[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119094-en":3,"doc-seo-119094-105":30,"detail-sidebar-cat-0-en-105":96},{"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},119094,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Customer Energy Flexibility Forecasting with Different Machine Learning Models - Master’s thesis","Modern power systems shift toward intelligent, flexible, and interactive operation to support higher shares of renewable generation, making energy flexibility a key enabler. This master’s thesis examines demand-response-based flexibility of consumers across different timescales and highlights how accurate individual load forecasting supports future grid planning and operation. The study identifies the most flexible consumer among seven and compares 11 machine learning models, including RNN, GRU, LSTM, gradient boosting, and linear regression, using RMSE to assess forecasting accuracy. It further estimates household flexibility to adjust consumption with price changes and proposes a three-data strategy for customer profit maximization and flexibility services such as congestion management and peak shaving.","Fatama Sultana Liza  \nCustomer Energy Flexibility Forecasting with Different Machine Learning Models  \nSchool of Technology and Innovations Master’s thesis in Smart Energy Programme  \nUNIVERSITY OF VAASA  \nSchool of Technology and Innovations  \nAuthor: Fatama Sultana Liza  \nTitle of the thesis: Customer Energy Flexibility Forecasting with Different Machine  \nLearning Models  \nDegree: Master of Science in Technology  \nDiscipline: Smart Energy  \nSupervisor: Hannu Laaksonen  \nCo-supervisor: Hosna khajeh  \nYear: 2024 Pages: 122  \nABSTRACT :  \nMost concerns about the sustainability of modern society are centred around energy issues. To address these, the power system is transitioning towards a more intelligent, flexible, and interactive system with higher penetration of renewable energy generation. A key enabler of this transition is energy flexibility, which focuses on the demand response of consumers at different times. It is the traceability of the energy flow among individual energy consumers. This master’s thesis focuses on the demand response-based flexibility of the consumers at different timescales. Accurate load forecasting of individual customers is increasingly vital for future grid planning and operation. The main objective of this thesis was to identify the most flexible consumer among seven consumers and to identify the most effective machine learning (ML) model for forecasting energy flexibility across time horizons and time scales. This study investigates how different machine learning models—such as recurrent neural networks (RNN), gradient boosting, linear regression, and long short-term memory (LSTM)—can be used in the energy forecasting process. This study utilised a total of 11 distinct machine learning models. The experimental findings clearly demonstrate that the proposed model is superior to the others in terms of accuracy in predicting consumption, as measured by the root mean square error (RMSE) .  \nIn addition, the model also evaluates the degree of flexibility of these households to adjust or reduce energy consumption in response to price fluctuations. This study proposes the implementation of a three-data model strategy to effectively manage load flexibility forecasting (Customer profit maximization) . This technique aims to provide flexibility services, like congestion management, peak shaving to the local distribution system operator (DSO) and integrate renewable energy sources by leveraging several features like advance forecasting and analytics, demand response.  \nKEYWORDS: Machine Learning, Energy flexibility, Demand response, Forecasting.  \nAcknowledgments  \nThis master’s thesis was conducted at the University of Vaasa in the frame of the Smart Energy Programme. I wish to express my sincere gratitude to all the people who have supported me during realization of this thesis.  \nIn the first instance, it is my pleasure to thank my thesis supervisor, Professor Hannu Laaksonen, for the opportunity to be associated with him. His suggestions and encouragement are irreplaceable; hence, I would not have been able to finish this thesis on my own. I would also like to thank my co-supervisor, Hosna Khajeh, for her endless support as well as her remarks on the work and her suggestions in this work.  \nI also want to accord my gratitude to the University of Vaasa´s Smart Grid 2.0 project, which voluntarily offered their data for this research. These were essential for the achievement of this research and they played a huge role.  \nMoreover, it is important to express my gratitude to the members of my family and friends for their contributions to completing this thesis and conducting all the research. They helped me make sense of whatever I have been through and to endure it. I want to dedicate this thesis to my parents, Firaoj Alam and Shahanara Begum. They are the reason I have achieved this milestone and their sweet words inspired me when I was down.  \nFinally, the successful outcomes of this work can be attri","cbCaifJwFmiZSlk4","https://ap.wps.com/l/cbCaifJwFmiZSlk4","pdf",3389965,1,122,"English","en",105,"# Introduction\n## Background and motivation\n## Problem statement\n## Research objectives\n## Thesis outlines\n## Significance of the study\n# Forecasting and demand response in energy sector\n## Energy flexibility: definition and concepts\n## Demand response programs and flexibility\n# Machine learning modelling techniques\n## Linear regression technique\n### Linear Regression\n### Poly linear regression\n## Ensemble learning\n### Gradient Boosting Regressor (GBR)\n## Neural network architecture\n### Recurrent Neural Network (RNN)\n### Gated recurrent units (GRU)\n### Long short-term memory (LSTM)\n# Statistical measurement for consumption\n## Correlation coefficient\n### Pearson correlation coefficient\n### Spearman’s correlation coefficient\n## Correlations between consumption, price, and temperature\n### Relationship between consumption and day-ahead price (EUR/MWH)\n### Relationship between consumption and air temperature (deg C)\n## Insights into house flexibility\n## Reasons behind varying degrees of flexibility\n# Flexibility forecast and different time horizons\n## Data manipulation\n## Analysis of model flexibility\n### Flexibility calculation for recurrent neural network (RNN)\n### Flexibility calculation for gated recurrent unit (GRU)\n### Flexibility calculation for long short-term memory (LSTM)\n## Analysis and interpretation\n### Comparison of models\n# Methodology\n## Data collection and description\n## Exploratory data analysis (EDA)\n### Autocorrelation analysis\n### Correlation analysis\n### Scatter plots\n## Forecasting methodology\n### Data Pre-processing","[{\"question\":\"What is the main goal of the thesis?\",\"answer\":\"The thesis aims to identify the most flexible consumer among seven and determine the most effective machine learning model for forecasting energy flexibility across different time horizons and timescales.\"},{\"question\":\"Which machine learning models are compared for forecasting?\",\"answer\":\"The study evaluates 11 machine learning models, including recurrent neural networks (RNN), gradient boosting, linear regression, and long short-term memory (LSTM) (and related recurrent variants such as GRU).\"},{\"question\":\"How is forecasting accuracy measured in the experiments?\",\"answer\":\"Accuracy is assessed using root mean square error (RMSE), with the proposed model showing superior prediction performance compared with the other models.\"},{\"question\":\"How does the thesis use forecasting to support flexibility services?\",\"answer\":\"It proposes a three-data model strategy to manage load flexibility forecasting and quantify household flexibility for services such as congestion management, peak shaving, and integrating renewable energy using features like advance forecasting and demand response.\"}]","Customer Energy Flexibility Forecasting with Different Machine Learning Models - Master’s thesis | PDF",1785722332,307,{"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":91,"head_meta":93,"extra_data":95,"updated_unix":28},"customer-energy-flexibility-forecasting-with-different-machine-learning-models-masters-thesis","",{"@graph":36,"@context":90},[37,54,69],{"@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/customer-energy-flexibility-forecasting-with-different-machine-learning-models-masters-thesis/119094/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82,86],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main goal of the thesis?","Question",{"text":76,"@type":77},"The thesis aims to identify the most flexible consumer among seven and determine the most effective machine learning model for forecasting energy flexibility across different time horizons and timescales.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which machine learning models are compared for forecasting?",{"text":81,"@type":77},"The study evaluates 11 machine learning models, including recurrent neural networks (RNN), gradient boosting, linear regression, and long short-term memory (LSTM) (and related recurrent variants such as GRU).",{"name":83,"@type":74,"acceptedAnswer":84},"How is forecasting accuracy measured in the experiments?",{"text":85,"@type":77},"Accuracy is assessed using root mean square error (RMSE), with the proposed model showing superior prediction performance compared with the other models.",{"name":87,"@type":74,"acceptedAnswer":88},"How does the thesis use forecasting to support flexibility services?",{"text":89,"@type":77},"It proposes a three-data model strategy to manage load flexibility forecasting and quantify household flexibility for services such as congestion management, peak shaving, and integrating renewable energy using features like advance forecasting and demand response.","https://schema.org",{"og:url":52,"og:type":92,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":94,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":97},[98,102,106,110,115,120,125,128,133,136,140],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Exam",70,"exam",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},5,"Comic",60,"comic",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},6,"Technology",50,"technology",{"id":121,"doc_module":4,"doc_module_name":46,"category_name":122,"show_sort_weight":123,"slug":124},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":126,"slug":127},30,"research-report",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":131,"slug":132},9,"Religion & Spirituality",20,"religion-spirituality",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":131,"slug":135},"World Cup","world-cup",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":137,"slug":139},10,"Lifestyle","lifestyle",{"id":141,"doc_module":4,"doc_module_name":46,"category_name":142,"show_sort_weight":111,"slug":143},19,"General","general"]