{"id":"https://openalex.org/W4381614296","doi":"https://doi.org/10.1007/s10619-023-07436-y","title":"SimCost: cost-effective resource provision prediction and recommendation for spark workloads","display_name":"SimCost: cost-effective resource provision prediction and recommendation for spark workloads","publication_year":2023,"publication_date":"2023-06-22","ids":{"openalex":"https://openalex.org/W4381614296","doi":"https://doi.org/10.1007/s10619-023-07436-y"},"language":"en","primary_location":{"id":"doi:10.1007/s10619-023-07436-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10619-023-07436-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10619-023-07436-y.pdf","source":{"id":"https://openalex.org/S35927321","display_name":"Distributed and Parallel Databases","issn_l":"0926-8782","issn":["0926-8782","1573-7578"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Distributed and Parallel Databases","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10619-023-07436-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101526503","display_name":"Yuxing Chen","orcid":"https://orcid.org/0000-0002-6220-2535"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yuxing Chen","raw_affiliation_strings":["Department of Computer Science, Univeristy of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Univeristy of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076999524","display_name":"Mohammad A. Hoque","orcid":"https://orcid.org/0000-0002-6135-932X"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mohammad A. Hoque","raw_affiliation_strings":["Department of Computer Science, Univeristy of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Univeristy of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600606","display_name":"Pengfei Xu","orcid":"https://orcid.org/0000-0003-1067-3607"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Pengfei Xu","raw_affiliation_strings":["Department of Computer Science, Univeristy of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Univeristy of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018627557","display_name":"Jiaheng Lu","orcid":"https://orcid.org/0000-0003-2067-454X"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Jiaheng Lu","raw_affiliation_strings":["Department of Computer Science, Univeristy of Helsinki, Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0003-2067-454X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Univeristy of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054443906","display_name":"Sasu Tarkoma","orcid":"https://orcid.org/0000-0003-4220-3650"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sasu Tarkoma","raw_affiliation_strings":["Department of Computer Science, Univeristy of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Univeristy of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018627557"],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":3.4432,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93338175,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"42","issue":"1","first_page":"73","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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":0.9994000196456909,"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"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/spark","display_name":"SPARK (programming language)","score":0.8948137760162354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8199381232261658},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7998315095901489},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6937540173530579},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5011279582977295},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4970887005329132},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48876094818115234},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4314688444137573},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40918806195259094},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35432201623916626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25710517168045044}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8948137760162354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199381232261658},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7998315095901489},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6937540173530579},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5011279582977295},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4970887005329132},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48876094818115234},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4314688444137573},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40918806195259094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35432201623916626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25710517168045044},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10619-023-07436-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10619-023-07436-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10619-023-07436-y.pdf","source":{"id":"https://openalex.org/S35927321","display_name":"Distributed and Parallel Databases","issn_l":"0926-8782","issn":["0926-8782","1573-7578"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Distributed and Parallel Databases","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10619-023-07436-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10619-023-07436-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10619-023-07436-y.pdf","source":{"id":"https://openalex.org/S35927321","display_name":"Distributed and Parallel Databases","issn_l":"0926-8782","issn":["0926-8782","1573-7578"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Distributed and Parallel Databases","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G7864986337","display_name":null,"funder_award_id":"310321","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381614296.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1525444182","https://openalex.org/W1979567624","https://openalex.org/W1980376525","https://openalex.org/W1980849679","https://openalex.org/W1983224729","https://openalex.org/W1984116073","https://openalex.org/W2038361169","https://openalex.org/W2057087550","https://openalex.org/W2058340614","https://openalex.org/W2059120516","https://openalex.org/W2064366207","https://openalex.org/W2088687427","https://openalex.org/W2090066046","https://openalex.org/W2121142115","https://openalex.org/W2133664094","https://openalex.org/W2155072926","https://openalex.org/W2206758307","https://openalex.org/W2415420807","https://openalex.org/W2511329048","https://openalex.org/W2570373436","https://openalex.org/W2580372963","https://openalex.org/W2582789036","https://openalex.org/W2590123570","https://openalex.org/W2735019080","https://openalex.org/W2760770811","https://openalex.org/W2762714487","https://openalex.org/W2776147949","https://openalex.org/W2895725544","https://openalex.org/W2948513753","https://openalex.org/W2963745734","https://openalex.org/W2970836712","https://openalex.org/W2982167413","https://openalex.org/W2984336599","https://openalex.org/W2999515616","https://openalex.org/W3009536016","https://openalex.org/W3098844916","https://openalex.org/W3138386522","https://openalex.org/W4289866483","https://openalex.org/W6604079170","https://openalex.org/W6993211581"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W2770764537","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991"],"abstract_inverted_index":{"Abstract":[0],"Spark":[1,23],"is":[2,26,112],"one":[3],"of":[4,71,81,94],"the":[5,42,69,137,150],"most":[6],"popular":[7],"big":[8],"data":[9,31,95],"analytical":[10],"platforms.":[11],"To":[12],"save":[13],"time,":[14],"achieve":[15,75],"high":[16],"resource":[17,36,53,56,156],"utilization,":[18],"and":[19,55,96,106,149],"remain":[20],"cost-effective":[21],"for":[22,30,103],"jobs,":[24],"it":[25,114],"challenging":[27],"but":[28],"imperative":[29],"scientists":[32],"to":[33,67,98,117,154],"configure":[34],"suitable":[35],"portions.In":[37],"this":[38],"paper,":[39],"we":[40,134],"investigate":[41],"proper":[43],"parameter":[44],"values":[45],"that":[46,113,136],"meet":[47],"workloads\u2019":[48],"performance":[49,70],"requirements":[50],"with":[51,130],"minimized":[52],"cost":[54,65,138,157],"utilization":[57],"time.":[58],"We":[59,74],"propose":[60],"SimCost":[61],",":[62,84],"a":[63,91,100],"simulation-based":[64],"model,":[66],"predict":[68],"jobs":[72],"accurately.":[73],"low-cost":[76],"training":[77,120],"by":[78],"taking":[79],"advantage":[80],"simulation":[82],"framework":[83],"i.e.,":[85],"Monte":[86],"Carlo":[87],"simulation,":[88],"which":[89],"uses":[90],"small":[92],"amount":[93],"resources":[97],"make":[99],"reliable":[101],"prediction":[102,147],"larger":[104],"datasets":[105],"clusters.":[107],"Our":[108],"method\u2019s":[109],"salient":[110],"feature":[111],"allows":[115],"us":[116],"invest":[118],"low":[119],"costs":[121],"while":[122],"obtaining":[123],"an":[124],"accurate":[125],"prediction.":[126],"Through":[127],"empirical":[128],"experiments":[129],"12":[131],"benchmark":[132],"workloads,":[133],"show":[135],"model":[139],"yields":[140],"less":[141],"than":[142],"5%":[143],"error":[144],"on":[145],"average":[146],"accuracy,":[148],"recommendation":[151],"achieves":[152],"up":[153],"6x":[155],"saving.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
