基于个性化联邦学习的配电网电力负荷预测方案
作者:
作者单位:

1.广东电网电力调度控制中心;2.中山供电局电力调度控制中心;3.重庆大学大数据与软件学院

中图分类号:

TP311


Privacy-protecting Personalized Federated Learning Load Forecasting Scheme
Author:
Affiliation:

1.Guangdong Power Grid Corp Ltd,Power Dispatching and Control Center,Guangzhou;2.Zhongshan Power Supply Bureau of Guangdong Power Grid Co.;3.School of Big Data Software Engineering,Chongqing University,Chongqing,,China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [18]
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    针对配电网电力负荷预测场景下的数据隐私保护,提出一个基于联邦学习的用户级负荷预测方案,应用于配电网负荷预测场景中的数据隐私保护。在方案中多个家庭智能电表共同参与模型训练过程,同时每个家庭智能电表会训练自己的个性化模型,用于本地个性化预测。此外,方案将自适应梯度裁剪加噪算法结合到个性化联邦学习中,增强了方案的隐私保护能力,同时也可以尽量减少对预测精度的影响。通过实验分析,说明了方案可以保护电力负荷数据隐私的同时,又能够提供精准的配电网电力负荷预测,从而有助于配电网的稳定运行和优化管理。

    Abstract:

    Addressing data privacy protection in the context of power load forecasting for distribution networks, a user-level load forecasting scheme based on federated learning is proposed, specifically tailored for data privacy safeguarding in user-level load forecasting scenarios. In this approach, multiple smart meters from different households collaboratively participate in the model training process, with each meter training its own personalized model for local, tailored predictions. Furthermore, the scheme integrates an adaptive gradient clipping and noise addition algorithm into personalized federated learning, bolstering the privacy protection capabilities of the solution while minimizing the impact on forecasting accuracy. Experimental analysis demonstrates that this scheme not only safeguards the privacy of power load data but also provides precise power load forecasting for distribution networks, thereby contributing to the stable operation and optimal management of the distribution grid.

    参考文献
    [1] 陈树勇, 宋书芳, 李兰欣, 等.智能电网技术综述[J].电网技术,2009, 33 (8): 1-7.Chen S Y, Song S F, LI L X, et al. Survey on Smart Grid Technology[J]. Power System Technology, 2009, 33 (8): 1-7.
    [2] 朱俊丞, 杨之乐, 郭媛君, 等. 深度学习在电力负荷预测中的应用综述[J].郑州大学学报:工学版,2019,40(05):13-22.Zhu J C, Yang Z L, Guo Y J, et al. Application of deep learning in power load forecasting[J]. Journal of Zhengzhou University (Engineering Science), 2019,40(05):13-22.
    [3] 张建寰, 吉莹, 陈立东. 深度学习在电力负荷预测中的应用[J].自动化仪表,2019, 40 (8): 6.Zhang J H,JI Y,Chen L D. Application of Deep Learning in Power Load Forecasting[J]. Process Automation Instrumentation, 2019, 40 (8): 6.
    [4] Li K, Yang Y, Wang S, et al.A lightweight privacy-preserving and sharing scheme with dual-blockchain for intelligent pricing system of smart grid[J].Computers Security,2021, 103: 102189.
    [5] Park K, Lee J, Das A K, et al.BPPS: Blockchain-enabled privacy-preserving scheme for demand-response management in smart grid environments[J]. IEEE Transactions on Dependable Secure Computing,2022, 20 (2): 1719-1729.
    [6] Syed D, Refaat S S, Bouhali O.Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic Encryption[J].Information,2020, 11 (7).
    [7] Xu W, Sun J, Cardell-Oliver R, et al.A privacy-preserving framework using homomorphic encryption for smart metering systems[J].Sensors,2023, 23 (10): 4746.
    [8] Soykan E U, Bilgin Z, Ersoy M A, et al. Differentially private deep learning for load forecasting on smart grid[C].2019 IEEE Globecom Workshops (GC Wkshps),2019: 1-6.
    [9] Wu L, Fu S, Luo Y, et al.SecTCN: Privacy-Preserving Short-Term Residential Electrical Load Forecasting[J]. IEEE Transactions on Industrial Informatics,2023.
    [10] Gao J, Wang W, Liu Z, et al. Decentralized federated learning framework for the neighborhood: a case study on residential building load forecasting[C].Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems,2021: 453-459.
    [11] Zhang G, Zhu S, Bai X J S.Federated learning-based multi-energy load forecasting method using CNN-Attention-LSTM model[J].Sustainability,2022, 14 (19): 12843.
    [12] Wang R, Yun H, Rayhana R, et al. An adaptive federated learning system for community building energy load forecasting and anomaly prediction[J]. Energy Buildings, 2023, 295: 113215.
    [13] Qureshi N B S, Kim D-H, Lee J, et al. On the performance impact of poisoning attacks on load forecasting in federated learning[C].Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers,2021: 64-66.
    [14] Moradzadeh A, Moayyed H, Mohammadi-Ivatloo B, et al.A secure federated deep learning-based approach for heating load demand forecasting in building environment[J].IEEE Access,2021, 10: 5037-5050.
    [15] Li T, Hu S, Beirami A, et al. Ditto: Fair and robust federated learning through personalization[C].International conference on machine learning,2021: 6357-6368.
    [16] Mcmahan B, Moore E, Ramage D, et al. Communication-efficient learning of deep networks from decentralized data[C].Artificial intelligence and statistics,2017: 1273-1282.
    [17] Makonin S J D I B.HUE: The hourly usage of energy dataset for buildings in British Columbia[J].Data in brief,2019, 23.
    [18] Wei K, Li J, Ding M, et al.Federated learning with differential privacy: Algorithms and performance analysis[J]. IEEE transactions on information forensics security,2020, 15: 3454-3469.
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-04-30
  • 最后修改日期:2024-09-04
  • 录用日期:2024-09-04
文章二维码