Loading…

Adaptive Predictive Control of a data center cooling unit

As server densities increase to support the rising demand for high density computing, traditional room cooling infrastructure is struggling to keep up. Rack-mounted cooling units are increasingly being deployed in data centers. These cooling units are located closer to the heat sources (the servers)...

Full description

Saved in:
Bibliographic Details
Published in:Control engineering practice 2021-02, Vol.107, p.104674, Article 104674
Main Authors: Martínez-García, Fernando, Badawy, Ghada, Kheradmandi, Masoud, Down, Douglas G.
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-c318t-1da773e3383730f7b9e29d5d2ac1569c6754bea6b3cec609aa894fef47e3937f3
cites cdi_FETCH-LOGICAL-c318t-1da773e3383730f7b9e29d5d2ac1569c6754bea6b3cec609aa894fef47e3937f3
container_end_page
container_issue
container_start_page 104674
container_title Control engineering practice
container_volume 107
creator Martínez-García, Fernando
Badawy, Ghada
Kheradmandi, Masoud
Down, Douglas G.
description As server densities increase to support the rising demand for high density computing, traditional room cooling infrastructure is struggling to keep up. Rack-mounted cooling units are increasingly being deployed in data centers. These cooling units are located closer to the heat sources (the servers) which allow them to cool more efficiently than traditional cooling infrastructure. In this work, a Multi-Input Single-Output (MISO) Adaptive Predictive Controller (APC) for rack-mounted cooling units is investigated and implemented using a low-cost general-purpose microcontroller. The proposed APC is implemented using Weighted Recursive Least Squares (WRLS) and a sub-optimal but fast algorithm based on the General Predictive Controller (GPC) approach. These are combined with a variable forgetting factor and variable prediction horizon algorithms. In addition, methods are proposed to handle stability issues arising due to practical hardware limitations. The controller is implemented on a real single rack system and challenges for practical implementation are addressed and illustrated. The proposed APC is also compared (via simulation) to a standard APC with equivalent complexity and a split-range PI controller. The results show that the proposed controller outperforms both the standard APC and the split-range PI controllers with respect to Mean Squared Error (MSE). •A fast and sub-optimal Adaptive Predictive Controller is designed and implemented.•Variable forgetting factor and variable prediction horizon allow higher flexibility.•Implementation can be done in a low-cost and general-purpose microcontroller.•Capabilities to appropriately control a Multi-Input Single-Output system was shown.•Competitive performance is obtained when compared to a standard APC and PI with split range control.
doi_str_mv 10.1016/j.conengprac.2020.104674
format article
fullrecord <record><control><sourceid>elsevier_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1016_j_conengprac_2020_104674</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0967066120302446</els_id><sourcerecordid>S0967066120302446</sourcerecordid><originalsourceid>FETCH-LOGICAL-c318t-1da773e3383730f7b9e29d5d2ac1569c6754bea6b3cec609aa894fef47e3937f3</originalsourceid><addsrcrecordid>eNqFkN1KAzEQRoMoWKvvkBfYNdnsJpvLWvyDgl7odUgnk5JlTUo2Fnx7t1bw0qv5GDgfM4cQylnNGZe3Qw0pYtzts4W6Yc1x3UrVnpEF75WopBb6nCyYlqpiUvJLcjVNA5tRrfmC6JWz-xIOSF8zugA_cZ1iyWmkyVNLnS2WAsaCmUJKY4g7-hlDuSYX3o4T3vzOJXl_uH9bP1Wbl8fn9WpTgeB9qbizSgkUohdKMK-2GhvtOtdY4J3UIFXXbtHKrQAEybS1vW49-lah0EJ5sST9qRdymqaM3uxz-LD5y3BmjgrMYP4UmKMCc1Iwo3cnFOf7DgGzmSBghPnRjFCMS-H_km-HvWoG</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Adaptive Predictive Control of a data center cooling unit</title><source>ScienceDirect Journals</source><creator>Martínez-García, Fernando ; Badawy, Ghada ; Kheradmandi, Masoud ; Down, Douglas G.</creator><creatorcontrib>Martínez-García, Fernando ; Badawy, Ghada ; Kheradmandi, Masoud ; Down, Douglas G.</creatorcontrib><description>As server densities increase to support the rising demand for high density computing, traditional room cooling infrastructure is struggling to keep up. Rack-mounted cooling units are increasingly being deployed in data centers. These cooling units are located closer to the heat sources (the servers) which allow them to cool more efficiently than traditional cooling infrastructure. In this work, a Multi-Input Single-Output (MISO) Adaptive Predictive Controller (APC) for rack-mounted cooling units is investigated and implemented using a low-cost general-purpose microcontroller. The proposed APC is implemented using Weighted Recursive Least Squares (WRLS) and a sub-optimal but fast algorithm based on the General Predictive Controller (GPC) approach. These are combined with a variable forgetting factor and variable prediction horizon algorithms. In addition, methods are proposed to handle stability issues arising due to practical hardware limitations. The controller is implemented on a real single rack system and challenges for practical implementation are addressed and illustrated. The proposed APC is also compared (via simulation) to a standard APC with equivalent complexity and a split-range PI controller. The results show that the proposed controller outperforms both the standard APC and the split-range PI controllers with respect to Mean Squared Error (MSE). •A fast and sub-optimal Adaptive Predictive Controller is designed and implemented.•Variable forgetting factor and variable prediction horizon allow higher flexibility.•Implementation can be done in a low-cost and general-purpose microcontroller.•Capabilities to appropriately control a Multi-Input Single-Output system was shown.•Competitive performance is obtained when compared to a standard APC and PI with split range control.</description><identifier>ISSN: 0967-0661</identifier><identifier>EISSN: 1873-6939</identifier><identifier>DOI: 10.1016/j.conengprac.2020.104674</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Adaptive Predictive Controller ; Data center ; Temperature control ; Variable forgetting factor ; Variable prediction horizon</subject><ispartof>Control engineering practice, 2021-02, Vol.107, p.104674, Article 104674</ispartof><rights>2020 Elsevier Ltd</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c318t-1da773e3383730f7b9e29d5d2ac1569c6754bea6b3cec609aa894fef47e3937f3</citedby><cites>FETCH-LOGICAL-c318t-1da773e3383730f7b9e29d5d2ac1569c6754bea6b3cec609aa894fef47e3937f3</cites><orcidid>0000-0003-0881-831X</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>Martínez-García, Fernando</creatorcontrib><creatorcontrib>Badawy, Ghada</creatorcontrib><creatorcontrib>Kheradmandi, Masoud</creatorcontrib><creatorcontrib>Down, Douglas G.</creatorcontrib><title>Adaptive Predictive Control of a data center cooling unit</title><title>Control engineering practice</title><description>As server densities increase to support the rising demand for high density computing, traditional room cooling infrastructure is struggling to keep up. Rack-mounted cooling units are increasingly being deployed in data centers. These cooling units are located closer to the heat sources (the servers) which allow them to cool more efficiently than traditional cooling infrastructure. In this work, a Multi-Input Single-Output (MISO) Adaptive Predictive Controller (APC) for rack-mounted cooling units is investigated and implemented using a low-cost general-purpose microcontroller. The proposed APC is implemented using Weighted Recursive Least Squares (WRLS) and a sub-optimal but fast algorithm based on the General Predictive Controller (GPC) approach. These are combined with a variable forgetting factor and variable prediction horizon algorithms. In addition, methods are proposed to handle stability issues arising due to practical hardware limitations. The controller is implemented on a real single rack system and challenges for practical implementation are addressed and illustrated. The proposed APC is also compared (via simulation) to a standard APC with equivalent complexity and a split-range PI controller. The results show that the proposed controller outperforms both the standard APC and the split-range PI controllers with respect to Mean Squared Error (MSE). •A fast and sub-optimal Adaptive Predictive Controller is designed and implemented.•Variable forgetting factor and variable prediction horizon allow higher flexibility.•Implementation can be done in a low-cost and general-purpose microcontroller.•Capabilities to appropriately control a Multi-Input Single-Output system was shown.•Competitive performance is obtained when compared to a standard APC and PI with split range control.</description><subject>Adaptive Predictive Controller</subject><subject>Data center</subject><subject>Temperature control</subject><subject>Variable forgetting factor</subject><subject>Variable prediction horizon</subject><issn>0967-0661</issn><issn>1873-6939</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNqFkN1KAzEQRoMoWKvvkBfYNdnsJpvLWvyDgl7odUgnk5JlTUo2Fnx7t1bw0qv5GDgfM4cQylnNGZe3Qw0pYtzts4W6Yc1x3UrVnpEF75WopBb6nCyYlqpiUvJLcjVNA5tRrfmC6JWz-xIOSF8zugA_cZ1iyWmkyVNLnS2WAsaCmUJKY4g7-hlDuSYX3o4T3vzOJXl_uH9bP1Wbl8fn9WpTgeB9qbizSgkUohdKMK-2GhvtOtdY4J3UIFXXbtHKrQAEybS1vW49-lah0EJ5sST9qRdymqaM3uxz-LD5y3BmjgrMYP4UmKMCc1Iwo3cnFOf7DgGzmSBghPnRjFCMS-H_km-HvWoG</recordid><startdate>202102</startdate><enddate>202102</enddate><creator>Martínez-García, Fernando</creator><creator>Badawy, Ghada</creator><creator>Kheradmandi, Masoud</creator><creator>Down, Douglas G.</creator><general>Elsevier Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0003-0881-831X</orcidid></search><sort><creationdate>202102</creationdate><title>Adaptive Predictive Control of a data center cooling unit</title><author>Martínez-García, Fernando ; Badawy, Ghada ; Kheradmandi, Masoud ; Down, Douglas G.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c318t-1da773e3383730f7b9e29d5d2ac1569c6754bea6b3cec609aa894fef47e3937f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Adaptive Predictive Controller</topic><topic>Data center</topic><topic>Temperature control</topic><topic>Variable forgetting factor</topic><topic>Variable prediction horizon</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Martínez-García, Fernando</creatorcontrib><creatorcontrib>Badawy, Ghada</creatorcontrib><creatorcontrib>Kheradmandi, Masoud</creatorcontrib><creatorcontrib>Down, Douglas G.</creatorcontrib><collection>CrossRef</collection><jtitle>Control engineering practice</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Martínez-García, Fernando</au><au>Badawy, Ghada</au><au>Kheradmandi, Masoud</au><au>Down, Douglas G.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Adaptive Predictive Control of a data center cooling unit</atitle><jtitle>Control engineering practice</jtitle><date>2021-02</date><risdate>2021</risdate><volume>107</volume><spage>104674</spage><pages>104674-</pages><artnum>104674</artnum><issn>0967-0661</issn><eissn>1873-6939</eissn><abstract>As server densities increase to support the rising demand for high density computing, traditional room cooling infrastructure is struggling to keep up. Rack-mounted cooling units are increasingly being deployed in data centers. These cooling units are located closer to the heat sources (the servers) which allow them to cool more efficiently than traditional cooling infrastructure. In this work, a Multi-Input Single-Output (MISO) Adaptive Predictive Controller (APC) for rack-mounted cooling units is investigated and implemented using a low-cost general-purpose microcontroller. The proposed APC is implemented using Weighted Recursive Least Squares (WRLS) and a sub-optimal but fast algorithm based on the General Predictive Controller (GPC) approach. These are combined with a variable forgetting factor and variable prediction horizon algorithms. In addition, methods are proposed to handle stability issues arising due to practical hardware limitations. The controller is implemented on a real single rack system and challenges for practical implementation are addressed and illustrated. The proposed APC is also compared (via simulation) to a standard APC with equivalent complexity and a split-range PI controller. The results show that the proposed controller outperforms both the standard APC and the split-range PI controllers with respect to Mean Squared Error (MSE). •A fast and sub-optimal Adaptive Predictive Controller is designed and implemented.•Variable forgetting factor and variable prediction horizon allow higher flexibility.•Implementation can be done in a low-cost and general-purpose microcontroller.•Capabilities to appropriately control a Multi-Input Single-Output system was shown.•Competitive performance is obtained when compared to a standard APC and PI with split range control.</abstract><pub>Elsevier Ltd</pub><doi>10.1016/j.conengprac.2020.104674</doi><orcidid>https://orcid.org/0000-0003-0881-831X</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0967-0661
ispartof Control engineering practice, 2021-02, Vol.107, p.104674, Article 104674
issn 0967-0661
1873-6939
language eng
recordid cdi_crossref_primary_10_1016_j_conengprac_2020_104674
source ScienceDirect Journals
subjects Adaptive Predictive Controller
Data center
Temperature control
Variable forgetting factor
Variable prediction horizon
title Adaptive Predictive Control of a data center cooling unit
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T12%3A21%3A33IST&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=Adaptive%20Predictive%20Control%20of%20a%20data%20center%20cooling%20unit&rft.jtitle=Control%20engineering%20practice&rft.au=Mart%C3%ADnez-Garc%C3%ADa,%20Fernando&rft.date=2021-02&rft.volume=107&rft.spage=104674&rft.pages=104674-&rft.artnum=104674&rft.issn=0967-0661&rft.eissn=1873-6939&rft_id=info:doi/10.1016/j.conengprac.2020.104674&rft_dat=%3Celsevier_cross%3ES0967066120302446%3C/elsevier_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c318t-1da773e3383730f7b9e29d5d2ac1569c6754bea6b3cec609aa894fef47e3937f3%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