Record link: 
http://hdl.handle.net/20.500.12708/209778
-
Title: 
Energy Efficiency Optimization and Preventive Maintenance of HVAC Systems Using Machine Learning
en
Citation: 
Bratukhin, A., Stippel, C., Sengl, D., Kobelrausch, M. D., & Sauter, T. (2024). Energy Efficiency Optimization and Preventive Maintenance of HVAC Systems Using Machine Learning. In IEEE Xplore (Ed.), 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA). https://doi.org/10.1109/ETFA61755.2024.10710735
-
Publisher DOI: 
10.1109/ETFA61755.2024.10710735
-
Publication Type: 
Inproceedings - Full-Paper Contribution
en
Language: 
English
-
Authors: 
Bratukhin, Aleksey 
Stippel, Christian 
Sengl, David 
Kobelrausch, Markus D. 
Sauter, Thilo 
-
Organisational Unit: 
E384-02 - Forschungsbereich Systems on Chip 
E384-01 - Forschungsbereich Software-intensive Systems 
E193-01 - Forschungsbereich Computer Vision 
-
Published in: 
2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA) 
-
ISBN: 
979-8-3503-6123-0
-
DOI of the book: 
10.1109/ETFA61755.2024
-
Date (published): 
16-Oct-2024
-
Event name: 
2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA) 
en
Event date: 
10-Sep-2024 - 13-Sep-2024
-
Event place: 
Padova, Italy
-
Number of Pages: 
4
-
Peer reviewed: 
Yes
-
Keywords: 
energy consumption; energy modelling; HVAC; machine learning
en
Abstract: 
HVAC systems are characterized by rigid and complex internal behaviour that limits the options for efficiency optimization. KI4HVACs project aims to apply machine learning to improve office building HVAC operation and maintenance efficiency. Reinforcement learning is used for energy use optimization and supervised learning for preventive maintenance. The models are wrapped into an MPC based and a decision tree algorithm for preventive maintenance. The system uses the TRNSYS18 simulation environment that matches an actual office building with multiple zones.
en
Project title: 
Energieeffizienzoptimierung von HLK-Systemen durch prädiktiver Algorithmen und Modellbildung mittels maschinellem Lernen: 888448 (FFG - Österr. Forschungsförderungs- gesellschaft mbH) 
-
Research Areas: 
Energy Active Buildings, Settlements and Spatial Infrastructures: 50%
Computer Science Foundations: 25%
Modeling and Simulation: 25%
-
Science Branch: 
2020 - Elektrotechnik, Elektronik, Informationstechnik: 100%
-
Appears in Collections:
Conference Paper

Show full item record

Page view(s)

571
checked on Jan 27, 2025

Google ScholarTM

Check