao , et al . Application and prospect of microgrid operation optimization enabled by artificial intelligence [J] High Voltage Engineering , 2023 , 49 ( 6 ): 2239 - 2252 .
LIU Y L , TAO S M , MENG W B , et al . LogPrompt: prompt engineering towards zero-shot and interpretable log analysis [C]// Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering , April 14-20 , 2024 , Lisbon, Portugal : 364 - 365 .
QI J X , HUANG S H , LUAN Z Z , et al . LogGPT: exploring ChatGPT for log-based anomaly detection [C]// 2023 IEEE International Conference on High Performance Computing & Communications , Data Science & Systems, Smart City & Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys), December 17-21, 2023, Melbourne, Australia : 273 - 280 .
HE P J , ZHU J M , ZHENG Z B , et al . Drain: an online log parsing approach with fixed depth tree [C]// 2017 IEEE International Conference on Web Services (ICWS) , June 25-30 , 2017 , Honolulu, USA : 33 - 40 .
ZHU J M , HE S L , LIU J Y , et al . Tools and benchmarks for automated log parsing [C]// 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice(ICSE-SEIP) , May 25-31 , 2019 , Montreal, Canada : 121 - 130 .
VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C]// Advances in neural information processing systems , December 4-9 , 2017 , Long Beach, USA .
GARG S , KAUR K , KUMAR N , et al . A hybrid deep learning-based model for anomaly detection in cloud datacenter networks [J]. IEEE Transactions on Network and Service Management , 2019 , 16 ( 3 ): 924 - 935 .
XIAO R Z , CHEN H , LU J T , et al . AllInfoLog: robust diverse anomalies detection based on all log features [J]. IEEE Transactions on Network and Service Management , 2023 , 20 ( 3 ): 2529 - 2543 .
DEVLIN J , CHANG M W , LEE K , et al . BERT: pre-training of deep bidirectional transformers for language understanding [C]// Proceedings of NAACL-HLT , June 2-7 , 2019 , Minneapolis, USA : 4171 - 4186 .
BROWN T , MANN B , RYDER N , et al . Language models are few-shot learners [C]// Advances in Neural Information Processing Systems , December 7 - 12 , 2020 : 1877 - 1901 .
LIU J C , SHEN D H , ZHANG Y Z , et al . What makes good In-context examples for GPT-3? [C]// Proceedings of Deep Learning Inside Out (DeeLIO 2022 ): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, May 27 ,2022, Dublin , Ireland: 100 - 114 .
YE J , WU Z , FENG J , et al . Compositional exemplars for in-context learning [C]// International Conference on Machine Learning . PMLR , July 23-29 , 2023 , Hawaii, USA : 39818 - 39833 .
ZHU J M , HE S L , HE P J , et al . Loghub: a large collection of system log datasets for AI-driven log analytics [C]// 2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE) , October 9-12 , 2023 , Florence, Italy : 355 - 366 .
OLINER A , STEARLEY J . What supercomputers say: a study of five system logs [C]// 37th Annual IEEE/IFIP International Conference on Dependable Systems and Networks(DSN'07 ), June 25-28 , 2007 , Edinburgh, UK : 575 - 584 .
LE V H , ZHANG H Y . Log-based anomaly detection with deep learning: how far are we? [C]// Proceedings of the 44th International Conference on Software Engineering , May 22-27 , 2022 , Pittsburgh, USA : 1356 - 1367 .
JIANG A Q , SABLAYROLLES A , MENSCH A , et al . Mistral 7 B[EB/OL]. [ 2024-05-23 ]. https://arxiv.org/abs/2310.06825 https://arxiv.org/abs/2310.06825 .
HU E J , WALLIS P , ALLEN-ZHU Z , et al . LoRA: low-rank adaptation of large language models [C]// Proceedings of the 10th International Conference on Learning Representations , April 25-29 , 2022 , Vienna, Austria .
0
浏览量
2
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621