[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120904-en":3,"doc-seo-120904-105":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},120904,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","A Comparison of Automated Machine Learning Tools for Predicting Energy Building Consumption in Smart Cities","This paper compares three recent Automated Machine Learning (AutoML) tools—AutoGluon, H2O, and Oracle AutoMLx—to build a single regression model that predicts smart city energy building consumption values. Experiments use a one-year hourly dataset collected from 29 buildings in a Portuguese city, evaluating two input feature settings (with and without lagged data) under a rolling window scheme. Results are benchmarked against a univariate time series forecasting baseline using the automated FEDOT tool, which trains a separate predictive model per building. The lagged AutoGluon single-regression approach achieves competitive predictive and computational efficiency.","A Comparison of Automated Machine Learning tools for Predicting Energy Building Consumption in Smart Cities  \nDaniela Soares 1 , Pedro José Pereira 1 ;2 , Paulo Cortez2 , and Carlos Gonçalves3  \n1 EPMQ-IT Engineering Maturity and Quality Lab, CCG ZGDV Institute,  \nGuimarÃčes, Portugal {daniela.soares,[pedro.pereira}@ccg.pt](pedro.pereira}@ccg.pt)  \n2 ALGORITMI Center/LASI, Dep. Information Systems, University of Minho, [pcortez@dsi.uminho.pt](pcortez@dsi.uminho.pt)  \n3 ISEP, Polytechnic of Porto, rua Dr. António Bernardino de Almeida, 4249-015 Porto, Portugal  \n[cag@isep.ipp.pt](cag@isep.ipp.pt)  \nAbstract. In this paper, we explore and compare three recently proposed Automated Machine Learning (AutoML) tools (AutoGluon, H2O, Oracle AutoMLx) to create a single regression model that is capable of predicting smart city energy building consumption values. Using a recently collected one year hourly energy consumption dataset, related with  \n29 buildings from a Portuguese city, we perform several Machine Learning (ML) computational experiments, assuming two sets of input features (with and without lagged data) and a realistic rolling window evaluation. Furthermore, the obtained results are compared with a univariate Time Series Forecasting (TSF) approach, based on the automated FEDOT tool, which requires generating a predictive model for each building.  \nOverall, competitive results, in terms of both predictive and computational effort performances, were obtained by the input lagged AutoGluon single regression modeling approach.  \nKeywords: Automated Machine Learning 􀀁 Smart Cities 􀀁 Regression.  \n1 Introduction  \nDue to advances in Information Technology (IT) and Artificial Intelligence (AI), nowadays it is easy to collect, store and process data that reflect relevant phenomena within the context of smart cities [13] . In particular, the efficient and environmentally responsible use of energy resources has become an important concern of smart cities decision makers, which aim to create ecological and sustainable environments for its citizens. Following this need, several works have been proposed regarding the usage of ML to predict energy consumption and demand, aiming to improve energy efficiency and sustainability [15,16,11,14,20,7] .  \nIn this paper, as a real-world demonstration use case, we address the prediction energy consumption of several buildings from a Portuguese city. Following  \n2 D. Soares, P.J. Pereira, P. Cortez and C. Gonçalves  \na typical smart city context, energy consumption data is collected on a regular basis with an associated timestamp, thus its prediction can be addressed as aunivariate Time Series Forecasting (TSF) task [12] . However, this TSF approach implies modeling each building separately, which can lead to a vast amount of forecasting models (one for each building), increasing the difficulty of ML model maintenance and monitoring. A different approach is to use a single regression model capable of predicting the energy consumption of any building, increasing the learning task difficulty but simplifying the ML deployment phase, since only one model is maintained.  \nRegarding the related works, the usage of a single regression building energy prediction model approach is a recent trend (e.g., [14,17,7]) . Nevertheless, the majority of these related works do not adopt an Automated ML (AutoML) model selection and tuning. AutoML is particularly valuable for smart cities, allowing non-experts to more easily create and maintain ML predictive models [13] . In effect, the related works typically adopt a manual tuning of ML algorithms, performing some trial-and-error comparison performances on a particular dataset. Within our knowledge, there are only two studies that have employed AutoML tools for building energy consumption prediction, addressing this goal as a regression [19] or TSF [12] tasks. Yet, in these two studies, the authors have modeled each building separately, resulting in one ML model for each building. I","cbCaii1MycPrW1cJ","https://ap.wps.com/l/cbCaii1MycPrW1cJ","pdf",757724,1,12,"English","en",105,"# Introduction\n## Related Work\n# Methodology and Evaluation\n## Datasets and Tools\n## Feature Sets and Rolling Window\n# Results and Discussion\n# Conclusions and Future Work","[{\"question\":\"Which AutoML tools are compared in the study?\",\"answer\":\"The paper compares AutoGluon, H2O, and Oracle AutoMLx for building a regression model to predict energy consumption in smart cities.\"},{\"question\":\"How is model evaluation performed?\",\"answer\":\"Evaluation uses two feature configurations (with and without lagged data) and a realistic rolling window evaluation scheme based on the one-year hourly dataset.\"},{\"question\":\"How does the AutoML approach differ from the FEDOT time-series baseline?\",\"answer\":\"The proposed approach targets a single regression model shared across buildings, while the FEDOT baseline trains an automated time-series forecasting model separately for each building.\"}]","A Comparison of Automated Machine Learning Tools for Predicting Energy Building Consumption in Smart Cities | PDF",1785732599,30,{"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-comparison-of-automated-machine-learning-tools-for-predicting-energy-building-consumption-in-smart-cities","",{"@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-comparison-of-automated-machine-learning-tools-for-predicting-energy-building-consumption-in-smart-cities/120904/",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","2026-08-03",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},"Which AutoML tools are compared in the study?","Question",{"text":75,"@type":76},"The paper compares AutoGluon, H2O, and Oracle AutoMLx for building a regression model to predict energy consumption in smart cities.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is model evaluation performed?",{"text":80,"@type":76},"Evaluation uses two feature configurations (with and without lagged data) and a realistic rolling window evaluation scheme based on the one-year hourly dataset.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the AutoML approach differ from the FEDOT time-series baseline?",{"text":84,"@type":76},"The proposed approach targets a single regression model shared across buildings, while the FEDOT baseline trains an automated time-series forecasting model separately for each building.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":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":29,"slug":121},"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"]