
浏览全部资源
扫码关注微信
1.西安交通大学电气工程学院,陕西省西安市 710049
2.国网江西省电力有限公司,江西省南昌市 330077
3.华北电力大学控制与计算机工程学院,北京市 102206
陈明亮(1989—),男,博士研究生,主要研究方向:电力系统自动化。E-mail:chenml@jx.sgcc.com.cn
卢志学(1979—),男,高级工程师,主要研究方向:电力系统自动化。E-mail:gz_luzx@jxsgcc.com.cn
谢国强(1984—),男,硕士,高级工程师,主要研究方向:电力系统自动化。E-mail:dky_xiegq@jx.sgcc.com.cn
李元诚(1970—),男,通信作者,博士,教授,主要研究方向:电力信息安全。E-mail:ncepua@163.com
收稿:2024-04-02,
修回:2024-06-21,
网络出版:2024-10-17,
纸质出版:2024-11-25
移动端阅览
陈明亮,卢志学,谢国强等.基于半监督联邦学习的分布式电源调控安全威胁协同检测[J].电力系统自动化,2024,48(22):199-209.
CHEN Mingliang,LU Zhixue,XIE Guoqiang,et al.Collaborative Detection for Security Threats to Distributed Generator Regulation Based on Semi-supervised Federated Learning[J].Automation of Electric Power Systems,2024,48(22):199-209.
陈明亮,卢志学,谢国强等.基于半监督联邦学习的分布式电源调控安全威胁协同检测[J].电力系统自动化,2024,48(22):199-209. DOI: 10.7500/AEPS20240402009.
CHEN Mingliang,LU Zhixue,XIE Guoqiang,et al.Collaborative Detection for Security Threats to Distributed Generator Regulation Based on Semi-supervised Federated Learning[J].Automation of Electric Power Systems,2024,48(22):199-209. DOI: 10.7500/AEPS20240402009.
针对现有分布式电源调控系统安全威胁检测存在的检测精度不高、通信效率低等突出问题,以及由于数据手工标注的高成本、低效率等客观原因和模型自动伪标注不可信导致的数据利用不充分问题,提出了一种基于半监督联邦学习(SSFL)的安全威胁分布式协同检测方法,在云端和边缘设备之间进行协同训练,并通过未标记数据进行模型自我学习和优化,从而更好适应分布式电源调控系统的安全威胁环境。首先,采用改进Transformer模型有效捕获安全威胁。其次,考虑到分布式电源调控系统的数据具有跨设备、跨区域的特点,引入联邦学习确保本地数据隐私安全。然后,针对未标记数据问题,通过云边协同训练获得全局模型并进行伪标记,设计一致性正则化与信息熵正则的损失函数以保证伪标记的可信度。最后,设计动态加权聚合方法优化参数更新和模型训练。在密西西比大学电力系统数据集上进行仿真实验,实验结果表明,与FedAvg-FixMatch方法和FedMatch方法相比,检测准确率分别提升了8%和4%,且类别召回率和精确率均有提高,显著减少了18%~28%的通信开销,表明了所提方法在分布式电源调控系统安全威胁检测中的有效性和实用性。
A collaborative detection method for regulation security threats to distributed generator based on semi-supervised federated learning is proposed to address the prominent issues of low detection accuracy and low communication efficiency in existing distributed generator regulation systems
as well as the objective reasons for the high cost and low efficiency of manual data annotation and insufficient data utilization caused by untrustworthy model automatic pseudo annotation. The method involves collaborative training between cloud and edge devices
and self-learning and optimization of the model are realized through unlabeled data to better adapt to the security threat environment of distributed generator regulation systems. Firstly
an improved Transformer model is used to effectively capture security threats. Secondly
considering the cross-device and cross-regional characteristics of data in distributed generator regulation systems
federated learning is introduced to ensure the privacy and security of local data. To address the issue of unlabeled data
a global model is obtained through cloud-edge collaborative training for pseudo labeling
and a loss function for consistency regularization and information entropy regularization is designed to ensure the credibility of pseudo labeling. Finally
a dynamic weighted aggregation method is designed to optimize parameter updates and model training. Simulation experiments are conducted on the power system dataset at the University of Mississippi
and the experimental results show that compared with FedAvg-FixMatch and FedMatch methods
the proposed method improved the detection accuracy by 8% and 4%
respectively
and both category recall and accuracy are improved
significantly reducing communication overhead by 18%~28%. This demonstrates the effectiveness and practicality of the proposed method in security threat detection in distributed generator regulation systems.
LIU X L , LIU Y B , LIU J Y , et al . Optimal planning of AC-DC hybrid transmission and distributed energy resource system: review and prospects [J]. CSEE Journal of Power and Energy Systems , 2019 , 5 ( 3 ): 409 - 422 .
盛万兴 , 吴鸣 , 季宇 , 等 . 分布式可再生能源发电集群并网消纳 关键技术及工程实践 [J]. 中国电机工程学报 , 2019 , 39 ( 8 ): 2175 - 2186 .
SHENG Wanxing , WU Ming , JI Yu , et al . Key techniques and engineering practice of distributed renewable generation clusters integration [J]. Proceedings of the CSEE , 2019 , 39 ( 8 ): 2175 - 2186 .
吴文传 , 张伯明 , 孙宏斌 , 等 . 主动配电网能量管理与分布式资源集群控制 [J]. 电力系统自动化 , 2020 , 44 ( 9 ): 111 - 118 .
WU Wenchuan , ZHANG Boming , SUN Hongbin , et al . Energy management and distributed energy resources cluster control for active distribution networks [J]. Automation of Electric Power Systems , 2020 , 44 ( 9 ): 111 - 118 .
路小俊 , 吴在军 , 李培帅 , 等 . 面向光伏集群的配电网模型-数据联合驱动无功/电压控制 [J]. 电力系统自动化 , 2024 , 48 ( 9 ): 97 - 106 .
LU Xiaojun , WU Zaijun , LI Peishuai , et al . Combined model- and data-driven volt/var control for distribution network with photovoltaic clusters [J]. Automation of Electric Power Systems , 2024 , 48 ( 9 ): 97 - 106 .
薛峰 , 常康 , 汪宁渤 . 大规模间歇式能源发电并网集群协调控制框架 [J]. 电力系统自动化 , 2011 , 35 ( 22 ): 45 - 53 .
XUE Feng , CHANG Kang , WANG Ningbo . Coordinated control frame of large-scale intermittent power plant cluster [J]. Automation of Electric Power Systems , 2011 , 35 ( 22 ): 45 - 53 .
顾晨骁 , 顾伟 , 陈超 , 等 . 分布式电源集群控制与电力信息实时仿真研究 [J]. 电力系统保护与控制 , 2020 , 48 ( 4 ): 64 - 71 .
GU Chenxiao , GU Wei , CHEN Chao , et al . Distributed power cluster control and research on power information real-time simulation [J]. Power System Protection and Control , 2020 , 48 ( 4 ): 64 - 71 .
万庆祝 , 薛潺 . 区域微电网集群技术研究新进展 [J]. 电气工程学报 , 2017 , 12 ( 3 ): 53 - 59 .
WAN Qingzhu , XUE Chan . The new progress on technology of regional micro-grids cluster [J]. Journal of Electrical Engineering , 2017 , 12 ( 3 ): 53 - 59 .
徐式蕴 , 王一鸣 , 孙华东 , 等 . 国外新能源脱网事故对中国电网安全稳定运行的启示 [J/OL]. 电力系统自动化 [ 2024-01-01 ]. https://kns-cnki-net.webvpn.ncepu.edu.cn/kcms/detail/32.1180.tp.20240428.2323.004.html https://kns-cnki-net.webvpn.ncepu.edu.cn/kcms/detail/32.1180.tp.20240428.2323.004.html .
XU Shiyun , WANG Yiming , SUN Huadong , et al . Inspiration of foreign new energy disconnection accidents on the safe and stable operation of China’s power grid [J/OL]. Power System Automation [ 2024-01-01 ]. https://kns-cnki-net.webvpn.ncepu.edu.cn/kcms/detail/32.1180.tp.20240428.2323.004.html https://kns-cnki-net.webvpn.ncepu.edu.cn/kcms/detail/32.1180.tp.20240428.2323.004.html .
杨挺 , 许哲铭 , 赵英杰 , 等 . 数字化新型电力系统攻击与防御方法研究综述 [J]. 电力系统自动化 , 2024 , 48 ( 6 ): 112 - 126 .
YANG Ting , XU Zheming , ZHAO Yingjie , et al . Review on research of attack and defense methods for digitalized new power system [J]. Automation of Electric Power Systems , 2024 , 48 ( 6 ): 112 - 126 .
李鹏 , 刘念 , 胡秦然 , 等 . “新型电力系统数字化关键技术综述” 专辑评述 [J]. 电力系统自动化 , 2024 , 48 ( 6 ): 1 - 12 .
LI Peng , LIU Nian , HU Qinran , et al . Commentary on special issue of reviews on key technologies for digitalization of new power system [J]. Automation of Electric Power Systems , 2024 , 48 ( 6 ): 1 - 12 .
朱彦名 , 徐潇源 , 严正 , 等 . 面向电力物联网的含可再生能源配电网运行展望 [J]. 电力系统保护与控制 , 2022 , 50 ( 2 ): 176 - 187 .
ZHU Yanming , XU Xiaoyuan , YAN Zheng , et al . Prospect of renewable energy integrated distribution network operation in the power Internet of Things [J]. Power System Protection and Control , 2022 , 50 ( 2 ): 176 - 187 .
杨义 , 杨苹 , 李壮壮 , 等 . 基于信息物理融合的微能源网统一调控架构及优化运行 [J]. 电力系统自动化 , 2023 , 47 ( 4 ): 34 - 41 .
YANG Yi , YANG Ping , LI Zhuangzhuang , et al . Architecture and optimal operation of unified dispatch and control of micro-energy grid based on cyber-physical fusion [J]. Automation of Electric Power Systems , 2023 , 47 ( 4 ): 34 - 41 .
LIU M X , TENG F , ZHANG Z Y , et al . Enhancing cyber-resiliency of DER-based SmartGrid: a survey [EB/OL]. [ 2024-01-01 ]. https://arxiv.org/abs/2305.05338v3 https://arxiv.org/abs/2305.05338v3 .
KONEČNÝ J , MCMAHAN H B , YU F X , et al . Federated learning: strategies for improving communication efficiency [EB/OL]. [ 2024-01-01 ]. https://arxiv.org/abs/1610.05492v2 https://arxiv.org/abs/1610.05492v2 .
LIU Y , GARG S , NIE J T , et al . Deep anomaly detection for time-series data in industrial IoT: a communication-efficient on-device federated learning approach [J]. IEEE Internet of Things Journal , 2021 , 8 ( 8 ): 6348 - 6358 .
MOTHUKURI V , KHARE P , PARIZI R M , et al . Federated-learning-based anomaly detection for IoT security attacks [J]. IEEE Internet of Things Journal , 2022 , 9 ( 4 ): 2545 - 2554 .
ITAHARA S , NISHIO T , KODA Y , et al . Distillation-based semi-supervised federated learning for communication-efficient collaborative training with non-IID private data [J]. IEEE Transactions on Mobile Computing , 2023 , 22 ( 1 ): 191 - 205 .
JEONG W , YOON J , YANG E , et al . Federated semi-supervised learning with inter-client consistency & disjoint learning [J/OL]. [ 2024-01-01 ]. https://doi.org/10.48550/arXiv.2006.12097 https://doi.org/10.48550/arXiv.2006.12097 .
何奉禄 , 陈佳琦 , 李钦豪 , 等 . 智能电网中的物联网技术应用与发展 [J]. 电力系统保护与控制 , 2020 , 48 ( 3 ): 58 - 69 .
HE Fenglu , CHEN Jiaqi , LI Qinhao , et al . Application and development of Internet of Things in smart grid [J]. Power System Protection and Control , 2020 , 48 ( 3 ): 58 - 69 .
孙浩洋 , 张冀川 , 王鹏 , 等 . 面向配电物联网的边缘计算技术 [J]. 电网技术 , 2019 , 43 ( 12 ): 4314 - 4321 .
SUN Haoyang , ZHANG Jichuan , WANG Peng , et al . Edge computation technology based on distribution Internet of Things [J]. Power System Technology , 2019 , 43 ( 12 ): 4314 - 4321 .
白昱阳 , 黄彦浩 , 陈思远 , 等 . 云边智能:电力系统运行控制的边缘计算方法及其应用现状与展望 [J]. 自动化学报 , 2020 , 46 ( 3 ): 397 - 410 .
BAI Yuyang , HUANG Yanhao , CHEN Siyuan , et al . Cloud-edge intelligence: status quo and future prospective of edge computing approaches and applications in power system operation and control [J]. Acta Automatica Sinica , 2020 , 46 ( 3 ): 397 - 410 .
梁志峰 , 叶畅 , 刘子文 , 等 . 分布式电源集群并网调控:体系架构与关键技术 [J]. 电网技术 , 2021 , 45 ( 10 ): 3791 - 3802 .
LIANG Zhifeng , YE Chang , LIU Ziwen , et al . Grid-connected scheduling and control of distributed generations clusters: architecture and key technologies [J]. Power System Technology , 2021 , 45 ( 10 ): 3791 - 3802 .
赵俊华 , 文福拴 , 薛禹胜 , 等 . 电力CPS的架构及其实现技术与挑战 [J]. 电力系统自动化 , 2010 , 34 ( 16 ): 1 - 7 .
ZHAO Junhua , WEN Fushuan , XUE Yusheng , et al . Cyber physical power systems: architecture, implementation techniques and challenges [J]. Automation of Electric Power Systems , 2010 , 34 ( 16 ): 1 - 7 .
刘东 , 盛万兴 , 王云 , 等 . 电网信息物理系统的关键技术及其进展 [J]. 中国电机工程学报 , 2015 , 35 ( 14 ): 3522 - 3531 .
LIU Dong , SHENG Wanxing , WANG Yun , et al . Key technologies and trends of cyber physical system for power grid [J]. Proceedings of the CSEE , 2015 , 35 ( 14 ): 3522 - 3531 .
郭庆来 , 辛蜀骏 , 孙宏斌 , 等 . 电力系统信息物理融合建模与综合安全评估:驱动力与研究构想 [J]. 中国电机工程学报 , 2016 , 36 ( 6 ): 1481 - 1489 .
GUO Qinglai , XIN Shujun , SUN Hongbin , et al . Power system cyber-physical modelling and security assessment: motivation and ideas [J]. Proceedings of the CSEE , 2016 , 36 ( 6 ): 1481 - 1489 .
WANG Q , TAI W , TANG Y , et al . Review of the false data injection attack against the cyber-physical power system [J]. IET Cyber-Physical Systems: Theory & Applications , 2019 , 4 ( 2 ): 101 - 107 .
SOHN K , BERTHELOT D , LI C L , et al . FixMatch: simplifying semi-supervised learning with consistency and confidence [EB/OL].[ 2024-01-01 ]. https://arxiv.org/abs/2001.07685v2 https://arxiv.org/abs/2001.07685v2 .
0
浏览量
0
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