Significance Against the background of new power system development, massive amounts of multi-source heterogeneous data are distributed across multiple data owners. However, concerns regarding data ownership and privacy protection often lead to the formation of "data silos" among these owners. Meanwhile, electric power data, as critical information closely related to national security and economic development, has become a key production factor supporting the development of new power systems. As a distributed machine learning paradigm, federated learning enables multiple data owners to perform collaborative model training and data sharing while preserving data privacy, ensuring data security, and complying with regulatory requirements. Therefore, federated learning is of great significance for artificial intelligence modeling and data value mining in various application scenarios of new power systems. Progress In this context, this study conducted a systematic review of the recent applications of federated learning in new power systems, as well as the existing challenges and future research directions. First, the basic concepts, classifications, and application scenarios of federated learning were briefly introduced. According to the distribution of feature and sample spaces among different participants, federated learning can generally be categorized into horizontal federated learning, vertical federated learning, and federated transfer learning. Horizontal federated learning is applicable to scenarios in which participants share the same feature space but have different sample spaces. Vertical federated learning is suitable for scenarios in which participants share the same sample space but have different feature spaces. Federated transfer learning is applicable to scenarios with limited overlap in both the feature and sample spaces among participants. Subsequently, to address the secure data-sharing challenges faced by data owners in new power systems, the current applications of federated learning in various business scenarios were reviewed in detail. Specifically, the main application scenarios of horizontal federated learning include renewable energy generation and load forecasting, electricity consumption behavior analysis, power system cybersecurity, power network dispatch and optimization, and power network security and stability assessment. The primary application scenarios of vertical federated learning include the operation and control of distribution networks and microgrids, as well as vehicle-to-grid interaction and electric vehicles. Federated transfer learning has been mainly applied to load forecasting, power equipment fault diagnosis, regulation capability assessment of buildings, and power safety equipment inspection. At present, federated learning has been applied across nearly all fundamental components of new power systems. The review further indicates that, with increasing diversity of stakeholders in new power systems, selecting an appropriate federated learning framework requires comprehensive consideration of data characteristics, computational resources, privacy protection requirements, and application-specific demands. Consequently, customized federated learning solutions should be developed for different application scenarios. Furthermore, considering the characteristics of new power systems, including stringent real-time requirements, high standards for data privacy and security, and increasing demands for personalized services for business models, this study analyzed the major challenges facing federated learning applications. From the perspective of communication, practical large-scale deployment is hindered by heterogeneous computing resources, large model sizes, and numerous participating clients, resulting in reduced communication efficiency. From the perspective of privacy and security, although various encryption techniques have been adopted to protect data privacy, federated learning remains vulnerable to information leakage and malicious attacks, which affect its credibility and reliability. From the perspective of model training, the non-independent and identically distributed nature of data across participants, together with the emphasis of conventional federated learning on learning a single global model, often leads to poor training performance, limited model generalization, and difficulty in satisfying the personalized requirements of individual participants. Conclusions and Prospects Finally, in view of the challenges facing federated learning, this study outlined three promising future research directions: hierarchical federated learning based on model compression and asynchronous update mechanisms, federated learning integrating blockchain and personalized differential privacy, and personalized federated learning based on client selection. These directions provide valuable references for data value mining in new power systems under the goals of "dual carbon". Although federated learning has great potential to promote the digital transformation of new power systems, its practical implementation and large-scale deployment still require effective solutions to challenges such as ensuring the stability of power communication networks, establishing a universal federated learning platform for power systems, and developing technical standards and specifications for federated learning in order to achieve its widespread application.
ChenSheng, WeiZhinong, GuWei,et al.Carbon neutral oriented transition and revolution of energy systems:Multi-energy flow coordination technology[J].Electric Power Automation Equipment,2021,41(9):3-12.
QiuWeiqiang, WangMaochun, LinZhenzhi,et al.Comprehensive evaluation of shared energy storage towards new energy accommodation scenario under targets of carbon emission peak and carbon neutrality[J].Electric Power Automation Equipment,2021,41(10):244-255. doi:10.16081/j.epae.202110017
HanFujia, WangXiaohui, QiaoJi,et al.Review on artificial intelligence based load forecasting research for the new-type power system[J].Proceedings of the CSEE,2023,43(22):8569-8592.
LiHongyu, DongXiaochong, WangXinying,et al.Framework for renewable energy scenario generation considering data privacy-preservation[J].Power System Technology,2023,47(9):3690-3697.
ChatterjeeP, DasD, RawatD B.Federated learning empowered recommendation model for financial consumer services[J].IEEE Transactions on Consumer Electronics,2024,70(1):2508-2516. doi:10.1109/tce.2023.3339702
[12]
WangBo, LiHongtao, WangJie,et al.Federated learning scheme for privacy-preserving of medical data[J].Journal of Xidian University(Natural Science),2023,50(5):166-177. doi:10.19665/j.issn1001-2400.20230202
DuHaizhou, NiChengdong, ChengChaoqian,et al.FedSwarm:An adaptive federated learning framework for scalable AIoT[J].IEEE Internet of Things Journal,2024,11(5):8268-8287. doi:10.1109/jiot.2023.3321325
FanHang, XuWei, FanXiaoyu,et al.Application analysis and prospect of privacy-preserving computation in new power system[J].Automation of Electric Power Systems,2023,47(19):187-199.
GuptaH, AgarwalP, GuptaK,et al.FedGrid:A secure framework with federated learning for energy optimization in the smart grid[J].Energies,2023,16(24):8097. doi:10.3390/en16248097
[24]
ShiBujin, ZhouXinbo, LiPeilin,et al.An IHPO-WNN-based federated learning system for area-wide power load forecasting considering data security protection[J].Energies,2023,16(19):6921. doi:10.3390/en16196921
[25]
MaoZhengxiong, LiHui, HuangZuyuan,et al.Communication-efficient federated learning for power load forecasting in electric IoTs[J].IEEE Access,2023,11:47930-47939. doi:10.1109/access.2023.3262171
WangYi, GaoNing, HugG.Personalized federated learning for individual consumer load forecasting[J].CSEE Journal of Power and Energy Systems,2023,9(1):326-330.
[28]
ParkK J, SonS Y.Residential load forecasting using modified federated learning algorithm[J].IEEE Access,2023,11:40675-40691. doi:10.1109/access.2023.3268530
[29]
WangBeibei, ZhuJing, WangJiale,et al.Federated-learning based industry load forecasting framework under privacy protection of meter data[J].Automation of Electric Power Systems,2023,47(13):86-93.
JiaoRunhai, ChuJiajie, LiJunliang,et al.Personalized federated multi-region load forecasting method based on data decomposition[J].Proceedings of the CSEE,2025,45(5):1691-1704.
WenMi, XieRong, LuKejie,et al.FedDetect:A novel privacy-preserving federated learning framework for energy theft detection in smart grid[J].IEEE Internet of Things Journal,2022,9(8):6069-6080. doi:10.1109/jiot.2021.3110784
[37]
AshrafM M, WaqasM, AbbasG,et al.FedDP:A privacy-protecting theft detection scheme in smart grids using federated learning[J].Energies,2022,15(17):6241. doi:10.3390/en15176241
[38]
BadrM, IbrahemM, KholidyH,et al.Review of the data-driven methods for electricity fraud detection in smart metering systems[J].Energies,2023,16(6):2852. doi:10.3390/en16062852
ZhaoLiang, LiJiaming, LiQi,et al.A federated learning framework for detecting false data injection attacks in solar farms[J].IEEE Transactions on Power Electronics,2022,37(3):2496-2501. doi:10.1109/tpel.2021.3114671
[41]
LiYang, WeiXinhao, LiYuanzheng,et al.Detection of false data injection attacks in smart grid:A secure federated deep learning approach[J].IEEE Transactions on Smart Grid,2022,13(6):4862-4872. doi:10.1109/tsg.2022.3204796
[42]
TaheriS, DavoodiM, AliM.Mitigating cyber anomalies in virtual power plants using artificial-neural-network-based secondary control with a federated learning-trust adaptation[J].Energies,2024,17(3):619. doi:10.3390/en17030619
[43]
LiYang, LiJiazheng, WangYi.Privacy-preserving spatiotemporal scenario generation of renewable energies:A federated deep generative learning approach[J].IEEE Transactions on Industrial Informatics,2022,18(4):2310-2320. doi:10.1109/tii.2021.3098259
[44]
PuTianjiao, DuShuai, LiYe,et al.Collaborative optimization strategy of distributed generators based on federated reinforcement learning for privacy preservation[J].Automation of Electric Power Systems,2023,47(8):62-70.
RenChao, WangTianjing, YuHan,et al.EFedDSA:An efficient differential privacy-based horizontal federated learning approach for smart grid dynamic security assessment[J].IEEE Journal on Emerging and Selected Topics in Circuits and Systems,2023,13(3):817-828. doi:10.1109/jetcas.2023.3293253
[47]
RenChao, YanRudai, XuMinrui,et al.QFDSA:A quantum-secured federated learning system for smart grid dynamic security assessment[J].IEEE Internet of Things Journal,2024,11(5):8414-8426. doi:10.1109/jiot.2023.3321793
[48]
RenChao, YuHan, YanRudai,et al.SecFedSA:A secure differential-privacy-based federated learning approach for smart cyber-physical grid stability assessment[J].IEEE Internet of Things Journal,2024,11(4):5578-5588. doi:10.1109/jiot.2023.3308170
[49]
PoudyalA, TamrakarU, TrevizanR D,et al.Multiarea inertia estimation using convolutional neural networks and federated learning[J].IEEE Systems Journal,2022,16(4):6401-6412. doi:10.1109/jsyst.2021.3134599
[50]
ChuYunfei, WeiZhinong, FangXicheng,et al.A multiagent federated reinforcement learning approach for plug-in electric vehicle fleet charging coordination in a residential community[J].IEEE Access,2022,10:98535-98548. doi:10.1109/access.2022.3206020
[51]
LiYuanzheng, HeShangyang, LiYang,et al.Federated multiagent deep reinforcement learning approach via physics-informed reward for multimicrogrid energy management[J].IEEE Transactions on Neural Networks and Learning Systems,2024,35(5):5902-5914. doi:10.1109/tnnls.2022.3232630
[52]
GuoFanghong, LiuShishuo, WuXiang,et al.Federated learning based fault diagnosis of power transformer with unbalanced sample data[J].Automation of Electric Power Systems,2023,47(10):145-152.
JenkelL, JonasS, MeyerA.Privacy-preserving fleet-wide learning of wind turbine conditions with federated learning[J].Energies,2023,16(17):6377. doi:10.3390/en16176377
[55]
GuoGuanghua, QiXinhong, WangRuiqi,et al.Integrated demand response mechanism for integrated energy system based on federated learning[J].Electric Power Automation Equipment,2023,43(8):33-39.
LiuHaotian, WuWenchuan.Federated reinforcement learning for decentralized voltage control in distribution networks[J].IEEE Transactions on Smart Grid,2022,13(5):3840-3843. doi:10.1109/tsg.2022.3169361
[58]
ZhouYibin, XiaoHao, PeiWei,et al.Collaborative optimization operation and strategy evolution of microgrid cluster based on vertical federated learning[J].Automation of Electric Power Systems,2023,47(11):121-132. doi:10.7500/AEPS20220704006
MukherjeeS, HossainR R, MohiuddinS M,et al.Resilient control of networked microgrids using vertical federated reinforcement learning:Designs and real-time test-bed validations[J].IEEE Transactions on Smart Grid,2025,16(2):1897-1910. doi:10.1109/tsg.2024.3466768
[61]
WangYi, GuoQinglai, YuYang.Cooperative pricing for vehicle-traffic-power nexus to support city decarbonization:A federated deep reinforcement learning framework[J].IEEE Transactions on Industrial Cyber-Physical Systems,2023,1:182-191. doi:10.1109/ticps.2023.3317012
[62]
TeimooriZ, YassineA, HossainM S.A secure cloudlet-based charging station recommendation for electric vehicles empowered by federated learning[J].IEEE Transactions on Industrial Informatics,2022,18(9):6464-6473. doi:10.1109/tii.2022.3148997
[63]
ChenMinghao, SunYi, HuYajie,et al.The collaborative training and management-optimized method for residential integrated energy system based on vertical federated reinforcement learning[J].Proceedings of the CSEE,2022,42(15):5535-5549.
KesiciM, PalB, YangGuangya.Detection of false data injection attacks in distribution networks:A vertical federated learning approach[J].IEEE Transactions on Smart Grid,2024,15(6):5952-5964. doi:10.1109/tsg.2024.3399396
[66]
ZhengKaihong, XiaoYong, WangXin,et al.A federated learning framework for power grid metering system[J].Proceedings of the CSEE,2020,40(Supp1):122-133.
AliM, SinghA K, KumarA,et al.Comparative analysis of data-driven algorithms for building energy planning via federated learning[J].Energies,2023,16(18):6517. doi:10.3390/en16186517
[69]
WangJian, WeiBaoquan, ZengJianjun,et al.Research on load forecasting of novel power system based on efficient federated transfer learning[J].Energies,2023,16(16):6070. doi:10.3390/en16166070
WangYanxin, YanJing, YangZhou,et al.A novel federated transfer learning framework for intelligent diagnosis of insulation defects in gas-insulated switchgear[J].IEEE Transactions on Instrumentation and Measurement,2022,71:3517711. doi:10.1109/tim.2022.3190529
[72]
YangWanqian, YuGang.Federated multi-model transfer learning-based fault diagnosis with peer-to-peer network for wind turbine cluster[J].Machines,2022,10(11):972. doi:10.3390/machines10110972
[73]
HanTengfei, YueShang, YangPu,et al.Source-free dynamic weighted federated transfer learning for state-of-health estimation of lithium-ion batteries with data privacy[J].IEEE Transactions on Power Electronics,2024,39(11):15085-15100. doi:10.1109/tpel.2024.3434751
[74]
WangZhenyi, YuPeipei, ZhangHongcai.Privacy-preserving regulation capacity evaluation for HVAC systems in heterogeneous buildings based on federated learning and transfer learning[J].IEEE Transactions on Smart Grid,2023,14(5):3535-3549. doi:10.1109/tsg.2022.3231592
[75]
WangYimeng, DingXiang, YangShusen,et al.FtlSPG:A federated transfer learning framework for personalized safety protective gear detection in electric power industry[J].IEEE Internet of Things Journal,2024,11(4):5887-5898. doi:10.1109/jiot.2023.3308117
[76]
SuZhou, WangYuntao, LuanT H,et al.Secure and efficient federated learning for smart grid with edge-cloud collaboration[J].IEEE Transactions on Industrial Informatics,2022,18(2):1333-1344. doi:10.1109/tii.2021.3095506
[77]
GeLina, WangMingyu, TianLei.Review of research on efficiency of federated learning[J].Journal of Computer Applications,2025,45(8):2387-2398.
ZhangXueqing, LiuYanwei, LiuJinxia,et al.An overview of federated learning in edge intelligence[J].Journal of Computer Research and Development,2023,60(6):1276-1295.
GaoYing, ChenXiaofeng, ZhangYiyu,et al.A survey of attack and defense techniques for federated learning systems[J].Chinese Journal of Computers,2023,46(9):1781-1805. doi:10.11897/SP.J.1016.2023.01781
ChenXuebin, RenZhiqiang, ZhangHongyang.Review on security threats and defense measures in federated learning[J].Journal of Computer Applications,2024,44(6):1663-1672.
YangZhikai, LiuYaping, ZhangShuo,et al.Review of communication optimization methods in federated learning[J].Chinese Journal of Network and Information Security,2024,10(6):1-23.
WuJie, QianXuezhong, SongWei.Personalized federated learning based on similarity clustering and regularization[J].Journal of Computer Applications,2024,44(11):3345-3353.
SunYanhua, ShiYahui, LiMeng,et al.Personalized federated learning method based on collation game and knowledge distillation[J].Journal of Electronics & Information Technology,2023,45(10):3702-3709.
ChenJinyin, LiRongchang, HuangGuohan,et al.Survey on vertical federated learning:Algorithm,privacy and security[J].Chinese Journal of Network and Information Security,2023,9(2):1-20. doi:10.11959/j.issn.2096-109x.2023017
ZhaoLuocheng, QuZhihao, XieZaipeng.Study on communication optimization of federated learning in multi-layer wireless edge environment[J].Computer Science,2022,49(3):39-45. doi:10.11896/jsjkx.210800054
HanYiliang, SongChaoyue, WuXuguang,et al.Review of integrated technology of blockchain and privacy computing[J].Science Technology and Engineering,2024,24(28):11945-11963.
WuWentai, WuYingliang, LinWeiwei,et al.Horizontal federated learning:Research status,system applications and open challenges[J].Chinese Journal of Computers,2025,48(1):35-67.
GaoYujia, WangPengfei, LiuLiang,et al.Personalized federated learning method based on attention-enhanced meta-learning network[J].Journal of Computer Research and Development,2024,61(1):196-208.