[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127433-en":3,"doc-seo-127433-105":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},127433,8796095027276,"Valentina","https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=",8,"Research & Report","Addressing Missing Smart Meter Data in Electricity Consumption Using Machine Learning - Master Thesis","This study investigates Long Short-Term Memory (LSTM) neural networks as a method to estimate a household’s daily electricity consumption from smart meter data when readings are missing. Comprehensive data analysis prepares the dataset for training. A feature engineering process enriches inputs using variables such as weekday, outdoor temperature, and household occupancy. A univariate LSTM model based on past consumption and a multivariate LSTM model using engineered features are trained, evaluated, and compared against a baseline approach.","Addressing Missing Smart Meter Data in Electricity Consumption Using Machine Learning  \nLong Short-Term Memory for Enhanced Electricity Consumption Forecasting  \nMaster Thesis submitted to the Faculty of Economics and Business  \nAndrea JOHN  \n16718918  \nInformation Management Institute  \nUniversity of Neuchtel  \nFor the degree of Master of Science in Applied Economics  \nSupervised by  \nProf Adrian Holzer, University of Neuchtel Dr Vladimir Macko, University of Neuchtel  \nNeuchtel, JUNE/2023  \nContents  \n1 Introduction 5  \n2 Literature review 7  \n3 Methodology 9  \n3.1 Univariate LSTM Model ............................ 9  \n3.1.1 Sequence Prediction .......................... 9  \n3.1.2 Classical neural networks ....................... 9  \n3.1.3 Recurrent neural networks ...................... 14  \n3.1.4 Long Short Term Memory ....................... 15  \n3.2 Multivariate LSTM Model ........................... 17  \n3.2.1 Weekday ................................. 17  \n3.2.2 Calendar Week ............................. 18  \n3.2.3 Lags ................................... 18  \n3.2.4 Outdoor Temperature ......................... 18  \n3.2.5 Previous consumption on the same weekday ............ 19  \n3.2.6 Similar household consumption ................... 20  \n3.2.7 Household Occupancy ......................... 21  \n3.3 Benchmarking baseline ............................. 21  \n4 Data 22  \n4.1 Data Analysis of 15-Minutes Intervals .................... 22  \n4.2 Data Analysis of Hourly Intervals ....................... 25  \n4.3 Data Analysis of Daily Intervals ........................ 28  \n4.4 Dataset for Training and Validation ...................... 28  \n5 LSTM Setup 30  \n5.1 Model, Training and Validation ........................ 30  \n5.2 Error metrics ................................... 32  \n6 Results 34  \n6.1 Performance overview ............................. 34  \n6.2 Performance based on load curve characteristics .............. 37  \n6.2.1 Benchmarking baseline ........................ 39  \n6.2.2 Univariate LSTM Model ........................ 42  \n6.2.3 Multivariate LSTM Model ....................... 46  \n6.2.4 Alternative models ........................... 49  \n7 Limitations and Future Work 50  \n8 Conclusions 52  \nAbstract: This study investigates the potential of Long Short Term Memory neural networks to estimate smart meter electricity daily consumption data for a given household. Long Short Term Memory, LSTM for short, is a machine learning solution particularly well suited for building predictive models in a time-series context, due to its architecture and long-term memory capability. In the first step, the smart-meter electricity data undergoes a comprehensive data analysis, aimed at effectively preparing the data for training. In the second step, a feature engineering approach is applied to add relevant information such as the weekday, temperature or the occupancy of the household to the dataset. A univariate LSTM model, which utilizes past energy consumption data, alongside a multivariate LSTM model, that incorporates the engineered features is designed and trained. Finally, the results of the univariate LSTM model, the multivariate LSTM model, and a baseline method are evaluated and compared.  \nKeywords: missing values; smart meter data; long short term memory; feature engineering; time series forecasting  \n1 Introduction  \nClimate change, a pervasive and persistent global challenge, has led to the establishment of carbon emission regulations through international agreements such as the Kyoto Protocol and the Paris Agreement (Cullen, 2011; Horowitz, 2016) . Consequently, these agreements have clearly underscored the increasing importance of strategies focused on the use of renewable energy and the development of efficient power grids. Given that energy consumption within buildings account for over 40% of global energy use-a figure that is steadily rising (Hwang et al., 2020) -improving energy efficiency in buildings has become a","cbCaisOmjiqM5Qz3","https://ap.wps.com/l/cbCaisOmjiqM5Qz3","pdf",2010378,1,57,"English","en",105,"# Contents\n## Introduction\n## Literature review\n## Methodology\n## Data\n## LSTM Setup\n## Results\n## Limitations and Future Work\n## Conclusions","[{\"question\":\"What problem does the thesis address?\",\"answer\":\"The thesis addresses missing smart meter readings and the resulting gaps in historical electricity consumption data, aiming to predict missing daily consumption values using available readings.\"},{\"question\":\"Which machine learning models are used?\",\"answer\":\"It uses Long Short-Term Memory (LSTM) networks, including a univariate LSTM model and a multivariate LSTM model that incorporates engineered features.\"},{\"question\":\"How is the dataset prepared for training?\",\"answer\":\"The study performs comprehensive data analysis for preparation and applies feature engineering to add relevant contextual variables such as weekday, temperature, and household occupancy.\"}]","Addressing Missing Smart Meter Data in Electricity Consumption Using Machine Learning - Master Thesis | PDF",1785938839,144,{"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},"addressing-missing-smart-meter-data-in-electricity-consumption-using-machine-learning-master-thesis","",{"@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/addressing-missing-smart-meter-data-in-electricity-consumption-using-machine-learning-master-thesis/127433/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address?","Question",{"text":75,"@type":76},"The thesis addresses missing smart meter readings and the resulting gaps in historical electricity consumption data, aiming to predict missing daily consumption values using available readings.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are used?",{"text":80,"@type":76},"It uses Long Short-Term Memory (LSTM) networks, including a univariate LSTM model and a multivariate LSTM model that incorporates engineered features.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the dataset prepared for training?",{"text":84,"@type":76},"The study performs comprehensive data analysis for preparation and applies feature engineering to add relevant contextual variables such as weekday, temperature, and household occupancy.","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"]