[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125763-en":3,"doc-seo-125763-105":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},125763,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","A Machine Learning-based Anomaly Detection Framework for Building Electricity Consumption Data","Suboptimal management or system malfunctions can cause abnormal electricity use in buildings, creating significant energy waste. Effective high-level monitoring using machine learning and visualization is therefore essential to detect deviations from baseline consumption. Many historical datasets lack labeled anomalies, limiting supervised methods, while expert interpretability challenges common ML techniques. The proposed Anomaly Detection Framework uses two complementary semi-supervised approaches with SAX encoding to improve both interpretability and accuracy, leveraging CART and MLP models on real telecom electricity data.","POLITECNICO DI TORINO  \nRepository ISTITUZIONALE  \nA Machine Learning-based Anomaly Detection Framework for Building Electricity Consumption Data  \nOriginal  \nA Machine Learning-based Anomaly Detection Framework for Building Electricity Consumption Data / Mascali, Lorenzo; Schiera, DANIELE SALVATORE; Eiraudo, Simone; Barbierato, Luca; Giannantonio, Roberta; Patti, Edoardo; Bottaccioli, Lorenzo; Lanzini, Andrea. -In: SUSTAINABLE ENERGY, GRIDS AND NETWORKS. -ISSN 2352-4677. -36:(2023) .[10.1016/j.segan.2023.101194]  \nAvailability:  \nThis version is available at: 11583/2983186 since: 2023-10-25T10:11:46Z  \nPublisher: Elsevier  \nPublished  \nDOI:10.1016/j.segan.2023.101194  \nTerms of use:  \nThis article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository  \nPublisher copyright  \n(Article begins on next page)  \n18 September 2024  \nA Machine Learning-based Anomaly Detection Framework for Building Electricity  \nConsumption Data  \nLorenzo Mascalia , Daniele Salvatore Schieraa , Simone Eiraudoa , Luca Barbieratoa , Roberta Giannantoniob , Edoardo Pattia ,  \nLorenzo Bottacciolia , Andrea Lanzinia  \na Energy Center Lab, Politecnico di Torino, name.surname@polito.it, Torino, 10138, Italy,  \nbTIM S.p.A, name.surname@telecomitalia.it, Milan, 20123, Italy,  \nAbstract  \nA suboptimal management or system malfunction can often lead to abnormal energy consumption in buildings, which results ina significant waste of energy. For this reason, the adoption of advanced monitoring systems, based on Machine Learning (ML) and visualization techniques, is crucial to avoid possible deviations from the baseline energy consumption. However, the historical data on which analyses are based generally do not report the occurrence of anomalies. Therefore, the application of supervised ML techniques is limited and unsupervised approaches are favoured. Moreover, domain experts find most ML techniques hard to interpret and thus find it difficult to contextualize anomalies. To overcome these issues, this work proposes a machine learningbased Anomaly Detection Framework (ADF) that involves the use of two complementary semi-supervised ML applications to obtain a highly interpretable and accurate detection of anomalies. Both techniques use Symbolic Aggregate approXimation (SAX) encoding to extract the most relevant information from load profiles. The aim of the first approach is to maximize the interpretability of the definition and distinction between anomalous and normal behavior. This is achieved using a Classification And Regression Tree (CART), albeit at the expense of a coarser output granularity. The second approach exploits a Multi-Layer Perceptron (MLP) algorithm to obtain a higher and more accurate output resolution, although it leads to a less interpretable definition of any anomalous behavior. The ADF has been applied to a real case study using electricity consumption data provided by a large telecommunications service provider. The results show that combining both ML models enhances the accuracy and interpretability of the detected anomalies.  \nKeywords: Anomaly Detection, Electricity Consumption, Machine Learning, Semi-Supervised, Synthetic Ground Truth, Symbolic Aggregate Approximation, Smart Meter  \nPACS: 0000, 1111  \n2000 MSC: 0000, 1111  \nList of Acronyms  \nADF Anomaly Detection Framework  \nARIMA Autoregressive Integrated Moving Average CART Classification And Regression Tree  \nCO Central Office  \nKPI Key Performance Indicator  \nLOF Local Outlier Factor  \nLSTM Long Short-Term Memory MAPE Mean Absolute Percentage Error MIA Mean Index Adequacy  \nML Machine Learning  \nMLP Multi-Layer Perceptron NDA Non-Disclosure Agreements NN Neural Network  \nPAA Piecewise Aggregate Approximation  \nPCA Principal Component Analysis PDF Probability Density Function  \nRNN Recurrent Neural Network  \nSAX Symbolic Aggregate approXimation  \nSGT Synthetic Ground Truth  \nSOM Self-Organizing Map  \nSVR Support Ve","cbCaifosx5UBZxXD","https://ap.wps.com/l/cbCaifosx5UBZxXD","pdf",3779657,1,17,"English","en",105,"# Introduction\n## Energy monitoring and anomaly detection challenges\n# Proposed framework\n## Semi-supervised approaches with SAX encoding\n# Results and evaluation\n## Combining CART and MLP for improved accuracy and interpretability","[{\"question\":\"Why are anomaly detection methods important for building electricity consumption?\",\"answer\":\"Abnormal consumption often stems from malfunction or poor management and leads to significant energy waste. Detecting deviations from baseline usage enables more effective monitoring and alerting.\"},{\"question\":\"Why are supervised machine learning techniques limited in this context?\",\"answer\":\"Historical building electricity datasets commonly do not include occurrences of anomalies as labeled training data. This makes supervised learning difficult to apply effectively.\"},{\"question\":\"How does the proposed framework achieve both interpretability and accuracy?\",\"answer\":\"It combines two complementary semi-supervised applications using SAX encoding. One approach uses CART to improve interpretability, while the second uses an MLP to produce higher-resolution results, and the combination improves both accuracy and interpretability.\"}]","A Machine Learning-based Anomaly Detection Framework for Building Electricity Consumption Data | PDF",1785901079,43,{"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},"a-machine-learning-based-anomaly-detection-framework-for-building-electricity-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/a-machine-learning-based-anomaly-detection-framework-for-building-electricity-consumption-data/125763/",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},"Why are anomaly detection methods important for building electricity consumption?","Question",{"text":75,"@type":76},"Abnormal consumption often stems from malfunction or poor management and leads to significant energy waste. Detecting deviations from baseline usage enables more effective monitoring and alerting.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why are supervised machine learning techniques limited in this context?",{"text":80,"@type":76},"Historical building electricity datasets commonly do not include occurrences of anomalies as labeled training data. This makes supervised learning difficult to apply effectively.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed framework achieve both interpretability and accuracy?",{"text":84,"@type":76},"It combines two complementary semi-supervised applications using SAX encoding. One approach uses CART to improve interpretability, while the second uses an MLP to produce higher-resolution results, and the combination improves both accuracy and interpretability.","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"]