Loading…
Total and thermal load forecasting in residential communities through probabilistic methods and causal machine learning
Indoor heating and cooling systems largely influence the power demand of residential buildings and can play a significant role in the Demand Side Management for energy communities. We propose a novel method for probabilistic forecasting of the total load of a residential community and its base and t...
Saved in:
Published in: | Applied energy 2023-12, Vol.351, p.121783, Article 121783 |
---|---|
Main Authors: | , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c360t-31e451c32a84386b0d72b49a955422a1ed5b788ee658028d8fff42146774ada3 |
---|---|
cites | cdi_FETCH-LOGICAL-c360t-31e451c32a84386b0d72b49a955422a1ed5b788ee658028d8fff42146774ada3 |
container_end_page | |
container_issue | |
container_start_page | 121783 |
container_title | Applied energy |
container_volume | 351 |
creator | Massidda, Luca Marrocu, Marino |
description | Indoor heating and cooling systems largely influence the power demand of residential buildings and can play a significant role in the Demand Side Management for energy communities. We propose a novel method for probabilistic forecasting of the total load of a residential community and its base and thermal components, combining conformalized quantile regression and causal machine learning techniques, using only aggregate consumption and environmental conditions data. We applied the proposed methods to the dataset of a residential community in Germany, which includes separate measurements of the total electricity demand and of domestic heating system consumption. The results show that the proposed method produces probabilistic day-ahead hourly forecasts of total energy demand that outperform benchmarks and forecasts of electricity consumption components that are not only more accurate than benchmarks but also close to the accuracy achievable with models trained directly on individual load component data. The T-learner method resulted the most effective among the causal methods for load disaggregation in terms of accuracy, simplicity, and potential for extension.
•Conformalized quantile regression is proposed for day-ahead load forecasting.•Thermal load component is separated using causal machine learning approches.•The methodology is tested on the energy demand forecast of a residential community.•The T-learner method resulted as the most effective CausalML approach for the task. |
doi_str_mv | 10.1016/j.apenergy.2023.121783 |
format | article |
fullrecord | <record><control><sourceid>elsevier_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1016_j_apenergy_2023_121783</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0306261923011479</els_id><sourcerecordid>S0306261923011479</sourcerecordid><originalsourceid>FETCH-LOGICAL-c360t-31e451c32a84386b0d72b49a955422a1ed5b788ee658028d8fff42146774ada3</originalsourceid><addsrcrecordid>eNqFkMlqwzAQQHVooenyC0U_YFeLLSu3ltANAr3kLmRpHCvYUpCUlvx9laY99zQDw3sMD6F7SmpKqHjY1XoPHuL2WDPCeE0Z7SS_QAvCiaiYoMsrdJ3SjhDCKCML9LUJWU9Ye4vzCHEu-xS0xUOIYHTKzm-x8zhCchZ8duVuwjwfvMsOUmFiOGxHvI-h172bXCEMniGPwaYfq9GHVKBZm9F5wBPo6Iv0Fl0Oekpw9ztv0OblebN6q9Yfr--rp3VluCC54hSalhrOtGy4FD2xHeubpV62bcOYpmDbvpMSQLSSMGnlMAwNo43oukZbzW-QOGtNDClFGNQ-ulnHo6JEnYqpnforpk7F1LlYAR_PIJTnPh1ElYwDb8C6EiYrG9x_im8Rd3z-</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Total and thermal load forecasting in residential communities through probabilistic methods and causal machine learning</title><source>ScienceDirect Freedom Collection</source><creator>Massidda, Luca ; Marrocu, Marino</creator><creatorcontrib>Massidda, Luca ; Marrocu, Marino</creatorcontrib><description>Indoor heating and cooling systems largely influence the power demand of residential buildings and can play a significant role in the Demand Side Management for energy communities. We propose a novel method for probabilistic forecasting of the total load of a residential community and its base and thermal components, combining conformalized quantile regression and causal machine learning techniques, using only aggregate consumption and environmental conditions data. We applied the proposed methods to the dataset of a residential community in Germany, which includes separate measurements of the total electricity demand and of domestic heating system consumption. The results show that the proposed method produces probabilistic day-ahead hourly forecasts of total energy demand that outperform benchmarks and forecasts of electricity consumption components that are not only more accurate than benchmarks but also close to the accuracy achievable with models trained directly on individual load component data. The T-learner method resulted the most effective among the causal methods for load disaggregation in terms of accuracy, simplicity, and potential for extension.
•Conformalized quantile regression is proposed for day-ahead load forecasting.•Thermal load component is separated using causal machine learning approches.•The methodology is tested on the energy demand forecast of a residential community.•The T-learner method resulted as the most effective CausalML approach for the task.</description><identifier>ISSN: 0306-2619</identifier><identifier>DOI: 10.1016/j.apenergy.2023.121783</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Causal machine learning ; Conformalized quantile regression ; Electric load forecasting ; HVAC ; Load disaggregation ; Thermal load</subject><ispartof>Applied energy, 2023-12, Vol.351, p.121783, Article 121783</ispartof><rights>2023 The Authors</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c360t-31e451c32a84386b0d72b49a955422a1ed5b788ee658028d8fff42146774ada3</citedby><cites>FETCH-LOGICAL-c360t-31e451c32a84386b0d72b49a955422a1ed5b788ee658028d8fff42146774ada3</cites><orcidid>0000-0003-2515-0833 ; 0000-0002-3561-4788</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Massidda, Luca</creatorcontrib><creatorcontrib>Marrocu, Marino</creatorcontrib><title>Total and thermal load forecasting in residential communities through probabilistic methods and causal machine learning</title><title>Applied energy</title><description>Indoor heating and cooling systems largely influence the power demand of residential buildings and can play a significant role in the Demand Side Management for energy communities. We propose a novel method for probabilistic forecasting of the total load of a residential community and its base and thermal components, combining conformalized quantile regression and causal machine learning techniques, using only aggregate consumption and environmental conditions data. We applied the proposed methods to the dataset of a residential community in Germany, which includes separate measurements of the total electricity demand and of domestic heating system consumption. The results show that the proposed method produces probabilistic day-ahead hourly forecasts of total energy demand that outperform benchmarks and forecasts of electricity consumption components that are not only more accurate than benchmarks but also close to the accuracy achievable with models trained directly on individual load component data. The T-learner method resulted the most effective among the causal methods for load disaggregation in terms of accuracy, simplicity, and potential for extension.
•Conformalized quantile regression is proposed for day-ahead load forecasting.•Thermal load component is separated using causal machine learning approches.•The methodology is tested on the energy demand forecast of a residential community.•The T-learner method resulted as the most effective CausalML approach for the task.</description><subject>Causal machine learning</subject><subject>Conformalized quantile regression</subject><subject>Electric load forecasting</subject><subject>HVAC</subject><subject>Load disaggregation</subject><subject>Thermal load</subject><issn>0306-2619</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNqFkMlqwzAQQHVooenyC0U_YFeLLSu3ltANAr3kLmRpHCvYUpCUlvx9laY99zQDw3sMD6F7SmpKqHjY1XoPHuL2WDPCeE0Z7SS_QAvCiaiYoMsrdJ3SjhDCKCML9LUJWU9Ye4vzCHEu-xS0xUOIYHTKzm-x8zhCchZ8duVuwjwfvMsOUmFiOGxHvI-h172bXCEMniGPwaYfq9GHVKBZm9F5wBPo6Iv0Fl0Oekpw9ztv0OblebN6q9Yfr--rp3VluCC54hSalhrOtGy4FD2xHeubpV62bcOYpmDbvpMSQLSSMGnlMAwNo43oukZbzW-QOGtNDClFGNQ-ulnHo6JEnYqpnforpk7F1LlYAR_PIJTnPh1ElYwDb8C6EiYrG9x_im8Rd3z-</recordid><startdate>20231201</startdate><enddate>20231201</enddate><creator>Massidda, Luca</creator><creator>Marrocu, Marino</creator><general>Elsevier Ltd</general><scope>6I.</scope><scope>AAFTH</scope><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0003-2515-0833</orcidid><orcidid>https://orcid.org/0000-0002-3561-4788</orcidid></search><sort><creationdate>20231201</creationdate><title>Total and thermal load forecasting in residential communities through probabilistic methods and causal machine learning</title><author>Massidda, Luca ; Marrocu, Marino</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c360t-31e451c32a84386b0d72b49a955422a1ed5b788ee658028d8fff42146774ada3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Causal machine learning</topic><topic>Conformalized quantile regression</topic><topic>Electric load forecasting</topic><topic>HVAC</topic><topic>Load disaggregation</topic><topic>Thermal load</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Massidda, Luca</creatorcontrib><creatorcontrib>Marrocu, Marino</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>CrossRef</collection><jtitle>Applied energy</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Massidda, Luca</au><au>Marrocu, Marino</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Total and thermal load forecasting in residential communities through probabilistic methods and causal machine learning</atitle><jtitle>Applied energy</jtitle><date>2023-12-01</date><risdate>2023</risdate><volume>351</volume><spage>121783</spage><pages>121783-</pages><artnum>121783</artnum><issn>0306-2619</issn><abstract>Indoor heating and cooling systems largely influence the power demand of residential buildings and can play a significant role in the Demand Side Management for energy communities. We propose a novel method for probabilistic forecasting of the total load of a residential community and its base and thermal components, combining conformalized quantile regression and causal machine learning techniques, using only aggregate consumption and environmental conditions data. We applied the proposed methods to the dataset of a residential community in Germany, which includes separate measurements of the total electricity demand and of domestic heating system consumption. The results show that the proposed method produces probabilistic day-ahead hourly forecasts of total energy demand that outperform benchmarks and forecasts of electricity consumption components that are not only more accurate than benchmarks but also close to the accuracy achievable with models trained directly on individual load component data. The T-learner method resulted the most effective among the causal methods for load disaggregation in terms of accuracy, simplicity, and potential for extension.
•Conformalized quantile regression is proposed for day-ahead load forecasting.•Thermal load component is separated using causal machine learning approches.•The methodology is tested on the energy demand forecast of a residential community.•The T-learner method resulted as the most effective CausalML approach for the task.</abstract><pub>Elsevier Ltd</pub><doi>10.1016/j.apenergy.2023.121783</doi><orcidid>https://orcid.org/0000-0003-2515-0833</orcidid><orcidid>https://orcid.org/0000-0002-3561-4788</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0306-2619 |
ispartof | Applied energy, 2023-12, Vol.351, p.121783, Article 121783 |
issn | 0306-2619 |
language | eng |
recordid | cdi_crossref_primary_10_1016_j_apenergy_2023_121783 |
source | ScienceDirect Freedom Collection |
subjects | Causal machine learning Conformalized quantile regression Electric load forecasting HVAC Load disaggregation Thermal load |
title | Total and thermal load forecasting in residential communities through probabilistic methods and causal machine learning |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T14%3A19%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Total%20and%20thermal%20load%20forecasting%20in%20residential%20communities%20through%20probabilistic%20methods%20and%20causal%20machine%20learning&rft.jtitle=Applied%20energy&rft.au=Massidda,%20Luca&rft.date=2023-12-01&rft.volume=351&rft.spage=121783&rft.pages=121783-&rft.artnum=121783&rft.issn=0306-2619&rft_id=info:doi/10.1016/j.apenergy.2023.121783&rft_dat=%3Celsevier_cross%3ES0306261923011479%3C/elsevier_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c360t-31e451c32a84386b0d72b49a955422a1ed5b788ee658028d8fff42146774ada3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |