A latent variable approach to heat load prediction in thermal grids

Document identifier: oai:DiVA.org:ltu-77819
Access full text here:10.23919/ECC51009.2020.9143860
Keyword: Engineering and Technology, Electrical Engineering, Electronic Engineering, Information Engineering, Control Engineering, Teknik och teknologier, Elektroteknik och elektronik, Reglerteknik
Publication year: 2020
Relevant Sustainable Development Goals (SDGs):

The SDG label(s) above have been assigned by OSDG.ai

Abstract:

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.

Authors

Johan Simonsson

Luleå tekniska universitet; Signaler och system; Optimation AB, Uppsala, Sweden
Other publications >>

Khalid Atta

Luleå tekniska universitet; Signaler och system
Other publications >>

Dave Zachariah

Department of Information Technology, Uppsala University, Sweden
Other publications >>

Wolfgang Birk

Luleå tekniska universitet; Signaler och system
Other publications >>

Record metadata

Click to view metadata

	
    header: 
        identifier: oai:DiVA.org:ltu-77819
        datestamp: 2021-04-19T13:07:08Z
        setSpec: SwePub-ltu
    metadata: 
        mods: 
            @attributes: 
                version: 3.7
            recordInfo: 
                recordContentSource: ltu
                recordCreationDate: 2020-02-24
            identifier: 
                http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-77819
                10.23919/ECC51009.2020.9143860
                2-s2.0-85090138559
            titleInfo: 
                @attributes: 
                    lang: eng
                title: A latent variable approach to heat load prediction in thermal grids
            abstract: 
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.

            subject: 
                    @attributes: 
                        lang: eng
                        authority: uka.se
                    topic: 
                        Engineering and Technology
                        Electrical Engineering Electronic Engineering Information Engineering
                        Control Engineering
                    @attributes: 
                        lang: swe
                        authority: uka.se
                    topic: 
                        Teknik och teknologier
                        Elektroteknik och elektronik
                        Reglerteknik
                    @attributes: 
                        lang: swe
                        authority: ltu
                    topic: Reglerteknik
                    genre: Research subject
                    @attributes: 
                        lang: eng
                        authority: ltu
                    topic: Control Engineering
                    genre: Research subject
            language: 
                languageTerm: eng
            genre: 
                conference/other
                ref
            note: 
                Published
                4
                
ISBN för värdpublikation: 978-3-90714-402-2 978-1-7281-8813-3

            name: 
                    @attributes: 
                        type: personal
                        authority: ltu
                    namePart: 
                        Simonsson
                        Johan
                        1980-
                    role: 
                        roleTerm: aut
                    affiliation: 
                        Luleå tekniska universitet
                        Signaler och system
                        Optimation AB Uppsala Sweden
                    nameIdentifier: 
                        johsim
                        0000-0001-5385-7022
                    @attributes: 
                        type: personal
                        authority: ltu
                    namePart: 
                        Atta
                        Khalid
                    role: 
                        roleTerm: aut
                    affiliation: 
                        Luleå tekniska universitet
                        Signaler och system
                    nameIdentifier: 
                        khaatt
                        0000-0002-9901-5776
                    @attributes: 
                        type: personal
                    namePart: 
                        Zachariah
                        Dave
                    role: 
                        roleTerm: aut
                    affiliation: Department of Information Technology Uppsala University Sweden
                    @attributes: 
                        type: personal
                        authority: ltu
                    namePart: 
                        Birk
                        Wolfgang
                        1968-
                    role: 
                        roleTerm: aut
                    affiliation: 
                        Luleå tekniska universitet
                        Signaler och system
                    nameIdentifier: 
                        wolfgang
                        0000-0002-5888-8626
            relatedItem: 
                    @attributes: 
                        type: host
                    genre: grantAgreement
                    name: 
                        @attributes: 
                            type: corporate
                        namePart: Energimyndigheten
                        role: 
                            roleTerm: fnd
                    identifier: 43090-2
                    @attributes: 
                        type: host
                    titleInfo: 
                        title: European Control Conference 2020
                    part: 
                        extent: 
                            start: 344
                            end: 349
                    @attributes: 
                        type: series
                    titleInfo: 
                        title: European Control Conference (ECC)
            originInfo: 
                dateIssued: 2020
                publisher: IEEE
            physicalDescription: 
                form: print
            typeOfResource: text