Shanxi Key Laboratory of Advanced Control and Equipment Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China
Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo 2007, Australia
Centre for Cyber Security Research and Innovation, Deakin University, Melbourne 3125, Australia
School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China
Show Author Information
Hide Author Information
Abstract
Accurate load forecasting is critical for electricity production, transmission, and maintenance. Deep learning (DL) model has replaced other classical models as the most popular prediction models. However, the deep prediction model requires users to provide a large amount of private electricity consumption data, which has potential privacy risks. Edge nodes can federally train a global model through aggregation using federated learning (FL). As a novel distributed machine learning (ML) technique, it only exchanges model parameters without sharing raw data. However, existing forecasting methods based on FL still face challenges from data heterogeneity and privacy disclosure. Accordingly, we propose a user-level load forecasting system based on personalized federated learning (PFL) to address these issues. The obtained personalized model outperforms the global model on local data. Further, we introduce a novel differential privacy (DP) algorithm in the proposed system to provide an additional privacy guarantee. Based on the principle of generative adversarial network (GAN), the algorithm achieves the balance between privacy and prediction accuracy throughout the game. We perform simulation experiments on the real-world dataset and the experimental results show that the proposed system can comply with the requirement for accuracy and privacy in real load forecasting scenarios.
No abstract is available for this article. Click the button above to view the PDF directly.
References
[1]
S.Haben, S.Arora, G.Giasemidis, M.Voss, and D. V.Greetham, Review of low voltage load forecasting: Methods, applications, and recommendations, Applied Energy, vol. 304, p. 117798, 2021.
M.Injadat, A.Moubayed, A. B.Nassif, and A.Shami, Machine learning towards intelligent systems: Applications, challenges, and opportunities, Artificial Intelligence Review, vol. 54, no. 5, pp. 3299–3348, 2021.
M.Faheem, S. B. H.Shah, R. A.Butt, B.Raza, M.Anwar, M. W.Ashraf, M. A.Ngadi, and V. C.Gungor, Smart grid communication and information technologies in the perspective of industry 4.0: Opportunities and challenges, Computer Science Review, vol. 30, pp. 1–30, 2018.
H.Shi, M.Xu, and R.Li, Deep learning for household load forecasting—A novel pooling deep RNN, IEEE Transactions on Smart Grid, vol. 9, no. 5, pp. 5271–5280, 2017.
W.Kong, Z. Y.Dong, Y.Jia, D. J.Hill, Y.Xu, and Y.Zhang, Short-term residential load forecasting based on LSTM recurrent neural network, IEEE Transactions on Smart Grid, vol. 10, no. 1, pp. 841–851, 2017.
M.Alhussein, K.Aurangzeb, and S. I.Haider, Hybrid CNN-LSTM model for short-term individual household load forecasting, IEEE Access, vol. 8, pp. 180544–180557, 2020.
N.Balta-Ozkan, O.Amerighi, and B.Boteler, A comparison of consumer perceptions towards smart homes in the UK, Germany and Italy: Reflections for policy and future research, Technology Analysis & Strategic Management, vol. 26, no. 10, pp. 1176–1195, 2014.
A.Jindal, A.Dua, K.Kaur, M.Singh, N.Kumar, and S.Mishra, Decision tree and SVM-based data analytics for theft detection in smart grid, IEEE Transactions on Industrial Informatics, vol. 12, no. 3, pp. 1005–1016, 2016.
M. G.Chuwa and F.Wang, A review of non-technical loss attack models and detection methods in the smart grid, Electric Power Systems Research, vol. 199, p. 107415, 2021.
L.Cui, Y.Qu, L.Gao, G.Xie, and S.Yu, Detecting false data attacks using machine learning techniques in smart grid: A survey, Journal of Network and Computer Applications, vol. 170, p. 102808, 2020.
P.Kairouz, H. B.McMahan, B.Avent, A.Bellet, M.Bennis, A. N.Bhagoji, K.Bonawitz, Z.Charles, G.Cormode, R.Cummings, et al., Advances and open problems in federated learning, arXiv preprint arXiv: 1912.04977, 2019.
H.Lee, J.Kim, R.Hussain, S.Cho, and J.Son, On defensive neural networks against inference attack in federated learning, in Proc. 2021 IEEE International Conference on Communications, Montreal, Canada, 2021, pp. 1–6.
C.Li, Y.Yuan, and F. Y.Wang, Blockchain-enabled federated learning: A survey, in Proc. 2021 IEEE 1st International Conference on Digital Twins and Parallel Intelligence (DTPI), Beijing, China, 2021, pp. 286–289.
X.Yin, Y.Zhu, and J.Hu, A comprehensive survey of privacy-preserving federated learning: A taxonomy, review, and future directions, ACM Computing Surveys (CSUR), vol. 54, no. 6, pp. 1–36, 2022.
Y.Qu, S.Yu, W.Zhou, S.Chen, and J.Wu, Customizable reliable privacy-preserving data sharing in cyber-physical social networks, IEEE Transactions on Network Science and Engineering, vol. 8, no. 1, pp. 269–281, 2020.
X.Fang, S.Misra, G.Xue, and D.Yang, Smart grid—The new and improved power grid: A survey, IEEE Communications Surveys & Tutorials, vol. 14, no. 4, pp. 944–980, 2011.
K.Sahinbas and F. O.Catak, Secure multi-party computation based privacy preserving data analysis in healthcare IoT systems, arXiv preprint arXiv: 2109.14334, 2021.
L.Zhang, J.Xu, P.Vijayakumar, P. K.Sharma, and U.Ghosh, Homomorphic encryption-based privacy-preserving federated learning in IoT-enabled healthcare system, IEEE Transactions on Network Science and Engineering, .
H.Wang, Z.Kaplan, D.Niu, and B.Li, Optimizing federated learning on non-IID data with reinforcement learning, in Proc. IEEE INFOCOM 2020-IEEE Conference on Computer Communications, Toronto, Canada, 2020, pp. 1698–1707.
V.Venkataramanan, S.Kaza, and A. M.Annaswamy, DER forecast using privacy-preserving federated learning, IEEE Internet of Things Journal, vol. 10, no. 3, pp. 2046–2055, 2022.
N. B. S.Qureshi, D. H.Kim, J.Lee, and E. K.Lee, Poisoning attacks against federated learning in load forecasting of smart energy, in Proc. 2022 IEEE/IFIP Network Operations and Management Symposium, Budapest, Hungary, 2022, pp. 1–7.
M.Sun, J.Li, Y.Ren, S.Fang, and J.Yan, Research on federated learning and its security issues for load forecasting, in Proc. 2021 13th International Conference on Computer Modeling and Simulation, Melbourne, Australia, 2021, pp. 237–243.
N.Gholizadeh and P.Musilek, Federated learning with hyperparameter-based clustering for electrical load forecasting, Internet of Things, vol. 17, p. 100470, 2022.
Y.Lu, D.Chen, E.Olaniyi, and Y.Huang, Generative adversarial networks (GANs) for image augmentation in agriculture: A systematic review, Computers and Electronics in Agriculture, vol. 200, p. 107208, 2022.
T.Li, S.Hu, A.Beirami, and V.Smith, Ditto: Fair and robust federated learning through personalization, in Proc. 38th International Conference on Machine Learning, Virtual, 2021, pp. 6357–6368.
M.Pau, E.Patti, L.Barbierato, A.Estebsari, E.Pons, F.Ponci, and A.Monti, A cloud-based smart metering infrastructure for distribution grid services and automation, Sustainable Energy, Grids and Networks, vol. 15, pp. 14–25, 2018.
Qu X, Guan C, Xie G, et al. Personalized Federated Learning for Heterogeneous Residential Load Forecasting. Big Data Mining and Analytics, 2023, 6(4): 421-432. https://doi.org/10.26599/BDMA.2022.9020043
The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
10.26599/BDMA.2022.9020043.F001
AMI architecture.
10.26599/BDMA.2022.9020043.F002
GAN-DP. “A” and “R” indicate acceptance and rejection, respectively.
GAN-DP modeling for PFL
Using DP algorithm in FL is an effective way to obtain a strong privacy guarantee. However, DP’s sacrifice of accuracy hinders its entry into practical application scenarios. Here we adopt GAN-DP[
34
], a modified GAN model, in the above FL setting, which improves the load forecasting accuracy while complying with the DP requirements.
As shown in
Fig. 2
, GAN-DP contains a generator, a discriminator, and the DP identifier (DPI) whose structure is similar to the discriminator. In our system, the local parameters are obtained through local training by the client. Then, the local model parameters are fed into the generator, and the generator produces a group of synthesized parameters. The generated synthesized parameters are then treated as inputs to the discriminators and the DPI. If the synthesized parameter satisfies the requirements of the two perceptrons, the parameter is taken as the output result and goes to the next step.
Table 1
provides brief instructions for notations in this chapter.
10.26599/BDMA.2022.9020043.T001
Notations in GAN-DP.
Notation
Explanation
Training data
Number of noise samples
Distribution of generator
Data samples for training
Mathematical expectation
Prior injected noise
Multilayer perceptron of generator
Multilayer perceptron of discriminator
Multilayer perceptron of DP identifier
Combined structure of the discriminator and DP identifier
10.26599/BDMA.2022.9020043.F002
GAN-DP. “A” and “R” indicate acceptance and rejection, respectively.
Generator: Utilizing the original local model parameters, the generator produces synthesized parameters and submits them to the discriminator for identification. The noise samples from are inputted and updated by
Discriminator: After several iterations, if the discriminator identifies the synthesized parameters as the original model parameters, the final result is obtained. Here we select data samples from , and the gradient ascent of discriminator in the update process can be formulated by
DP identifier: Since the DPI serves as a discriminator, the discriminator and DPI interact with the generator in parallel. Unlike the discriminator, DPI attempts to confirm whether the synthesized model parameters satisfy the DP requirements. The update procedure can be expressed as
In GAN-DP, there is a min-max game established between the generator, discriminator, and DPI. Based on the above formulas, this problem can be modeled as
In Formula (
9
), we use to reduce the likelihood of discrimination and to increase the likelihood of deception.
The PFL for heterogeneous residential load forecasting is shown in Algorithm 1.
10.26599/BDMA.2022.9020043.F003
System architecture.
10.26599/BDMA.2022.9020043.F004
Forecasting results for electrical load using global and our proposed model.
10.26599/BDMA.2022.9020043.F005
Forecasting results for electrical load on regional consumption using global model.
10.26599/BDMA.2022.9020043.F006
Comparison of privacy protection effect.
10.26599/BDMA.2022.9020043.F007
Forecasting performance on privacy protection strategy.