[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125484-en":3,"doc-seo-125484-105":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":20,"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},125484,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","Development and Evaluation of Machine Learning Algorithms for Anomaly Detection in Building Technology Consumption Data","Buildings account for a large share of global energy use, and the EU promotes retrofitting buildings with sensors to enable collection of consumption data. Beyond basic KPIs, the thesis explores how real-time analysis of data streams can support detection of anomalous behavior linked to energy inefficiencies or technical issues. It evaluates suitable machine learning methods for anomaly detection and systematic anomaly classification, combining expert interviews, literature review, and quantitative model performance assessment. A prototype architecture integrates predictive and classification tasks into a unified anomaly detection framework.","Master’s Thesis  \nDevelopment and Evaluation of Machine Learning Algorithms for Anomaly Detection in Building Technology Consumption Data  \nunder the supervision of  \nAo.Univ.Prof. Dipl.-Ing. Mag.rer.soc.oec. Dr.techn. Alexander Redlein  \nE330-02-2-Forschungsgruppe Immobilien und Facility Management  \nsubmitted to the Faculty of Mechanical and Industrial Engineering of Technische Universität Wien  \nfor the degree of Diplom-Ingenieur (Dipl.-Ing.)  \nby  \nDavid Osl, BSc  \nStatutory Declaration  \nThis thesis is the result of my own work and includes nothing that is the outcome of work done in collaboration except as specified in the text.  \nIt is not substantially the same as any that I have submitted, or, is being concurrently submitted for a degree or diploma or other qualification at Technische Universität Wien or any other University or similar institution except as specified in the text. I further state that no substantial part of my thesis has already been submitted, or, is being concurrently submitted for any such degree, diploma or other qualification at Technische Universität Wien or any other University or similar institution except as specified in the text.  \nVienna, December 2025 .. .. .. ... .. ... .. .. .. .. ... .. .. .. ..  \nDavid Osl, BSc  \nI  \nAcknowledgements  \nI would like to express my gratitude to all those who supported me throughout all stages of this thesis and also throughout my studies.  \nSpecial thanks go to ...  \n  Prof. Alexander Redlein for his dedicated supervision of this thesis, the provision of valuable insights and offering of constant support throughout my research. I also owe him my sincere gratitude for organising the AREC project which enabled the study visits at Stanford University and laid the foundation of this work. In this context, I would also like to thank my project partners from the Austrian side, namely Georg Windhager, Nicolas Gleissner and Paul Huber for offering moral support. Without them, this project work would not have been such a fun time.  \n... the industry partners Burghauptmannschaft and Bundesimmobiliengesellschaft for providing the funding of this project. Special thanks also goto those who supported this study with their expertise, namely Mr. Darko Srbu, Mr. Lukas Nöbauer and Mr. Thomas Mann.  \n... my wonderful girlfriend Lena who lovingly supported me throughout my studies and always was at my side. Also special thanks to my lovely sisters Maria, Sarah and Anna, always having an ear for my problems. My heartfelt gratitude goes out to all my friends in and outside of Vienna, but especially tomy people from the Dönertour for filling my weekends with laughter. Thankyou!  \n  most importantly my parents Sebastian and Marianne. Their endless support, trust, and belief in me carried me through this journey, I could not have done this without them. Thank you so much!  \nII  \nAbstract  \nAs buildings account for a large share of global energy use, the EU is pushing for the retrofitting of sensors to enable consumption data collection. While this already enables the provision of basic KPIs, additional value can be created by analysing the resulting data streams in real-time for anomalous behaviours, which may indicate energy inefficiencies or technical issues.  \nThis thesis addresses the questions of how machine learning algorithms can be applied in this context, focusing on which methods are best suited for anomaly detection and on how such anomalies can be systematically classified. The methodology for answering these questions combines expert interviews, a comprehensive literature review, and a quantitative performance assessment of different machine learning models. Furthermore, a prototype software architecture was developed to integrate predictive and classification tasks into a holistic anomaly detection framework, where predictive models can serve as effective providers of \"normal\" consumption values, with anomalies identified and classified in their deviations from thes","cbCaiqqc6avCu4rL","https://ap.wps.com/l/cbCaiqqc6avCu4rL","pdf",2986692,1,104,"English","en",105,"# Abstract\n## Research objectives\n## Methodology\n## Model evaluation results\n## Constraints and contributions","[{\"question\":\"How does the thesis connect building sensors to anomaly detection?\",\"answer\":\"It uses consumption data collected via retrofitted sensing to analyze data streams in real time, aiming to detect anomalous behavior that may reflect energy inefficiencies or technical issues.\"},{\"question\":\"Which machine learning approaches are compared in the work?\",\"answer\":\"The study compares multiple models including XGBoost, LSTM, GRU, TCN, Auto-Encoders, and Transformers for prediction and anomaly classification tasks.\"},{\"question\":\"What does the prototype system architecture do?\",\"answer\":\"It integrates predictive and classification tasks into a single anomaly detection framework, where predictive models provide normal consumption values and anomalies are identified and classified by their deviations.\"}]","Development and Evaluation of Machine Learning Algorithms for Anomaly Detection in Building Technology Consumption Data | PDF",1785899279,262,{"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},"development-and-evaluation-of-machine-learning-algorithms-for-anomaly-detection-in-building-technology-consumption-data","",{"@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/development-and-evaluation-of-machine-learning-algorithms-for-anomaly-detection-in-building-technology-consumption-data/125484/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does the thesis connect building sensors to anomaly detection?","Question",{"text":75,"@type":76},"It uses consumption data collected via retrofitted sensing to analyze data streams in real time, aiming to detect anomalous behavior that may reflect energy inefficiencies or technical issues.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning approaches are compared in the work?",{"text":80,"@type":76},"The study compares multiple models including XGBoost, LSTM, GRU, TCN, Auto-Encoders, and Transformers for prediction and anomaly classification tasks.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the prototype system architecture do?",{"text":84,"@type":76},"It integrates predictive and classification tasks into a single anomaly detection framework, where predictive models provide normal consumption values and anomalies are identified and classified by their deviations.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]