Generalized global solar radiation forecasting model via cyber-secure deep federated learning

被引:2
|
作者
Moradzadeh, Arash [1 ]
Moayyed, Hamed [2 ]
Mohammadi-Ivatloo, Behnam [1 ,3 ]
Aguiar, Antonio Pedro [4 ]
Anvari-Moghaddam, Amjad [5 ]
Abdul-Malek, Zulkurnain [6 ]
机构
[1] Univ Tabriz, Fac Elect & Comp Engn, Tabriz 5166616471, Iran
[2] Polytech Porto, Res Grp Intelligent Engn & Comp Adv Innovat & Dev, GECAD, LASI Intelligent Syst Associate Lab, P-4200072 Porto, Portugal
[3] LUT Univ, Sch Energy Syst, Lappeenranta, Finland
[4] Univ Porto, Fac Engn, SYSTEC ARISE Res Ctr Syst & Technol, Elect & Comp Engn Dept, P-4200465 Porto, Portugal
[5] Aalborg Univ, Dept Energy AAU Energy, DK-9220 Aalborg, Denmark
[6] Univ Teknol Malaysia, Inst High Voltage & High Current, Fac Elect Engn, Johor Baharu, Malaysia
关键词
Renewable energy resources; Solar energy; Solar radiation forecasting; Cyber-security; Federated learning; Deep learning; Machine learning; NEURAL-NETWORK; IDENTIFICATION; MANAGEMENT; FRAMEWORK;
D O I
10.1007/s11356-023-30224-1
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Recently, the increasing prevalence of solar energy in power and energy systems around the world has dramatically increased the importance of accurately predicting solar irradiance. However, the lack of access to data in many regions and the privacy concerns that can arise when collecting and transmitting data from distributed points to a central server pose challenges to current predictive techniques. This study proposes a global solar radiation forecasting approach based on federated learning (FL) and convolutional neural network (CNN). In addition to maintaining input data privacy, the proposed procedure can also be used as a global supermodel. In this paper, data related to eight regions of Iran with different climatic features are considered as CNN input for network training in each client. To test the effectiveness of the global supermodel, data related to three new regions of Iran named Abadeh, Jarqavieh, and Arak are used. It can be seen that the global forecasting supermodel was able to forecast solar radiation for Abadeh, Jarqavieh, and Arak regions with 95%, 92%, and 90% accuracy coefficients, respectively. Finally, in a comparative scenario, various conventional machine learning and deep learning models are employed to forecast solar radiation in each of the study regions. The results of the above approaches are compared and evaluated with the results of the proposed FL-based method. The results show that, since no training data were available from regions of Abadeh, Jarqavieh, and Arak, the conventional methods were not able to forecast solar radiation in these regions. This evaluation confirms the high ability of the presented FL approach to make acceptable predictions while preserving privacy and eliminating model reliance on training data.
引用
收藏
页码:18281 / 18295
页数:15
相关论文
共 50 条
  • [1] Generalized global solar radiation forecasting model via cyber-secure deep federated learning
    Arash Moradzadeh
    Hamed Moayyed
    Behnam Mohammadi-Ivatloo
    António Pedro Aguiar
    Amjad Anvari-Moghaddam
    Zulkurnain Abdul-Malek
    Environmental Science and Pollution Research, 2024, 31 : 18281 - 18295
  • [2] A Cyber-Secure generalized supermodel for wind power forecasting based on deep federated learning and image processing
    Moayyed, Hamed
    Moradzadeh, Arash
    Mohammadi-Ivatloo, Behnam
    Aguiar, A. Pedro
    Ghorbani, Reza
    ENERGY CONVERSION AND MANAGEMENT, 2022, 267
  • [3] A novel cyber-Resilient solar power forecasting model based on secure federated deep learning and data visualization
    Moradzadeh, Arash
    Moayyed, Hamed
    Mohammadi-Ivatloo, Behnam
    Vale, Zita
    Ramos, Carlos
    Ghorbani, Reza
    RENEWABLE ENERGY, 2023, 211 : 697 - 705
  • [4] A Global Cyber-Resilient Model for Dynamic Line Rating Forecasting Based on Deep Federated Learning
    Moayyed, Hamed
    Moradzadeh, Arash
    Mansour-Saatloo, Amin
    Mohammadi-Ivatloo, Behnam
    Abapour, Mehdi
    Vale, Zita
    IEEE SYSTEMS JOURNAL, 2023, 17 (04): : 6390 - 6400
  • [5] Deep Federated Learning Enhanced Secure POI Microservices for Cyber-Physical Systems
    Guo, Zhiwei
    Yu, Keping
    Lv, Zhihan
    Choo, Kim-Kwang Raymond
    Shi, Peng
    Rodrigues, Joel J. P. C.
    IEEE WIRELESS COMMUNICATIONS, 2022, 29 (02) : 22 - 29
  • [6] Estimation of daily global solar radiation using deep learning model
    Kaba, Kazim
    Sarigul, Mehmet
    Avci, Mutlu
    Kandirmaz, H. Mustafa
    ENERGY, 2018, 162 : 126 - 135
  • [7] Probabilistic Solar Irradiation Forecasting Based on Variational Bayesian Inference With Secure Federated Learning
    Zhang, Xiaoning
    Fang, Fang
    Wang, Jiaqi
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 17 (11) : 7849 - 7859
  • [8] A Deep Learning Model for Secure Cyber-Physical Transportation Systems
    Chen, Yuanfang
    Chen, Falin
    Wu, Ting
    Hu, Weitong
    Xu, Xiaohua
    IEEE INFOCOM 2018 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (INFOCOM WKSHPS), 2018,
  • [9] Multi-step ahead forecasting of global solar radiation for arid zones using deep learning
    Chandola, Deeksha
    Gupta, Harsh
    Tikkiwal, Vinay Anand
    Bohra, Manoj Kumar
    INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND DATA SCIENCE, 2020, 167 : 626 - 635
  • [10] A Lightweight and Secure Deep Learning Model for Privacy-Preserving Federated Learning in Intelligent Enterprises
    Fotohi, Reza
    Shams Aliee, Fereidoon
    Farahani, Bahar
    IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (19): : 31988 - 31998