Controlling HVAC and lighting systems: Difference between revisions
initial text in HVAC control section
(created page) |
Jan.drgona (talk | contribs) (initial text in HVAC control section) |
||
Line 1:
Buildings contribute to roughly 40% of the global energy use (approx. 64 PWh), of which a large portion is used for heating, cooling, ventilation, and air-conditioning (HVAC).<ref name=":0">{{Cite journal|date=2020-09-29|title=All you need to know about model predictive control for buildings|url=https://www.sciencedirect.com/science/article/pii/S1367578820300584|journal=Annual Reviews in Control|language=en|doi=10.1016/j.arcontrol.2020.09.001|issn=1367-5788}}</ref> The challenge is that current [https://en.wikipedia.org/wiki/Building_management_system building management systems (BMS)] are manually designed by human operators, which leads to energy inefficient operations. ML can help develop predictive models of building energy systems, leading to efficient building operation via advanced model-based optimal control methods. Independent studies reported that advanced HVAC control can significantly reduce energy use and mitigate greenhouse gas emissions with energy savings of 13% to 53%<ref>{{Cite journal|last=Gyalistras|first=Dimitrios|last2=Gwerder|first2=Markus|last3=Oldewurtel|first3=Frauke|last4=Jones|first4=Colin N.|last5=Morari|first5=Manfred|last6=Lehmann|first6=Beat|last7=Wirth|first7=Katharina|last8=Stauch|first8=Vanessa|date=2010|title=Analysis of energy savings potentials for integrated room automation|url=https://www.research-collection.ethz.ch/handle/20.500.11850/28685|journal=Clima 2010 sustainable energy use in buildings : 10th REHVA world congress ; 9 - 12 May, Antalya ; proceedings|language=en|publisher=Turkish Society of HVAC and Sanitary Engineers (TTMD); Federation of European Heating and Air Conditioning Associations (REHVA)|pages=R2|isbn=978-975-6907-14-6}}</ref><ref>{{Cite journal|last=Castilla|first=María del Mar|last2=Álvarez|first2=José Domingo|last3=Rodríguez|first3=Francisco|last4=Berenguel|first4=Manuel|date=2014|title=Comfort Control in Buildings|url=https://link.springer.com/book/10.1007/978-1-4471-6347-3|journal=Advances in Industrial Control|language=en-gb|doi=10.1007/978-1-4471-6347-3|issn=1430-9491}}</ref><ref>{{Cite journal|last=Široký|first=Jan|last2=Oldewurtel|first2=Frauke|last3=Cigler|first3=Jiří|last4=Prívara|first4=Samuel|date=2011-09-01|title=Experimental analysis of model predictive control for an energy efficient building heating system|url=http://www.sciencedirect.com/science/article/pii/S0306261911001668|journal=Applied Energy|language=en|volume=88|issue=9|pages=3079–3087|doi=10.1016/j.apenergy.2011.03.009|issn=0306-2619}}</ref><ref>{{Cite journal|last=Ma|first=Y.|last2=Borrelli|first2=F.|last3=Hencey|first3=B.|last4=Coffey|first4=B.|last5=Bengea|first5=S.|last6=Haves|first6=P.|date=2012-05|title=Model Predictive Control for the Operation of Building Cooling Systems|url=https://ieeexplore.ieee.org/abstract/document/5739562|journal=IEEE Transactions on Control Systems Technology|volume=20|issue=3|pages=796–803|doi=10.1109/TCST.2011.2124461|issn=1558-0865}}</ref><ref>{{Cite journal|date=2020-04-01|title=Cloud-based implementation of white-box model predictive control for a GEOTABS office building: A field test demonstration|url=https://www.sciencedirect.com/science/article/pii/S0959152419306857|journal=Journal of Process Control|language=en|volume=88|pages=63–77|doi=10.1016/j.jprocont.2020.02.007|issn=0959-1524}}</ref>. Additional benefit is that advanced control strategies can provide grid flexibility services via price-responsiveness and active demand response capabilities<ref>{{Cite journal|last=Bianchini|first=G.|last2=Casini|first2=M.|last3=Pepe|first3=D.|last4=Vicino|first4=A.|last5=Zanvettor|first5=G. G.|date=2017-12|title=An integrated MPC approach for demand-response heating and energy storage operation in smart buildings|url=https://ieeexplore.ieee.org/abstract/document/8264228|journal=2017 IEEE 56th Annual Conference on Decision and Control (CDC)|pages=3865–3870|doi=10.1109/CDC.2017.8264228}}</ref><ref>{{Cite journal|last=Borsche|first=Theodor|last2=Oldewurtel|first2=Frauke|last3=Andersson|first3=Göran|date=2014-01-01|title=Scenario-based MPC for Energy Schedule Compliance with Demand Response|url=http://www.sciencedirect.com/science/article/pii/S1474667016432489|journal=IFAC Proceedings Volumes|series=19th IFAC World Congress|language=en|volume=47|issue=3|pages=10299–10304|doi=10.3182/20140824-6-ZA-1003.01284|issn=1474-6670}}</ref><ref>{{Cite journal|last=Esther|first=B. Priya|last2=Kumar|first2=K. Sathish|date=2016-06-01|title=A survey on residential Demand Side Management architecture, approaches, optimization models and methods|url=http://www.sciencedirect.com/science/article/pii/S1364032115016652|journal=Renewable and Sustainable Energy Reviews|language=en|volume=59|pages=342–351|doi=10.1016/j.rser.2015.12.282|issn=1364-0321}}</ref><ref>{{Cite journal|last=O'Neill|first=D.|last2=Levorato|first2=M.|last3=Goldsmith|first3=A.|last4=Mitra|first4=U.|date=2010-10|title=Residential Demand Response Using Reinforcement Learning|url=https://ieeexplore.ieee.org/document/5622078|journal=2010 First IEEE International Conference on Smart Grid Communications|pages=409–414|doi=10.1109/SMARTGRID.2010.5622078}}</ref><ref>{{Cite journal|last=Pallonetto|first=Fabiano|last2=De Rosa|first2=Mattia|last3=Milano|first3=Federico|last4=Finn|first4=Donal P.|date=2019-04-01|title=Demand response algorithms for smart-grid ready residential buildings using machine learning models|url=http://www.sciencedirect.com/science/article/pii/S0306261919303101|journal=Applied Energy|language=en|volume=239|pages=1265–1282|doi=10.1016/j.apenergy.2019.02.020|issn=0306-2619}}</ref><ref>{{Cite journal|last=Vázquez-Canteli|first=José R.|last2=Nagy|first2=Zoltán|date=2019-02-01|title=Reinforcement learning for demand response: A review of algorithms and modeling techniques|url=http://www.sciencedirect.com/science/article/pii/S0306261918317082|journal=Applied Energy|language=en|volume=235|pages=1072–1089|doi=10.1016/j.apenergy.2018.11.002|issn=0306-2619}}</ref>.
==Background Readings==
==Community==
Line 4 ⟶ 6:
==Data==
==Future Directions==
Based on the reflections presented in<ref name=":0" /><ref>{{Cite journal|last=Prívara|first=Samuel|last2=Cigler|first2=Jiří|last3=Váňa|first3=Zdeněk|last4=Oldewurtel|first4=Frauke|last5=Sagerschnig|first5=Carina|last6=Žáčeková|first6=Eva|date=2013-01-01|title=Building modeling as a crucial part for building predictive control|url=http://www.sciencedirect.com/science/article/pii/S0378778812005336|journal=Energy and Buildings|language=en|volume=56|pages=8–22|doi=10.1016/j.enbuild.2012.10.024|issn=0378-7788}}</ref><ref>{{Cite journal|last=Killian|first=M.|last2=Kozek|first2=M.|date=2016-08-15|title=Ten questions concerning model predictive control for energy efficient buildings|url=http://www.sciencedirect.com/science/article/pii/S0360132316301925|journal=Building and Environment|language=en|volume=105|pages=403–412|doi=10.1016/j.buildenv.2016.05.034|issn=0360-1323}}</ref><ref>{{Cite journal|last=Henze|first=Gregor P.|date=2013-05-01|title=Model predictive control for buildings: a quantum leap?|url=https://doi.org/10.1080/19401493.2013.778519|journal=Journal of Building Performance Simulation|volume=6|issue=3|pages=157–158|doi=10.1080/19401493.2013.778519|issn=1940-1493}}</ref><ref>{{Cite journal|last=Wang|first=Zhe|last2=Hong|first2=Tianzhen|date=2020-07|title=Reinforcement learning for building controls: The opportunities and challenges|url=http://dx.doi.org/10.1016/j.apenergy.2020.115036|journal=Applied Energy|volume=269|pages=115036|doi=10.1016/j.apenergy.2020.115036|issn=0306-2619}}</ref>, there are several challenges for wide-spread application of advanced building controls:
# Availability of appropriate hardware and software infrastructure with compatible communication interfaces.
# Availability of data, and data-efficiency of the modeling and control design algorithms.
# User-friendly and computationally efficient building modeling and control design tools.
# Automated design, tuning, and deployment with plug-and-play implementation of advanced control strategy.
# Capability of handling multi-dimensional and hierarchical systems with dynamical coupling.
# Dealing with uncertainties in modeling and real-time measurements.
# Control security/safety/robustness by minimizing or eliminating the chance of generating control signals that might lead to undesirable outcomes during operation.
# Trained personnel to handle commissioning, and maintenance of advanced control methods in practice.
# Privacy and cyber-security issues and the user trust.
# Performance evaluation and algorithms benchmarking.
==References==
| |||