Data-Driven Predictions of Heating Energy Savings in Residential Buildings
Along with the increasing use of intermittent electricity sources, such as wind and sun, comes a growing demand for user flexibility. This has paved the way for a new market of services that provide electricity customers with energy saving solutions. These include a variety of techniques ranging fro...
Main Authors: | , |
---|---|
Format: | Others |
Language: | English |
Published: |
Uppsala universitet, Byggteknik
2019
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-387395 |
id |
ndltd-UPSALLA1-oai-DiVA.org-uu-387395 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-UPSALLA1-oai-DiVA.org-uu-3873952019-06-25T09:10:44ZData-Driven Predictions of Heating Energy Savings in Residential BuildingsengLindblom, EllenAlmquist, IsabelleUppsala universitet, ByggteknikUppsala universitet, Byggteknik2019Building EnergyMachine LearningEnergy SavingsHeating EnergyIndoor TemperatureNeural NetworksSupport Vector RegressionRandom ForestRidge RegressionK-Nearest NeighborsEnergy SystemsEnergisystemComputer and Information SciencesData- och informationsvetenskapAlong with the increasing use of intermittent electricity sources, such as wind and sun, comes a growing demand for user flexibility. This has paved the way for a new market of services that provide electricity customers with energy saving solutions. These include a variety of techniques ranging from sophisticated control of the customers’ home equipment to information on how to adjust their consumption behavior in order to save energy. This master thesis work contributes further to this field by investigating an additional incentive; predictions of future energy savings related to indoor temperature. Five different machine learning models have been tuned and used to predict monthly heating energy consumption for a given set of homes. The model tuning process and performance evaluation were performed using 10-fold cross validation. The best performing model was then used to predict how much heating energy each individual household could save by decreasing their indoor temperature by 1°C during the heating season. The highest prediction accuracy (of about 78%) is achieved with support vector regression (SVR), closely followed by neural networks (NN). The simpler regression models that have been implemented are, however, not far behind. According to the SVR model, the average household is expected to lower their heating energy consumption by approximately 3% if the indoor temperature is decreased by 1°C. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-387395UPTEC STS, 1650-8319 ; 19027application/pdfinfo:eu-repo/semantics/openAccess |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
Building Energy Machine Learning Energy Savings Heating Energy Indoor Temperature Neural Networks Support Vector Regression Random Forest Ridge Regression K-Nearest Neighbors Energy Systems Energisystem Computer and Information Sciences Data- och informationsvetenskap |
spellingShingle |
Building Energy Machine Learning Energy Savings Heating Energy Indoor Temperature Neural Networks Support Vector Regression Random Forest Ridge Regression K-Nearest Neighbors Energy Systems Energisystem Computer and Information Sciences Data- och informationsvetenskap Lindblom, Ellen Almquist, Isabelle Data-Driven Predictions of Heating Energy Savings in Residential Buildings |
description |
Along with the increasing use of intermittent electricity sources, such as wind and sun, comes a growing demand for user flexibility. This has paved the way for a new market of services that provide electricity customers with energy saving solutions. These include a variety of techniques ranging from sophisticated control of the customers’ home equipment to information on how to adjust their consumption behavior in order to save energy. This master thesis work contributes further to this field by investigating an additional incentive; predictions of future energy savings related to indoor temperature. Five different machine learning models have been tuned and used to predict monthly heating energy consumption for a given set of homes. The model tuning process and performance evaluation were performed using 10-fold cross validation. The best performing model was then used to predict how much heating energy each individual household could save by decreasing their indoor temperature by 1°C during the heating season. The highest prediction accuracy (of about 78%) is achieved with support vector regression (SVR), closely followed by neural networks (NN). The simpler regression models that have been implemented are, however, not far behind. According to the SVR model, the average household is expected to lower their heating energy consumption by approximately 3% if the indoor temperature is decreased by 1°C. |
author |
Lindblom, Ellen Almquist, Isabelle |
author_facet |
Lindblom, Ellen Almquist, Isabelle |
author_sort |
Lindblom, Ellen |
title |
Data-Driven Predictions of Heating Energy Savings in Residential Buildings |
title_short |
Data-Driven Predictions of Heating Energy Savings in Residential Buildings |
title_full |
Data-Driven Predictions of Heating Energy Savings in Residential Buildings |
title_fullStr |
Data-Driven Predictions of Heating Energy Savings in Residential Buildings |
title_full_unstemmed |
Data-Driven Predictions of Heating Energy Savings in Residential Buildings |
title_sort |
data-driven predictions of heating energy savings in residential buildings |
publisher |
Uppsala universitet, Byggteknik |
publishDate |
2019 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-387395 |
work_keys_str_mv |
AT lindblomellen datadrivenpredictionsofheatingenergysavingsinresidentialbuildings AT almquistisabelle datadrivenpredictionsofheatingenergysavingsinresidentialbuildings |
_version_ |
1719209276512141312 |