[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123489-en":3,"doc-seo-123489-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123489,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Determine the heat demand of existing buildings with machine learning","The renovation rate of existing buildings is crucial to advancing the Swiss Energy Strategy 2050+. A simple, cost-effective approach is needed to determine heating demand even when detailed planning inputs are limited. This study develops a machine-learning method using the Swiss cantonal building energy certificate (GEAK) database, aiming to estimate heat demand quickly from a minimal parameter set. Results compare ML-derived building envelope classes with original GEAK classes for single-family houses.","PAPER • OPEN ACCESS  \nDetermine the heat demand of existing buildings with machine learning  \nTo cite this article: Joachim Werner Hofmann et al 2023 J. Phys. : Conf. Ser. 2600 032013  \nView the article online for updates and enhancements.  \nThis content was downloaded from IP address [147.86.223.248](147.86.223.248) on 04/12/2023 at 12:34  \nJournal of Physics: Conference Series 2600 (2023) 032013 doi:10.1088/1742-6596/2600/3/032013  \nDetermine the heat demand of existing buildings with machine learning  \nJoachim Werner Hofmann, Christian Amoser, Achim Geissler, Monika Hall  \nInstitute for Sustainability and Energy in Construction (INEB) University of Applied Science and Arts Northwestern Switzerland, Hofackerstrasse 30, CH 4132 Muttenz  \nE-mail: joachim.hofmann@fhnw.ch  \nAbstract. The renovation rate of existing buildings plays a major role in the Swiss Energy Strategy 2050+ . To increase this rate, there must be a simple and cost-effective method to determine the heat demand of existing buildings. In this paper, the generation of such a method, based on the Swiss cantonal building energy certificate (GEAK) database with the help of machine learning (ML), is studied. The aim of the project was to develop a ML model which allows the heat demand of existing buildings to be determined quickly with a minimal set of parameters. The comparison of the GEAK building envelope class for single family houses calculated with the new ML model and the original GEAK classes shows that approximately 62 % have the same class, 32 % differ by one class and 6 % by two classes. The ML model is a good starting point for further refinements and developments.  \n1. Introduction  \nThe Swiss Federal Office of Energy (SFOE) is aligning its vision with the net-zero basic variant of the energy perspectives 2050+ [1] . The vision of the SFOE for the Swiss building stock can be explained with the term ROSES. ROSES stands for Reduction, Optimization, Substitution, Renewable Energy and Sustainability. The project is based on the topics of reduction, optimization and substitution. To significantly increase the renovation rate in the coming years, easy-to-use planning methods must be developed to determine the heat demand of buildings. In these calculations, the determination of the Uvalues and the areas are work intensive. For this reason, the aim of the project was to develop a ML method to quickly determine the heat demand of existing buildings. The potential for using this ML method is diverse:  \n• Reduction of the effort necessary to calculate the heat demand for existing buildings as a basis for planning energy renewal measures. Fast and yet sufficiently accurate recording of the status, even if the planning basis is missing or incomplete.  \n• Simple and yet sufficiently precise determination of the heat demand as a basis for the design of heating systems in existing buildings, especially for heat pump systems.  \n• Determination of the heat demand of districts as a basis for the design of local heating networks or energy policy decisions.  \n• The ML method also has the potential for the simplified creation of energy or CO2 labels.  \n• There is still a lack of experts in the energy sector. Efforts to increase efficiency in their work can help to increase both the renewal rate and the assessment quality of existing buildings.  \nContent from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.  \nPublished under licence by IOP Publishing Ltd 1  \nJournal of Physics: Conference Series 2600 (2023) 032013 doi:10.1088/1742-6596/2600/3/032013  \n2. Methodology  \n2.1. Overview  \nMethods using machine learning are suitable for solving complex technical problems. The methodology of the procedure (process steps) is shown in Figure 1.  \nFigure 1. Workflow for machine learning [2,3] .  \nThe workflow is divi","cbCailfMzbw6rhp9","https://ap.wps.com/l/cbCailfMzbw6rhp9","pdf",1103931,1,7,"English","en",105,"# Abstract\n# Introduction\n## Motivation and project goals\n## Potential applications of the ML method\n# Methodology\n## Overview\n## Statistical and building physical approach","[{\"question\":\"What problem does the paper address about existing buildings?\",\"answer\":\"The paper addresses the need for a simple, cost-effective method to determine the heat demand of existing buildings to support higher renovation rates.\"},{\"question\":\"How is the machine-learning method developed in this study?\",\"answer\":\"It is built using the Swiss GEAK database, applying a statistical and building-physical approach with strong feature selection and then training a machine-learning model.\"},{\"question\":\"What is the key comparison result with GEAK classes?\",\"answer\":\"For single-family houses, about 62% of buildings have the same envelope class as the original GEAK classification, 32% differ by one class, and 6% by two classes.\"}]","Determine the heat demand of existing buildings with machine learning | PDF",1785816815,18,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"determine-the-heat-demand-of-existing-buildings-with-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/determine-the-heat-demand-of-existing-buildings-with-machine-learning/123489/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address about existing buildings?","Question",{"text":75,"@type":76},"The paper addresses the need for a simple, cost-effective method to determine the heat demand of existing buildings to support higher renovation rates.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the machine-learning method developed in this study?",{"text":80,"@type":76},"It is built using the Swiss GEAK database, applying a statistical and building-physical approach with strong feature selection and then training a machine-learning model.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the key comparison result with GEAK classes?",{"text":84,"@type":76},"For single-family houses, about 62% of buildings have the same envelope class as the original GEAK classification, 32% differ by one class, and 6% by two classes.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]