A Short term Electricity Load Forecasting for Community Residents Based on Federated Learning and Considering Privacy Protection

Bo Peng; Jing Zuo; Xianfu Gong; Yaodong Li; Weijie Wu; Yixin Li

doi:10.4108/ew.6007

Authors

Bo Peng Guangdong Power Grid Co.
Jing Zuo Guangdong Power Grid Co.
Xianfu Gong Guangdong Power Grid Co.
Yaodong Li Guangdong Power Grid Co.
Weijie Wu Guangdong Power Grid Co.
Yixin Li Guangdong Power Grid Co.

DOI:

https://doi.org/10.4108/ew.6007

Keywords:

Neural Network, Privacy, Federated Learning, Aggregation, Short-term Load Forecasting

Abstract

INTRODUCTION: As the penetration rate of renewable energy increases and patterns of energy demand evolve, fluctuations on both the supply and demand sides of electricity are becoming more pronounced. Consequently, accurate forecasting of community residential electrical loads has become crucial.

OBJECTIVES: Although the widespread adoption of smart meters among residents provides abundant data for model training, strict challenges arise during the training process due to the need for privacy protection and data security.

METHODS: This paper proposes a privacy-preserving community residential short-term electric load forecasting method based on federated learning. Initially, the method applies shared random masking encryption to the sensitive data of community residents, ensuring data privacy while maintaining consistency with the original data after preprocessing. Subsequently, a private data aggregation scheme is established to perform dynamic clustering of the community’s electrical load.

RESULTS: The clustered model then serves as the basis for establishing individual load forecasting models for each category of community residents to predict short-term electrical loads. Finally, an empirical analysis is performed using the electrical load data from 120 households across 6 communities in a city in Southern China.

CONCLUSION: The analysis demonstrates that the proposed method can achieve the prediction of community residential electrical loads without sharing residents’ data, thus verifying the effectiveness of this approach.

Downloads

Download data is not yet available.

References

[1] ZHAO Hanting, ZHANG Yao, HUO Wei, et al. Collaborative Forecasting Method for Short-term Wind Power Based on Vertical Federated Learning. Automation of Electric Power Systems. 2023, 47(16): 44-53.

[2] ZHENG Jie, NIU Zhewen, HAN Xiaojie, et al. Facing Data Privacy Protection in Distributed Short-Term Wind Power Forecasting for Multiple Wind Farms. Journal of Taiyuan University of Technology.2024, 55(01): 102-110.

[3] GAO Yi, ZHOU Yu, ZHANG Anlong, et al. The PV output and load power prediction based on personalized federated learning under the photovoltaic system in the whole county. Power System Technology. 2023, 47(11): 4629-4638.

[4] ZHU Congyang, ZHANG Ge, JIA Yujing, et al. Based on the Long Short-Term Memory Network Model, Federated Learning for Residential Load Forecasting. Modern Electric Power. 2023.

[5] HUA Yuanpeng, WANG Yuanyuan, HAN Ding, et al. Mid-and Long-term Charging Load Forecasting for Electric Vehicles in Residential Areas Considering Orderly Charging. Proceedings of the CSU-EPSA. 2022, 34(6): 142-150.

[6] DONG Tao, YONG Jing, ZHAO Jin, et al. The comprehensive management system of power load for residential areas with PV, energy storage, and EVs. Journal of Chongqing University. 2021, 44(08): 45-58.

[7] LIU Xiaofeng, GAO Bingtuan, LUO Jing, et al. A model of residential load stratification scheduling based on non-cooperative game theory. Automation of Electric Power Systems. 2017, 41(14): 54-60.

[8] KONG Xiangyu, MA Yuying, AI Qian, et al. Review on Electricity Consumption Characteristic Modeling and Load Forecasting for Diverse Users in New Power System. Automation of Electric Power Systems. 2023, 47(13): 2-17.

[9] LU Jixiang, ZHANG Qipei, YANG Zhihong, et al. Short-term load forecasting method based on CNN-LSTM hybrid neural network model. Power System Automation 2019, 43(08): 131-137.

[10] WANG Dewen, SUN Zhiwei. Power user-side big data analysis and parallel load forecasting. Proceedings of the Chinese Society for Electrical Engineering. 2015, 35(03): 527-537.

[11] SUN Qingkai, WANG Xiaojun, ZHANG Yizhi, et al. Based on LSTM and multi-task learning, multi-dimensional load forecasting for integrated energy systems. Power System Automation 2021, 45(05): 63-70.

[12] GE Xiaolin, SHI Liang, LIU Ya, et al. Consideration of demand response uncertainty for EVs load Sigmoid cloud model prediction. Transactions of China Electrotechnical Society. 2020, 40(21): 6913-6925.

[13] LIU Xin, LIU Donglan, FU Ting, et al. An algorithm for time series prediction based on federated learning. Journal of Shandong University. 2023.

[14] CAO Zhaojing. The research on source-load probability prediction and its application in the new energy power system driven by data-model fusion. Zhejiang University.2022.

[15] WANG Teng, HUO Zheng, HUANG Yaxin, et al. Review on privacy-preserving technologies in federated learning. Journal of Computer Applications. 2023, 43(2): 437-449.

[16] Zhang L, Wen J, Li Y, et al. A review of machine learning in building load prediction. Applied Energy. 2021, 285: 116452.

[17] Mothukuri V, Parizi R M, Pouriyeh S, et al. A survey on security and privacy of federated learning. Future Generation Computer Systems. 2021, 115: 619-640.

[18] LIU Xiaoqian, XU Fei, MA Zhuo, et al. Research on Privacy Protection Technology in Federated Learning. Journal of Information Securyity Research. 2024, 10(03): 194-201.

[19] Li L, Fan Y, Tse M, et al. A review of applications in federated learning. Computers & Industrial Engineering. 2020, 149: 106854.

[20] Wang Z, Wang Y, Zeng R, et al. Random Forest based hourly building energy prediction. Energy and Buildings. 2018, 171: 11-25.

[21] ZHU Youcheng, WANG Jinrong, XU Jian. Medium and Long Term Wind Power Generation Forecasting Method Based on Deep Learning. Guangdong Electric Power. 2021, 34(6): 72-78.

[22] YU Dengwu, LIU Min, PU Fannuo,et al. Power Load Interval Prediction Method Based on Deep Learning Quantile Regression. Guangdong Electric Power. 2022, 35(09): 1-8.

[23] Somu N, M R G R, Ramamritham K. A hybrid model for building energy consumption forecasting using long short term memory networks[J]. Applied Energy. 2020, 261: 114131.

[24] Li A, Xiao F, Zhang C, et al. Attention-based interpretable neural network for building cooling load prediction. Applied Energy. 2021, 299: 117238.

[25] Kim T, Cho S. Predicting residential energy consumption using CNN-LSTM neural networks. Energy. 2019, 182: 72-81.

[26] Le T, Vo M T, Vo B, et al. Improving Electric Energy Consumption Prediction Using CNN and Bi-LSTM. 2019: 9.

[27] QIN Feixiang, ZHU Gelan. Falut Loacation MEthod for Distribution Network Based on LSTM-CNN Machine Learning. Guangdong Electric Power. 2021, 34(11): 27-34.

[28] WANG Beibei, ZHU Jing, WANG Jiale, et al. Federated-learning Based Industry Load Forecasting Framework Under Privacy Protection of Meter Data. Automation of Electric Power Systems. 2023, 47(13): 86-93.

[29] CHEN Haoyu, LI Yidong, ZHANG Honglei et al. A research review on fairness in federated learning. Acta Electronica Sinica. 2023, 51(10): 2985-3010.

[30] WANG Jianzong, KONG Lingwei, HUANG Zhangcheng, et al. Research review of federated learning algorithms. Big Data Research. 2020, 6(6): 64-82.

[31] C Jiayi, S Chenyu, Z Xintong, et al. Local Protection of Power Data Prediction Model Based on Federated Learning and Homomorphic Encryption. Journal of Information Securyity Research. 2023, 9(3): 228-234.

[32] Eibl G, Engel D. Differential privacy for real smart metering data. Computer Science - Research and Development. 2017, 32(1): 173-182.

[33] CHEN Zhenyu, LIU Jinbo, LI Chen, et al. Based on the combination model of LSTM and XGBoost for ultra-short-term electricity load forecasting. Power System Technology 2020, 44(02): 614-620.

[34] Feature Engineering for Machine Learning. Beijing: Posts and Telecommunications Press, 2019: 156.