Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A latent variable approach to heat load prediction in thermal grids
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems. Optimation AB, Uppsala, Sweden.ORCID iD: 0000-0001-5385-7022
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.ORCID iD: 0000-0002-9901-5776
Department of Information Technology, Uppsala University, Sweden.
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.ORCID iD: 0000-0002-5888-8626
2020 (English)In: European Control Conference 2020, IEEE, 2020, p. 344-349Conference paper, Published paper (Refereed)
Abstract [en]

In this paper a new method for heat load prediction in district energy systems is proposed. The method uses a nominal model for the prediction of the outdoor temperature dependent space heating load, and a data driven latent variable model to predict the time dependent residual heat load. The residual heat load arises mainly from time dependent operation of space heating and ventilation, and domestic hot water production. The resulting model is recursively updated on the basis of a hyper-parameter free implementation that results in a parsimonious model allowing for high computational performance. The approach is applied to a single multi-dwelling building in Luleå, Sweden, predicting the heat load using a relatively small number of model parameters and easily obtained measurements. The results are compared with predictions using an artificial neural network, showing that the proposed method achieves better prediction accuracy for the validation case. Additionally, the proposed methods exhibits explainable behavior through the use of an interpretable physical model.

Place, publisher, year, edition, pages
IEEE, 2020. p. 344-349
Series
European Control Conference (ECC)
National Category
Control Engineering
Research subject
Control Engineering
Identifiers
URN: urn:nbn:se:ltu:diva-77819DOI: 10.23919/ECC51009.2020.9143860ISI: 000613138000065Scopus ID: 2-s2.0-85090138559OAI: oai:DiVA.org:ltu-77819DiVA, id: diva2:1395586
Conference
2020 European Control Conference (ECC), 12-15 May, 2020, Saint Petersburg, Russia
Funder
Swedish Energy Agency, 43090-2
Note

ISBN för värdpublikation: 978-3-90714-402-2, 978-1-7281-8813-3

Available from: 2020-02-24 Created: 2020-02-24 Last updated: 2021-03-12Bibliographically approved
In thesis
1. Towards efficient modeling and simulation of district energy systems
Open this publication in new window or tab >>Towards efficient modeling and simulation of district energy systems
2021 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Dynamic simulation of district energy systems has an increased importance in the transition towards renewable energy sources, lower temperature district heating grids and waste heat recovery from industrial plants and data centers. However, a city-scale, automatically generated and updated simulator that can be used for the whole lifecycle of the plant remains a distant vision. Physics based models are often used for planning and validation, but the complexity is too high to use the models for optimization and automatic control, or for longer time spans.

In this thesis, the experiences and challenges from previous district heating simulation projects using a co-simulation approach are summarized, with corresponding research gaps and proposed research directions. Two of the identified shortcomings are investigated in more detail in the thesis: 

First, a robust and computationally efficient method for prediction of the heat load for buildings is proposed. A deterministic dynamic model is used to predict the space heating load, and a latent variable model using Fourier basis functions predicts the heat load used for e.g. hot tap water and ventilation. The prediction model validity is shown on a multi-dwelling building located in Luleå, Sweden. 

Second, a probabilistic model based on Gaussian Processes is used to simulate the temperature dynamics of a district heating pipe. The model is trained and validated against a state-of-the-art physics based pipe model. It is shown that the model both replicates the behavior of the reference model, and that it can account for uncertainty of the inputs. By employing a kernel exploiting the underlying physics, many shortcomings of Gaussian Process models can be mitigated. 

The results suggest that a mix of physics based and probabilistic methods can be one way forward towards a digital twin of a city-scale district energy system. Natural extensions to the published papers would be to research how the methods can be applied to a larger scale district energy system. 

Place, publisher, year, edition, pages
Luleå University of Technology, 2021
Series
Licentiate thesis / Luleå University of Technology, ISSN 1402-1757
National Category
Control Engineering
Research subject
Automatic Control
Identifiers
urn:nbn:se:ltu:diva-83242 (URN)978-91-7790-781-7 (ISBN)978-91-7790-782-4 (ISBN)
Presentation
2021-05-06, Distans, 13:00 (English)
Opponent
Supervisors
Available from: 2021-03-12 Created: 2021-03-12 Last updated: 2021-04-22Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Atta, KhalidBirk, Wolfgang

Search in DiVA

By author/editor
Simonsson, JohanAtta, KhalidBirk, Wolfgang
By organisation
Signals and Systems
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 154 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf