<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04721852</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-22T23:10:37+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A Review of Data Placement and Replication Strategies Based on Machine Learning</title>
            <author role="aut">
              <persName>
                <forename type="first">Amir</forename>
                <surname>Najjar</surname>
              </persName>
              <email type="md5">c9b2c227bd1b222f4cc0972feb7c7e99</email>
              <email type="domain">irit.fr</email>
              <idno type="idhal" notation="string">amir-najjar</idno>
              <idno type="idhal" notation="numeric">1419814</idno>
              <idno type="halauthorid" notation="string">3244315-1419814</idno>
              <idno type="ORCID">https://orcid.org/0009-0009-1558-1681</idno>
              <affiliation ref="#struct-1001829"/>
              <affiliation ref="#struct-442522"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Riad</forename>
                <surname>Mokadem</surname>
              </persName>
              <email type="md5">d8bf79046b1f92da5d0fd10e45c1a021</email>
              <email type="domain">irit.fr</email>
              <idno type="idhal" notation="string">riad-mokadem</idno>
              <idno type="idhal" notation="numeric">752557</idno>
              <idno type="halauthorid" notation="string">14936-752557</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3325-7331</idno>
              <affiliation ref="#struct-1001829"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Jean-Marc</forename>
                <surname>Pierson</surname>
              </persName>
              <email type="md5">88f7de991aecf0997ad341df04d8f1c1</email>
              <email type="domain">irit.fr</email>
              <idno type="idhal" notation="string">jean-marc-pierson</idno>
              <idno type="idhal" notation="numeric">184702</idno>
              <idno type="halauthorid" notation="string">16761-184702</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-8948-0474</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=UnCXn_QAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/080240518</idno>
              <affiliation ref="#struct-442522"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Amir</forename>
                <surname>Najjar</surname>
              </persName>
              <email type="md5">c9b2c227bd1b222f4cc0972feb7c7e99</email>
              <email type="domain">irit.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-10-07 13:12:31</date>
              <date type="whenModified">2026-02-05 11:56:25</date>
              <date type="whenReleased">2024-10-07 13:39:59</date>
              <date type="whenProduced">2024-10-09</date>
              <date type="whenEndEmbargoed">2024-10-07</date>
              <ref type="file" target="https://hal.science/hal-04721852v1/document">
                <date notBefore="2024-10-07"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04721852v1/file/A_Review_of_Data_Placement_and_Replication_Strategies_Based_on_Machine_Learning__Camera_Ready___v1.pdf" id="file-4721852-4110401">
                <date notBefore="2024-10-07"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1577920">
                <persName>
                  <forename>Amir</forename>
                  <surname>Najjar</surname>
                </persName>
                <email type="md5">c9b2c227bd1b222f4cc0972feb7c7e99</email>
                <email type="domain">irit.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04721852</idno>
            <idno type="halUri">https://hal.science/hal-04721852</idno>
            <idno type="halBibtex">najjar:hal-04721852</idno>
            <idno type="halRefHtml">&lt;i&gt;The 30th International Conference on Parallel and Distributed Systems (ICPADS 2024)&lt;/i&gt;, Oct 2024, Belgrade, Serbia</idno>
            <idno type="halRef">The 30th International Conference on Parallel and Distributed Systems (ICPADS 2024), Oct 2024, Belgrade, Serbia</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4721852-4110401"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-TLSE2">Université Toulouse 2</idno>
            <idno type="stamp" n="UNIV-TLSE3">Université de Toulouse</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UT1-CAPITOLE">Université Toulouse 1 Capitole</idno>
            <idno type="stamp" n="IRIT">IRIT - Institut de Recherche en Informatique de Toulouse</idno>
            <idno type="stamp" n="IRIT-PYRAMIDE" corresp="IRIT">Optimisation Dynamique de Requêtes Réparties à grande échelle</idno>
            <idno type="stamp" n="IRIT-SEPIA" corresp="IRIT">Système d’Exploitation, systèmes Répartis, de l’Intergiciel à l’Architecture</idno>
            <idno type="stamp" n="IRIT-GD" corresp="IRIT">Gestion des Données</idno>
            <idno type="stamp" n="IRIT-ASR" corresp="IRIT">Architecture, Systèmes, Réseaux</idno>
            <idno type="stamp" n="TOULOUSE-INP">Toulouse - INP</idno>
            <idno type="stamp" n="UNIV-UT3">Université Toulouse 3</idno>
            <idno type="stamp" n="UT3-INP">Université de Toulouse / Toulouse INP</idno>
            <idno type="stamp" n="UT3-TOULOUSEINP">Université de Toulouse / Toulouse INP</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">A Review of Data Placement and Replication Strategies Based on Machine Learning</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Amir</forename>
                    <surname>Najjar</surname>
                  </persName>
                  <email type="md5">c9b2c227bd1b222f4cc0972feb7c7e99</email>
                  <email type="domain">irit.fr</email>
                  <idno type="idhal" notation="string">amir-najjar</idno>
                  <idno type="idhal" notation="numeric">1419814</idno>
                  <idno type="halauthorid" notation="string">3244315-1419814</idno>
                  <idno type="ORCID">https://orcid.org/0009-0009-1558-1681</idno>
                  <affiliation ref="#struct-1001829"/>
                  <affiliation ref="#struct-442522"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Riad</forename>
                    <surname>Mokadem</surname>
                  </persName>
                  <email type="md5">d8bf79046b1f92da5d0fd10e45c1a021</email>
                  <email type="domain">irit.fr</email>
                  <idno type="idhal" notation="string">riad-mokadem</idno>
                  <idno type="idhal" notation="numeric">752557</idno>
                  <idno type="halauthorid" notation="string">14936-752557</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3325-7331</idno>
                  <affiliation ref="#struct-1001829"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Jean-Marc</forename>
                    <surname>Pierson</surname>
                  </persName>
                  <email type="md5">88f7de991aecf0997ad341df04d8f1c1</email>
                  <email type="domain">irit.fr</email>
                  <idno type="idhal" notation="string">jean-marc-pierson</idno>
                  <idno type="idhal" notation="numeric">184702</idno>
                  <idno type="halauthorid" notation="string">16761-184702</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-8948-0474</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=UnCXn_QAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/080240518</idno>
                  <affiliation ref="#struct-442522"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>The 30th International Conference on Parallel and Distributed Systems (ICPADS 2024)</title>
                  <date type="start">2024-10-09</date>
                  <date type="end">2024-10-14</date>
                  <settlement>Belgrade</settlement>
                  <country key="RS">Serbia</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Data Replication</term>
                <term xml:lang="en">Data Placement</term>
                <term xml:lang="en">Machine Learning</term>
                <term xml:lang="en">Distributed Systems</term>
                <term xml:lang="en">Distributed Systems Data Replication Data Placement Machine Learning</term>
                <term xml:lang="en">Data Replication</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-dc">Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>&lt;div&gt;&lt;p&gt;The global increase in data volumes has brought forth the need for scalable distributed systems that can provide satisfactory quality of service. Data placement and replication are well known techniques that provide increased performance, improved fault tolerance and higher availability. These techniques often require threshold-based activation mechanisms that can vary due to the nature of the workload and the underlying system architecture. Hence, setting and adjusting those thresholds usually require human intervention. In this context, machine learning presents a promising facet to automatically define such thresholds to adapt to different workloads and architectures. In this paper, we study the data placement and replication strategies proposed in the literature that employ machine learning. We classify such strategies based on the machine learning method, the platform on which they are deployed, the dynamicity and the achieved objectives. We describe the approach applied by each strategy as well as possible limitations. In addition, we provide insights into the experimental environments and metrics used to evaluate the strategies. We highlight the need to design data placement and replication strategies that respond better to modern needs for distributed systems. We also motivate the use of machine learning to achieve autonomy in distributed systems.&lt;/p&gt;&lt;/div&gt;</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1001829" status="OLD">
          <orgName>Optimisation Dynamique de Requêtes Réparties à grande échelle</orgName>
          <orgName type="acronym">IRIT-PYRAMIDE</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>Institut de recherche en informatique de Toulouse - IRIT118 Route de Narbonne 31062 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.irit.fr/departement/gestion-des-donnees/equipe-pyramide/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-34499" type="direct"/>
            <relation active="#struct-81148" type="indirect"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="indirect"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-217752" type="indirect"/>
            <relation name="UMR5505 / URA1399" active="#struct-441569" type="indirect"/>
            <relation active="#struct-448187" type="indirect"/>
            <relation active="#struct-1149079" type="indirect"/>
            <relation name="FED4171" active="#struct-217752" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-442522" status="OLD">
          <orgName>Système d’exploitation, systèmes répartis, de l’intergiciel à l’architecture</orgName>
          <orgName type="acronym">IRIT-SEPIA</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>IRIT118 Route de Narbonne31062 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irit.fr/-Equipe-SEPIA-</ref>
          </desc>
          <listRelation>
            <relation active="#struct-34499" type="direct"/>
            <relation active="#struct-81148" type="indirect"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="indirect"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-217752" type="indirect"/>
            <relation name="UMR5505 / URA1399" active="#struct-441569" type="indirect"/>
            <relation active="#struct-448187" type="indirect"/>
            <relation active="#struct-1149079" type="indirect"/>
            <relation name="FED4171" active="#struct-217752" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-34499" status="OLD">
          <idno type="IdRef">030947448</idno>
          <idno type="ISNI">0000000121927225</idno>
          <idno type="RNSR">199511949P</idno>
          <idno type="ROR">https://ror.org/01rx4qw44</idno>
          <orgName>Institut de recherche en informatique de Toulouse</orgName>
          <orgName type="acronym">IRIT</orgName>
          <date type="start">1990-01-01</date>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 Route de Narbonne, F-31062 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irit.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-81148" type="direct"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-217752" type="direct"/>
            <relation name="UMR5505 / URA1399" active="#struct-441569" type="direct"/>
            <relation active="#struct-448187" type="direct"/>
            <relation active="#struct-1149079" type="direct"/>
            <relation name="FED4171" active="#struct-217752" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-81148" status="VALID">
          <idno type="IdRef">026404354</idno>
          <idno type="ISNI">0000000121902837</idno>
          <idno type="ROR">https://ror.org/0443n9e75</idno>
          <orgName>Université Toulouse Capitole</orgName>
          <orgName type="acronym">UT Capitole</orgName>
          <date type="start">1970-01-01</date>
          <desc>
            <address>
              <addrLine>2 rue du Doyen-Gabriel-Marty - 31042 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ut-capitole.fr/</ref>
          </desc>
          <listRelation>
            <relation name="443875" active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-443875" status="VALID">
          <idno type="ROR">https://ror.org/017tgbk05</idno>
          <orgName>Communauté d'universités et établissements de Toulouse</orgName>
          <orgName type="acronym">Comue de Toulouse</orgName>
          <desc>
            <address>
              <addrLine>41 Allée Jules Guesde, 31000 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-toulouse.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-116256" status="VALID">
          <idno type="IdRef">026403994</idno>
          <idno type="ROR">https://ror.org/04ezk3x31</idno>
          <orgName>Université Toulouse - Jean Jaurès</orgName>
          <orgName type="acronym">UT2J</orgName>
          <date type="start">1971-01-01</date>
          <desc>
            <address>
              <addrLine>5 allées Antonio Machado - 31058 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse2.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-217752" status="OLD">
          <idno type="IdRef">026404672</idno>
          <idno type="ISNI">0000000121617331</idno>
          <idno type="ROR">https://ror.org/02v6kpv12</idno>
          <idno type="Wikidata">Q1273188</idno>
          <orgName>Université Toulouse III - Paul Sabatier</orgName>
          <orgName type="acronym">UT3</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 route de Narbonne - 31062 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse3.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-448187" status="VALID">
          <idno type="IdRef">026388820</idno>
          <idno type="ISNI">0000000121766169</idno>
          <idno type="ROR">https://ror.org/033p9g875</idno>
          <orgName>Institut National Polytechnique (Toulouse)</orgName>
          <orgName type="acronym">Toulouse INP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inp-toulouse.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-1149079" status="OLD">
          <orgName>Toulouse Mind &amp; Brain Institut</orgName>
          <orgName type="acronym">TMBI</orgName>
          <date type="start">2021-01-01</date>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>CHU Purpan, Pavillon Baudot, 31059 Toulouse cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.tmbi.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation name="FED4171" active="#struct-217752" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>