prikaz prve stranice dokumenta Human-centered predictive control in buildings using personalized comfort data-driven models
  Download
PDF 8.86 MB
doctoral thesis
Human-centered predictive control in buildings using personalized comfort data-driven models
Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2024. urn:nbn:hr:235:963503
Bresa, Arlinda
University of Zagreb
Faculty of Mechanical Engineering and Naval Architecture

Institutional repository: Repository of Faculty of Mechanical Engineering and Naval Architecture University of Zagreb

Cite this document

Bresa, A. (2024). Human-centered predictive control in buildings using personalized comfort data-driven models (Doctoral thesis). Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:235:963503

Bresa, Arlinda. "Human-centered predictive control in buildings using personalized comfort data-driven models." Doctoral thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2024. https://urn.nsk.hr/urn:nbn:hr:235:963503

Bresa, Arlinda. "Human-centered predictive control in buildings using personalized comfort data-driven models." Doctoral thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2024. https://urn.nsk.hr/urn:nbn:hr:235:963503

Bresa, A. (2024). 'Human-centered predictive control in buildings using personalized comfort data-driven models', Doctoral thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, accessed 20 December 2024, https://urn.nsk.hr/urn:nbn:hr:235:963503

Bresa A. Human-centered predictive control in buildings using personalized comfort data-driven models [Doctoral thesis]. Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture; 2024 [cited 2024 December 20] Available at: https://urn.nsk.hr/urn:nbn:hr:235:963503

A. Bresa, "Human-centered predictive control in buildings using personalized comfort data-driven models", Doctoral thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, Zagreb, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:235:963503

Metadata
TitleHuman-centered predictive control in buildings using personalized comfort data-driven models
Title (croatian)Prediktivno upravljanje u zgradama orijentirano na korisnike pomoću modela ugodnosti temeljenih na personaliziranim podacima
AuthorArlinda Bresa https://orcid.org/0000-0002-0702-5425
MentorTea Žakula (mentor)
Committee memberAndrej Jokić (predsjednik povjerenstva)
Committee memberClayton Miller https://orcid.org/0000-0002-1186-4299 (član povjerenstva)
Committee memberDean Ajduković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Mechanical Engineering and Naval Architecture
Zagreb
Defense date and country2024-09-30, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Universal decimal classification
(UDC)		62 - Engineering. Technology in general
Abstract
The strive for improved building energy performance has led to increased automation levels in building control systems, challenging the balance between energy efficiency and comfort. This often leads to dissatisfaction as occupants are unable to adjust conditions to their preferences, causing discomfort. Since people spend almost 90% of their time indoors, shifting to human-centered control (HCC) systems in buildings is crucial. HCC allows the integration of user preferences provided as self-reported subjective feedback into the building control system for indoor environmental control and grid flexibility actions. This thesis explores user-building interactions through data-driven personalized comfort models (PCMs) by implementing HCC in a building and focuses on the human aspect of HCC. Methods include a survey of nearly 1000 respondents, two field experiments, and simulations. Results from the field experiment show that integrating user preferences using PCMs increases comfort satisfaction by 17%. However, the survey shows that only 56% of respondents are willing to interact or share data with HCC, and this willingness can be predicted with 64% prediction potential using a Theory of Planned Behaviour framework. The results also suggest that integrating HCC with model predictive control (MPC) improves grid flexibility, achieving up to 45% energy savings, 61% load shifting and 59% cost savings compared to standard systems. These findings provide valuable insights for designing future HCC systems that prioritize occupant needs while empowering buildings in smart grids.
Abstract (croatian)
Potreba za poboljšanjem energetskih značajki zgrada dovela je do povećane razine automatizacije zgrada, a što može imati i negativan utjecaj. Specifično, može dovesti do nezadovoljstva korisnika koji ne mogu prilagoditi uvjete svojim preferencijama, što uzrokuje neugodu. Budući da ljudi provode 90% vremena u zatvorenom prostoru, prijelaz na sustave upravljanja usmjerenih na ljude (HCC) je ključan. HCC omogućuje integraciju korisničkih preferencija u sustav upravljanja zgradom za regulaciju unutarnjeg okruženja i interakciju s energetskom mrežom. Doktorska disertacija istražuje interakciju između korisnika i zgrade putem personaliziranih modela udobnosti (PCM) implementacijom HCC-a u stvarnoj zgradi. Metode uključuju anketu s gotovo 1000 ispitanika, dva terenska eksperimenta i simulacije. Rezultati terenskih eksperimenata pokazuju da integracija korisničkih preferencija pomoću PCM-ova povećava zadovoljstvo korisnika za 17%. Međutim, anketa pokazuje da je samo 56% ispitanika spremno dijeliti podatke s HCC-om. Korištenjem predložene metodologije, temeljene na Teoriji planiranog ponašanja, spremnost korisnika može se predvidjeti sa 64%-tnom sigurnošću. Rezultati istraživanja također pokazuju da integracija HCC-a s modelsko prediktivnim upravljanjem povećava fleksibilnost mreže, ostvarujući uštede energije od 45%, premještanje opterećenja od 61% i smanjenje troškova od 59% u usporedbi sa standardnim sustavima. Ovi rezultati pružaju vrijedne informacije za dizajn budućih HCC sustava koji stavljaju potrebe korisnika u prvi plan i omogućuju zgradama ulogu u pametnim mrežama.
Keywords
Keywords (croatian)
Languageenglish
URN:NBNurn:nbn:hr:235:963503
Study programmeTitle: Mechanical Engineering, Shipbuilding, Aeronautical Engineering, Metallurgy - PhD
Study programme type: university
Study level: postgraduate
Academic / professional title: doktor/doktorica znanosti u području tehničkih znanosti (doktor/doktorica znanosti u području tehničkih znanosti)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2024-10-16 10:11:58