Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
A Secure Federated Deep Learning-Based Approach for Heating Load Demand Forecasting in Building Environment
Recently, with the establishment of new thermal regulation, the energy efficiency of buildings has increased significantly, and various deep learning-based methods have been presented to accurately forecast the heating load demand of buildings. However, all of these methods are executed on a dataset with specific distribution and do not have the property of global forecasting, and have no guarantee of data privacy against cyber-attacks. This paper presents a novel approach to heating load demand forecasting based on Cyber-Secure Federated Deep Learning (CSFDL). The suggested CSFDL provides a global super-model for forecasting heating load demand of different local clients without knowing their location and, most importantly, without revealing their privacy. In this study, a CSFDL global server is trained and tested considering the heating load demand of 10 different clients in their building environment. The presented results, including a comparative study, prove the viability and accuracy of the proposed procedure.
A Secure Federated Deep Learning-Based Approach for Heating Load Demand Forecasting in Building Environment
Recently, with the establishment of new thermal regulation, the energy efficiency of buildings has increased significantly, and various deep learning-based methods have been presented to accurately forecast the heating load demand of buildings. However, all of these methods are executed on a dataset with specific distribution and do not have the property of global forecasting, and have no guarantee of data privacy against cyber-attacks. This paper presents a novel approach to heating load demand forecasting based on Cyber-Secure Federated Deep Learning (CSFDL). The suggested CSFDL provides a global super-model for forecasting heating load demand of different local clients without knowing their location and, most importantly, without revealing their privacy. In this study, a CSFDL global server is trained and tested considering the heating load demand of 10 different clients in their building environment. The presented results, including a comparative study, prove the viability and accuracy of the proposed procedure.
A Secure Federated Deep Learning-Based Approach for Heating Load Demand Forecasting in Building Environment
Moradzadeh, Arash (Autor:in) / Moayyed, Hamed (Autor:in) / Mohammadi-Ivatloo, Behnam (Autor:in) / Aguiar, A Pedro (Autor:in) / Anvari-Moghaddam, Amjad (Autor:in)
01.01.2022
Moradzadeh , A , Moayyed , H , Mohammadi-Ivatloo , B , Aguiar , A P & Anvari-Moghaddam , A 2022 , ' A Secure Federated Deep Learning-Based Approach for Heating Load Demand Forecasting in Building Environment ' , IEEE Access , vol. 10 , pp. 5037-5050 . https://doi.org/10.1109/ACCESS.2021.3139529
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
/dk/atira/pure/sustainabledevelopmentgoals/affordable_and_clean_energy , Heating load , Load forecasting , Building , Cyber-secure Federated Learning , Deep Learning , name=SDG 17 - Partnerships for the Goals , /dk/atira/pure/sustainabledevelopmentgoals/partnerships , Forecasting , Heating systems , Predictive models , Buildings , name=SDG 7 - Affordable and Clean Energy , Energy Management , Load modeling
DDC:
690
Predicting Building Energy Demand Using Federated Learning with Attribute-Based Clustering
| Springer Verlag | 2024
Federated Learning-Based Multi-Energy Load Forecasting Method Using CNN-Attention-LSTM Model
| DOAJ | 2022