{"id":"https://openalex.org/W4412610511","doi":"https://doi.org/10.1109/hpcc64274.2024.00113","title":"On an Approximation Algorithm for HDFS Data Block Placement in Heterogeneous Hadoop Clusters","display_name":"On an Approximation Algorithm for HDFS Data Block Placement in Heterogeneous Hadoop Clusters","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4412610511","doi":"https://doi.org/10.1109/hpcc64274.2024.00113"},"language":"en","primary_location":{"id":"doi:10.1109/hpcc64274.2024.00113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100610194","display_name":"Yijie Zhang","orcid":"https://orcid.org/0000-0001-6478-0657"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijie Zhang","raw_affiliation_strings":["New Jersey Institute of Technology,Department of Data Science,Newark,NJ,USA,07102"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology,Department of Data Science,Newark,NJ,USA,07102","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054307870","display_name":"Chase Q. Wu","orcid":"https://orcid.org/0000-0002-8218-1209"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chase Q. Wu","raw_affiliation_strings":["New Jersey Institute of Technology,Department of Data Science,Newark,NJ,USA,07102"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology,Department of Data Science,Newark,NJ,USA,07102","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064754265","display_name":"Aiqin Hou","orcid":"https://orcid.org/0000-0003-0821-417X"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiqin Hou","raw_affiliation_strings":["Northwest University,School of Information Science and Technology,Xi’an,China,710127"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwest University,School of Information Science and Technology,Xi’an,China,710127","institution_ids":["https://openalex.org/I37802460"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0449,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81988636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"822","last_page":"829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7815027832984924},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6531025171279907},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6285316348075867},{"id":"https://openalex.org/keywords/distributed-file-system","display_name":"Distributed File System","score":0.5734115242958069},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38447919487953186},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3774714171886444},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09983769059181213},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08249440789222717}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7815027832984924},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6531025171279907},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6285316348075867},{"id":"https://openalex.org/C152043487","wikidata":"https://www.wikidata.org/wiki/Q1229600","display_name":"Distributed File System","level":2,"score":0.5734115242958069},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38447919487953186},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3774714171886444},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09983769059181213},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08249440789222717}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcc64274.2024.00113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2102201348","https://openalex.org/W2198756567","https://openalex.org/W2270087850","https://openalex.org/W2469949315","https://openalex.org/W2565829752","https://openalex.org/W2738797121","https://openalex.org/W2901383909","https://openalex.org/W2911204426","https://openalex.org/W2922086451","https://openalex.org/W2990234340","https://openalex.org/W3033610197","https://openalex.org/W3082431408","https://openalex.org/W3088170966","https://openalex.org/W4225920279","https://openalex.org/W4293147077","https://openalex.org/W4294691717","https://openalex.org/W4300589096","https://openalex.org/W4309825916","https://openalex.org/W4315481937","https://openalex.org/W4315798336","https://openalex.org/W4317620952","https://openalex.org/W4321072006","https://openalex.org/W4360995330","https://openalex.org/W4361859230"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W4409439182","https://openalex.org/W2393386140","https://openalex.org/W4322706912","https://openalex.org/W3086554866","https://openalex.org/W1606243561","https://openalex.org/W2053286651","https://openalex.org/W1173381687","https://openalex.org/W2029210135"],"abstract_inverted_index":{"Hadoop":[0,17,25,78,106],"stands":[1],"out":[2],"as":[3,18,45,70],"one":[4],"of":[5,77,86,92,148,158],"the":[6,24,60,64,75,81,89,144,156],"most":[7],"widely":[8],"employed":[9],"systems":[10],"for":[11,104,118],"processing":[12],"big":[13],"data.":[14],"Embedded":[15],"within":[16],"a":[19,71,114,137],"foundational":[20],"technological":[21],"layer":[22],"is":[23,40],"Distributed":[26],"File":[27],"System":[28],"(HDFS),":[29],"providing":[30],"fault":[31],"tolerance":[32],"and":[33,50,95,126],"high":[34],"throughput":[35],"in":[36,54,59],"data":[37,46,93,98],"storage.":[38],"This":[39],"achieved":[41],"through":[42],"mechanisms":[43],"such":[44],"partitioning,":[47],"block":[48,67,83],"replication,":[49],"cluster-wide":[51],"distribution,":[52],"which":[53],"turn":[55],"facilitate":[56],"parallel":[57],"computing":[58],"upper":[61],"layers.":[62],"Consequently,":[63],"strategy":[65],"governing":[66],"placement":[68],"emerges":[69],"pivotal":[72],"factor":[73],"influencing":[74],"performance":[76,139,146],"clusters.":[79,107],"However,":[80],"default":[82],"distribution":[84],"approach":[85],"HDFS":[87],"overlooks":[88],"varying":[90],"capacities":[91],"nodes":[94],"their":[96],"diverse":[97],"access":[99],"patterns,":[100],"rendering":[101],"it":[102,122],"unsuitable":[103],"heterogeneous":[105,119],"To":[108],"address":[109],"this":[110],"challenge,":[111],"we":[112],"formulate":[113],"Block":[115],"Distribution":[116],"problem":[117],"clusters,":[120],"prove":[121],"to":[123],"be":[124],"NP-complete,":[125],"design":[127],"an":[128],"approximation":[129],"algorithm,":[130],"Linear":[131],"Programming-based":[132],"Iterative":[133],"Rounding":[134],"(LPIR-BD),":[135],"with":[136],"rigorous":[138],"guarantee.":[140],"Extensive":[141],"experiments":[142],"illustrate":[143],"notable":[145],"superiority":[147],"LPIR-BD":[149],"over":[150],"several":[151],"state-of-the-art":[152],"algorithms,":[153],"thus":[154],"confirming":[155],"efficacy":[157],"our":[159],"theoretical":[160],"analysis.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}