[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123385-en":3,"doc-seo-123385-105":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},123385,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Machine Learning and Statistical Approaches for Forecasting Electricity Demand in Vaasa - Master’s Thesis","Electricity is essential to modern life, yet stable supply is increasingly pressured by shifting consumption patterns, climate variability, and the growing integration of renewable energy. This Master’s thesis develops tailored short- and long-term forecasting models for Vaasa, Finland, aiming to support grid stability. Using Vaasa-specific historical electricity and weather data, it applies preprocessing, feature engineering, and iterative model development.","Dinesh Karunarathne  \nMACHINE LEARNING AND STATISTICAL APPROACHES FOR FORECASTING ELECTRICITY DEMAND IN VAASA  \nInformation Technology 2025  \nACKNOWLEDGEMENT  \nI would like to express my sincere gratitude to the many individuals who have helped and supported me in numerous ways throughout the journey of this Master's thesis. Their guidance, assistance, and encouragement have been invaluable to the successful completion of this research.  \nFirst and foremost, I am deeply indebted to my supervisor, Dr. Ghodrat Moghadampour, Principal Lecturer at VAMK, for his insightful guidance, unwavering support, and constant encouragement throughout my study. His expertise and constructive feedback were instrumental in shaping this research.  \nI am also very grateful for the crucial assistance I received in gathering the necessary data for this project. I would like to extend my thanks to Tiia Haapakoski of Statistics Finland for her helpful guidance in navigating data collection processes. My appreciation also goes to Hanna Nurmilo of Fingrid Oyj for her valuable direction in obtaining relevant data. Furthermore, I wish to sincerely thank Mari Böling and Jaakko Yliaho of Vaasan Sähkö, who were instrumental in providing the historical hourly electricity consumption data for Vaasa, which formed the backbone of this study.  \nThe completion of this thesis would not have been possible without the contributions of these individuals.  \nDinesh Karunarathne Vaasa, Finland May 26, 2025  \nVAASAN AMMATTIKORKEAKOULU UNIVERSITY OF APPLIED SCIENCES  \nMasters in Cloud-Based Software Engineering  \nABSTRACT  \nAuthor Dinesh Karunarathne  \nTitle Machine Learning and Statistical Approaches for Forecasting  \nElectricity Demand in Vaasa  \nYear 2025  \nLanguage English Pages 86  \nSupervisor Dr. Ghodrat Moghadampour  \nElectricity is vital to modern life, but stable supply is increasingly challenged by changing consumption patterns, climate variability, and renewable integration. This research focuses on forecasting electricity demand in Vaasa, Finland, a regional energy hub. Tailored short and long-term prediction models were developed to address grid stability challenges driven by factors such as climate variability.  \nThe study utilized established load forecasting literature, comparing traditional statistical models against machine learning techniques and identifying key demand drivers. A quantitative methodology was employed using historical Vaasa-specific data, including electricity consumption and weather information. This involved comprehensive data acquisition, preprocessing, feature engineering (such as deriving'Is_workday' and 'Sun_Flag' variables), and the iterative development and evaluation of Multiple Linear Regression (MLR), Random Forest, and XGBoost models for monthly, daily, and hourly forecasts, using metrics like R2 and MAPE.  \nThe results demonstrated strong predictive capabilities, with an MLR model using temperature variables proving best for monthly forecasts with R2 =96 . 3%(Table 6) . For daily forecasts, MLR outperformed the tested machine learning models with R2 =92 .8%(Table 7) . In hourly forecasting, XGBoost achieved a marginally better R2 =90. 2%(Table 17), closely followed by MLR with R2 =90 . 1% . Temperature and various temporal features were consistently the most dominant demand drivers. The study concludes that for Vaasa's context, well-specified multiple linear models can be highly effective, offering valuable and interpretable tools for local energy management and strategic planning.  \nKeywords electricity demand forecasting, machine learning, multiple linear regression, short-term load forecasting, long-term forecasting  \nCONTENTS  \nACKNOWLEDGEMENT.................................................................. I  \nABSTRACT ............................................................................... II  \n1 INTRODUCTION .................................................................... 1  \n1.1 Background ................","cbCaicK5oUckaoLH","https://ap.wps.com/l/cbCaicK5oUckaoLH","pdf",3762338,1,99,"English","en",105,"# Acknowledgement\n# Abstract\n# Introduction\n## Background\n## Motivations\n## Objectives\n## Method\n## Limitations\n# Literature Review\n# Data Collection and Preparation\n## Data Sources and Variables\n## Data Preparation and Feature Engineering\n# Feature Selection Analysis\n## Time Series Analysis\n## Relationship with Categorical Features\n## Relationship with Continuous Features\n## Statistical Significance Testing\n## Summary of Feature Selection\n# Long-Term Forecasting\n## Model Fitting using Multiple Linear Regression Approach\n## Residual Analysis of the Selected Multiple Linear Regression Model\n## Interpreting the Selected Multiple Linear Regression Model\n## Model Performance and Forecast Visualization\n# Short-Term (Daily) Load Forecasting\n## Daily Electricity Demand Forecasting – Multiple Linear Regression Approach","[{\"question\":\"What forecasting problem does the thesis address for Vaasa?\",\"answer\":\"It targets forecasting electricity demand in Vaasa, Finland, with the goal of improving grid stability under changing consumption patterns and climate variability.\"},{\"question\":\"Which data and preprocessing steps are used to build the forecasting models?\",\"answer\":\"The study uses historical Vaasa-specific electricity consumption and weather information, followed by data acquisition, preprocessing, and feature engineering such as workday and sun-related flags.\"},{\"question\":\"How do the models perform across monthly, daily, and hourly horizons?\",\"answer\":\"For monthly forecasts, Multiple Linear Regression (MLR) using temperature variables performs best (R² about 96.3%). For daily forecasts, MLR outperforms the tested machine learning methods (R² about 92.8%), while hourly forecasting is best by XGBoost (R² about 90.2%) with MLR close behind.\"}]","Machine Learning and Statistical Approaches for Forecasting Electricity Demand in Vaasa - Master’s Thesis | PDF",1785816223,249,{"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},"machine-learning-and-statistical-approaches-for-forecasting-electricity-demand-in-vaasa-masters-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/machine-learning-and-statistical-approaches-for-forecasting-electricity-demand-in-vaasa-masters-thesis/123385/",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 forecasting problem does the thesis address for Vaasa?","Question",{"text":75,"@type":76},"It targets forecasting electricity demand in Vaasa, Finland, with the goal of improving grid stability under changing consumption patterns and climate variability.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which data and preprocessing steps are used to build the forecasting models?",{"text":80,"@type":76},"The study uses historical Vaasa-specific electricity consumption and weather information, followed by data acquisition, preprocessing, and feature engineering such as workday and sun-related flags.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the models perform across monthly, daily, and hourly horizons?",{"text":84,"@type":76},"For monthly forecasts, Multiple Linear Regression (MLR) using temperature variables performs best (R² about 96.3%). For daily forecasts, MLR outperforms the tested machine learning methods (R² about 92.8%), while hourly forecasting is best by XGBoost (R² about 90.2%) with MLR close behind.","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"]