A Modified Sequence-to-point HVAC Load Disaggregation Algorithm

This paper presents a modified sequence-to-point (S2P) algorithm for disaggregating the heat, ventilation, and air conditioning (HVAC) load from the total building electricity consumption. The original S2P model is convolutional neural network (CNN) based, which uses load profiles as inputs. We prop...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ye, Kai, Kim, Hyeonjin, Hu, Yi, Lu, Ning, Wu, Di, Rehm, PJ
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Ye, Kai
Kim, Hyeonjin
Hu, Yi
Lu, Ning
Wu, Di
Rehm, PJ
description This paper presents a modified sequence-to-point (S2P) algorithm for disaggregating the heat, ventilation, and air conditioning (HVAC) load from the total building electricity consumption. The original S2P model is convolutional neural network (CNN) based, which uses load profiles as inputs. We propose three modifications. First, the input convolution layer is changed from 1D to 2D so that normalized temperature profiles are also used as inputs to the S2P model. Second, a drop-out layer is added to improve adaptability and generalizability so that the model trained in one area can be transferred to other geographical areas without labelled HVAC data. Third, a fine-tuning process is proposed for areas with a small amount of labelled HVAC data so that the pre-trained S2P model can be fine-tuned to achieve higher disaggregation accuracy (i.e., better transferability) in other areas. The model is first trained and tested using smart meter and sub-metered HVAC data collected in Austin, Texas. Then, the trained model is tested on two other areas: Boulder, Colorado and San Diego, California. Simulation results show that the proposed modified S2P algorithm outperforms the original S2P model and the support-vector machine based approach in accuracy, adaptability, and transferability.
doi_str_mv 10.48550/arxiv.2212.04886
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2212_04886</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2212_04886</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-16c711776c5eefdefc95b867737111a2aebdf4c0c0bd737aa1f60c6193518a833</originalsourceid><addsrcrecordid>eNotz71OwzAYhWEvHVDLBTDhG3Bqx_FPJxSFnyIFMVCxRl_sz8FSG7duQHD3lJbpSO9wpIeQG8GLyirFl5C_41dRlqIseGWtviJ3NX1JPoaInr7h4RNHh2xKbJ_iONH1e93QNoGn9_EIw5BxgCmmkdbbIeU4fewWZBZge8Tr_52TzePDplmz9vXpualbBtpoJrQzQhijnUIMHoNbqd5qY-QpCygBex8qxx3v_akBiKC502IllbBgpZyT28vtWdDtc9xB_un-JN1ZIn8BLvFCqg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Modified Sequence-to-point HVAC Load Disaggregation Algorithm</title><source>arXiv.org</source><creator>Ye, Kai ; Kim, Hyeonjin ; Hu, Yi ; Lu, Ning ; Wu, Di ; Rehm, PJ</creator><creatorcontrib>Ye, Kai ; Kim, Hyeonjin ; Hu, Yi ; Lu, Ning ; Wu, Di ; Rehm, PJ</creatorcontrib><description>This paper presents a modified sequence-to-point (S2P) algorithm for disaggregating the heat, ventilation, and air conditioning (HVAC) load from the total building electricity consumption. The original S2P model is convolutional neural network (CNN) based, which uses load profiles as inputs. We propose three modifications. First, the input convolution layer is changed from 1D to 2D so that normalized temperature profiles are also used as inputs to the S2P model. Second, a drop-out layer is added to improve adaptability and generalizability so that the model trained in one area can be transferred to other geographical areas without labelled HVAC data. Third, a fine-tuning process is proposed for areas with a small amount of labelled HVAC data so that the pre-trained S2P model can be fine-tuned to achieve higher disaggregation accuracy (i.e., better transferability) in other areas. The model is first trained and tested using smart meter and sub-metered HVAC data collected in Austin, Texas. Then, the trained model is tested on two other areas: Boulder, Colorado and San Diego, California. Simulation results show that the proposed modified S2P algorithm outperforms the original S2P model and the support-vector machine based approach in accuracy, adaptability, and transferability.</description><identifier>DOI: 10.48550/arxiv.2212.04886</identifier><language>eng</language><subject>Computer Science - Systems and Control</subject><creationdate>2022-12</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2212.04886$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2212.04886$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Ye, Kai</creatorcontrib><creatorcontrib>Kim, Hyeonjin</creatorcontrib><creatorcontrib>Hu, Yi</creatorcontrib><creatorcontrib>Lu, Ning</creatorcontrib><creatorcontrib>Wu, Di</creatorcontrib><creatorcontrib>Rehm, PJ</creatorcontrib><title>A Modified Sequence-to-point HVAC Load Disaggregation Algorithm</title><description>This paper presents a modified sequence-to-point (S2P) algorithm for disaggregating the heat, ventilation, and air conditioning (HVAC) load from the total building electricity consumption. The original S2P model is convolutional neural network (CNN) based, which uses load profiles as inputs. We propose three modifications. First, the input convolution layer is changed from 1D to 2D so that normalized temperature profiles are also used as inputs to the S2P model. Second, a drop-out layer is added to improve adaptability and generalizability so that the model trained in one area can be transferred to other geographical areas without labelled HVAC data. Third, a fine-tuning process is proposed for areas with a small amount of labelled HVAC data so that the pre-trained S2P model can be fine-tuned to achieve higher disaggregation accuracy (i.e., better transferability) in other areas. The model is first trained and tested using smart meter and sub-metered HVAC data collected in Austin, Texas. Then, the trained model is tested on two other areas: Boulder, Colorado and San Diego, California. Simulation results show that the proposed modified S2P algorithm outperforms the original S2P model and the support-vector machine based approach in accuracy, adaptability, and transferability.</description><subject>Computer Science - Systems and Control</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAYhWEvHVDLBTDhG3Bqx_FPJxSFnyIFMVCxRl_sz8FSG7duQHD3lJbpSO9wpIeQG8GLyirFl5C_41dRlqIseGWtviJ3NX1JPoaInr7h4RNHh2xKbJ_iONH1e93QNoGn9_EIw5BxgCmmkdbbIeU4fewWZBZge8Tr_52TzePDplmz9vXpualbBtpoJrQzQhijnUIMHoNbqd5qY-QpCygBex8qxx3v_akBiKC502IllbBgpZyT28vtWdDtc9xB_un-JN1ZIn8BLvFCqg</recordid><startdate>20221209</startdate><enddate>20221209</enddate><creator>Ye, Kai</creator><creator>Kim, Hyeonjin</creator><creator>Hu, Yi</creator><creator>Lu, Ning</creator><creator>Wu, Di</creator><creator>Rehm, PJ</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20221209</creationdate><title>A Modified Sequence-to-point HVAC Load Disaggregation Algorithm</title><author>Ye, Kai ; Kim, Hyeonjin ; Hu, Yi ; Lu, Ning ; Wu, Di ; Rehm, PJ</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-16c711776c5eefdefc95b867737111a2aebdf4c0c0bd737aa1f60c6193518a833</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Systems and Control</topic><toplevel>online_resources</toplevel><creatorcontrib>Ye, Kai</creatorcontrib><creatorcontrib>Kim, Hyeonjin</creatorcontrib><creatorcontrib>Hu, Yi</creatorcontrib><creatorcontrib>Lu, Ning</creatorcontrib><creatorcontrib>Wu, Di</creatorcontrib><creatorcontrib>Rehm, PJ</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ye, Kai</au><au>Kim, Hyeonjin</au><au>Hu, Yi</au><au>Lu, Ning</au><au>Wu, Di</au><au>Rehm, PJ</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Modified Sequence-to-point HVAC Load Disaggregation Algorithm</atitle><date>2022-12-09</date><risdate>2022</risdate><abstract>This paper presents a modified sequence-to-point (S2P) algorithm for disaggregating the heat, ventilation, and air conditioning (HVAC) load from the total building electricity consumption. The original S2P model is convolutional neural network (CNN) based, which uses load profiles as inputs. We propose three modifications. First, the input convolution layer is changed from 1D to 2D so that normalized temperature profiles are also used as inputs to the S2P model. Second, a drop-out layer is added to improve adaptability and generalizability so that the model trained in one area can be transferred to other geographical areas without labelled HVAC data. Third, a fine-tuning process is proposed for areas with a small amount of labelled HVAC data so that the pre-trained S2P model can be fine-tuned to achieve higher disaggregation accuracy (i.e., better transferability) in other areas. The model is first trained and tested using smart meter and sub-metered HVAC data collected in Austin, Texas. Then, the trained model is tested on two other areas: Boulder, Colorado and San Diego, California. Simulation results show that the proposed modified S2P algorithm outperforms the original S2P model and the support-vector machine based approach in accuracy, adaptability, and transferability.</abstract><doi>10.48550/arxiv.2212.04886</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2212.04886
ispartof
issn
language eng
recordid cdi_arxiv_primary_2212_04886
source arXiv.org
subjects Computer Science - Systems and Control
title A Modified Sequence-to-point HVAC Load Disaggregation Algorithm
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T01%3A30%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Modified%20Sequence-to-point%20HVAC%20Load%20Disaggregation%20Algorithm&rft.au=Ye,%20Kai&rft.date=2022-12-09&rft_id=info:doi/10.48550/arxiv.2212.04886&rft_dat=%3Carxiv_GOX%3E2212_04886%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true