Loading…

CFWS: DRL-Based Framework for Energy Cost and Carbon Footprint Optimization in Cloud Data Centers

The rapid growth and widespread adoption of cloud computing have led to significant electricity costs and environmental impacts. Traditional approaches that rely on static utilization thresholds are ineffective in dynamic cloud environments, and simply consolidating virtual machines (VMs) to minimiz...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on sustainable computing 2024, p.1-13
Main Authors: Zhao, Daming, Zhou, Jian-tao, Li, Keqin
Format: Article
Language:English
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 13
container_issue
container_start_page 1
container_title IEEE transactions on sustainable computing
container_volume
creator Zhao, Daming
Zhou, Jian-tao
Li, Keqin
description The rapid growth and widespread adoption of cloud computing have led to significant electricity costs and environmental impacts. Traditional approaches that rely on static utilization thresholds are ineffective in dynamic cloud environments, and simply consolidating virtual machines (VMs) to minimize energy costs does not necessarily result in the lowest carbon footprints. In this paper, a deep reinforcement learning (DRL) based framework called CFWS is proposed to enhance the energy efficiency of renewable energy sources (RES) supplied data centers (DCs). CFWS incorporates an adaptive thresholds adjustment method TCN-MAD by evaluating the predicted probability of a physical machine (PM) being overloaded to prevent unnecessary VM migrations and mitigate service level agreement (SLA) violations due to imbalanced workload distribution. Additionally, CFWS introduces a novel action space in the DRL algorithm by representing VM migrations among geo-distributed cloud data centers as flattened indices to accelerate its execution efficiency. Simulation results demonstrate that CFWS can achieve a superior optimization of energy costs and carbon footprints, saving 5.67% to 13.22% brown energy with maximized RES utilization. Furthermore, CFWS reduces VM migrations by up to 86.53% and maintains the lowest SLA violations within suboptimal execution time in comparison to the state-of-art algorithms.
doi_str_mv 10.1109/TSUSC.2024.3391791
format article
fullrecord <record><control><sourceid>crossref_ieee_</sourceid><recordid>TN_cdi_ieee_primary_10506585</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10506585</ieee_id><sourcerecordid>10_1109_TSUSC_2024_3391791</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1781-b1918af208fa1047255ddd7b5ac7723332ee0b3cacb958745e4319a2bd53c30f3</originalsourceid><addsrcrecordid>eNpNkNFKwzAUhoMoOOZeQLzIC3TmJI1pvNPMqjAYuA0vy2mTSnVrRhKR-fRubohX5-fA9_PzEXIJbAzA9PVivpybMWc8HwuhQWk4IQMulMqE0uz0Lxf8nIxifGeMgVJScxgQNOXr_JZOXqbZPUZnaRlw7b58-KCtD_Shd-FtS42PiWJvqcFQ-56W3qdN6PpEZ5vUrbtvTN3u3fXUrPynpRNMSI3rkwvxgpy1uIpudLxDsiwfFuYpm84en83dNGtAFZDVoKHAlrOiRWC54lJaa1UtsVGKCyG4c6wWDTa1loXKpcsFaOS1laIRrBVDwg-9TfAxBtdWu4VrDNsKWLX3VP16qvaeqqOnHXR1gDrn3D9AshtZSPEDApZjow</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>CFWS: DRL-Based Framework for Energy Cost and Carbon Footprint Optimization in Cloud Data Centers</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Zhao, Daming ; Zhou, Jian-tao ; Li, Keqin</creator><creatorcontrib>Zhao, Daming ; Zhou, Jian-tao ; Li, Keqin</creatorcontrib><description>The rapid growth and widespread adoption of cloud computing have led to significant electricity costs and environmental impacts. Traditional approaches that rely on static utilization thresholds are ineffective in dynamic cloud environments, and simply consolidating virtual machines (VMs) to minimize energy costs does not necessarily result in the lowest carbon footprints. In this paper, a deep reinforcement learning (DRL) based framework called CFWS is proposed to enhance the energy efficiency of renewable energy sources (RES) supplied data centers (DCs). CFWS incorporates an adaptive thresholds adjustment method TCN-MAD by evaluating the predicted probability of a physical machine (PM) being overloaded to prevent unnecessary VM migrations and mitigate service level agreement (SLA) violations due to imbalanced workload distribution. Additionally, CFWS introduces a novel action space in the DRL algorithm by representing VM migrations among geo-distributed cloud data centers as flattened indices to accelerate its execution efficiency. Simulation results demonstrate that CFWS can achieve a superior optimization of energy costs and carbon footprints, saving 5.67% to 13.22% brown energy with maximized RES utilization. Furthermore, CFWS reduces VM migrations by up to 86.53% and maintains the lowest SLA violations within suboptimal execution time in comparison to the state-of-art algorithms.</description><identifier>ISSN: 2377-3782</identifier><identifier>EISSN: 2377-3790</identifier><identifier>DOI: 10.1109/TSUSC.2024.3391791</identifier><identifier>CODEN: ITSCBE</identifier><language>eng</language><publisher>IEEE</publisher><subject>Carbon dioxide ; Carbon emission ; Carbon footprint ; Cloud computing ; cloud data centers ; Costs ; Data centers ; energy cost ; Optimization ; renewable energy ; resource allocation ; Service level agreements ; workload shifting</subject><ispartof>IEEE transactions on sustainable computing, 2024, p.1-13</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><orcidid>0000-0001-5224-4048 ; 0000-0002-7066-9282 ; 0000-0002-1518-9948</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10506585$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,4024,27923,27924,27925,54796</link.rule.ids></links><search><creatorcontrib>Zhao, Daming</creatorcontrib><creatorcontrib>Zhou, Jian-tao</creatorcontrib><creatorcontrib>Li, Keqin</creatorcontrib><title>CFWS: DRL-Based Framework for Energy Cost and Carbon Footprint Optimization in Cloud Data Centers</title><title>IEEE transactions on sustainable computing</title><addtitle>TSUSC</addtitle><description>The rapid growth and widespread adoption of cloud computing have led to significant electricity costs and environmental impacts. Traditional approaches that rely on static utilization thresholds are ineffective in dynamic cloud environments, and simply consolidating virtual machines (VMs) to minimize energy costs does not necessarily result in the lowest carbon footprints. In this paper, a deep reinforcement learning (DRL) based framework called CFWS is proposed to enhance the energy efficiency of renewable energy sources (RES) supplied data centers (DCs). CFWS incorporates an adaptive thresholds adjustment method TCN-MAD by evaluating the predicted probability of a physical machine (PM) being overloaded to prevent unnecessary VM migrations and mitigate service level agreement (SLA) violations due to imbalanced workload distribution. Additionally, CFWS introduces a novel action space in the DRL algorithm by representing VM migrations among geo-distributed cloud data centers as flattened indices to accelerate its execution efficiency. Simulation results demonstrate that CFWS can achieve a superior optimization of energy costs and carbon footprints, saving 5.67% to 13.22% brown energy with maximized RES utilization. Furthermore, CFWS reduces VM migrations by up to 86.53% and maintains the lowest SLA violations within suboptimal execution time in comparison to the state-of-art algorithms.</description><subject>Carbon dioxide</subject><subject>Carbon emission</subject><subject>Carbon footprint</subject><subject>Cloud computing</subject><subject>cloud data centers</subject><subject>Costs</subject><subject>Data centers</subject><subject>energy cost</subject><subject>Optimization</subject><subject>renewable energy</subject><subject>resource allocation</subject><subject>Service level agreements</subject><subject>workload shifting</subject><issn>2377-3782</issn><issn>2377-3790</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><recordid>eNpNkNFKwzAUhoMoOOZeQLzIC3TmJI1pvNPMqjAYuA0vy2mTSnVrRhKR-fRubohX5-fA9_PzEXIJbAzA9PVivpybMWc8HwuhQWk4IQMulMqE0uz0Lxf8nIxifGeMgVJScxgQNOXr_JZOXqbZPUZnaRlw7b58-KCtD_Shd-FtS42PiWJvqcFQ-56W3qdN6PpEZ5vUrbtvTN3u3fXUrPynpRNMSI3rkwvxgpy1uIpudLxDsiwfFuYpm84en83dNGtAFZDVoKHAlrOiRWC54lJaa1UtsVGKCyG4c6wWDTa1loXKpcsFaOS1laIRrBVDwg-9TfAxBtdWu4VrDNsKWLX3VP16qvaeqqOnHXR1gDrn3D9AshtZSPEDApZjow</recordid><startdate>2024</startdate><enddate>2024</enddate><creator>Zhao, Daming</creator><creator>Zhou, Jian-tao</creator><creator>Li, Keqin</creator><general>IEEE</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0001-5224-4048</orcidid><orcidid>https://orcid.org/0000-0002-7066-9282</orcidid><orcidid>https://orcid.org/0000-0002-1518-9948</orcidid></search><sort><creationdate>2024</creationdate><title>CFWS: DRL-Based Framework for Energy Cost and Carbon Footprint Optimization in Cloud Data Centers</title><author>Zhao, Daming ; Zhou, Jian-tao ; Li, Keqin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1781-b1918af208fa1047255ddd7b5ac7723332ee0b3cacb958745e4319a2bd53c30f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Carbon dioxide</topic><topic>Carbon emission</topic><topic>Carbon footprint</topic><topic>Cloud computing</topic><topic>cloud data centers</topic><topic>Costs</topic><topic>Data centers</topic><topic>energy cost</topic><topic>Optimization</topic><topic>renewable energy</topic><topic>resource allocation</topic><topic>Service level agreements</topic><topic>workload shifting</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhao, Daming</creatorcontrib><creatorcontrib>Zhou, Jian-tao</creatorcontrib><creatorcontrib>Li, Keqin</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Xplore Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>CrossRef</collection><jtitle>IEEE transactions on sustainable computing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhao, Daming</au><au>Zhou, Jian-tao</au><au>Li, Keqin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>CFWS: DRL-Based Framework for Energy Cost and Carbon Footprint Optimization in Cloud Data Centers</atitle><jtitle>IEEE transactions on sustainable computing</jtitle><stitle>TSUSC</stitle><date>2024</date><risdate>2024</risdate><spage>1</spage><epage>13</epage><pages>1-13</pages><issn>2377-3782</issn><eissn>2377-3790</eissn><coden>ITSCBE</coden><abstract>The rapid growth and widespread adoption of cloud computing have led to significant electricity costs and environmental impacts. Traditional approaches that rely on static utilization thresholds are ineffective in dynamic cloud environments, and simply consolidating virtual machines (VMs) to minimize energy costs does not necessarily result in the lowest carbon footprints. In this paper, a deep reinforcement learning (DRL) based framework called CFWS is proposed to enhance the energy efficiency of renewable energy sources (RES) supplied data centers (DCs). CFWS incorporates an adaptive thresholds adjustment method TCN-MAD by evaluating the predicted probability of a physical machine (PM) being overloaded to prevent unnecessary VM migrations and mitigate service level agreement (SLA) violations due to imbalanced workload distribution. Additionally, CFWS introduces a novel action space in the DRL algorithm by representing VM migrations among geo-distributed cloud data centers as flattened indices to accelerate its execution efficiency. Simulation results demonstrate that CFWS can achieve a superior optimization of energy costs and carbon footprints, saving 5.67% to 13.22% brown energy with maximized RES utilization. Furthermore, CFWS reduces VM migrations by up to 86.53% and maintains the lowest SLA violations within suboptimal execution time in comparison to the state-of-art algorithms.</abstract><pub>IEEE</pub><doi>10.1109/TSUSC.2024.3391791</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0001-5224-4048</orcidid><orcidid>https://orcid.org/0000-0002-7066-9282</orcidid><orcidid>https://orcid.org/0000-0002-1518-9948</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2377-3782
ispartof IEEE transactions on sustainable computing, 2024, p.1-13
issn 2377-3782
2377-3790
language eng
recordid cdi_ieee_primary_10506585
source IEEE Electronic Library (IEL) Journals
subjects Carbon dioxide
Carbon emission
Carbon footprint
Cloud computing
cloud data centers
Costs
Data centers
energy cost
Optimization
renewable energy
resource allocation
Service level agreements
workload shifting
title CFWS: DRL-Based Framework for Energy Cost and Carbon Footprint Optimization in Cloud Data Centers
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T15%3A25%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=CFWS:%20DRL-Based%20Framework%20for%20Energy%20Cost%20and%20Carbon%20Footprint%20Optimization%20in%20Cloud%20Data%20Centers&rft.jtitle=IEEE%20transactions%20on%20sustainable%20computing&rft.au=Zhao,%20Daming&rft.date=2024&rft.spage=1&rft.epage=13&rft.pages=1-13&rft.issn=2377-3782&rft.eissn=2377-3790&rft.coden=ITSCBE&rft_id=info:doi/10.1109/TSUSC.2024.3391791&rft_dat=%3Ccrossref_ieee_%3E10_1109_TSUSC_2024_3391791%3C/crossref_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c1781-b1918af208fa1047255ddd7b5ac7723332ee0b3cacb958745e4319a2bd53c30f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10506585&rfr_iscdi=true