{"id":"https://openalex.org/W2967212855","doi":"https://doi.org/10.3390/bdcc3030047","title":"PerTract: Model Extraction and Specification of Big Data Systems for Performance Prediction by the Example of Apache Spark and Hadoop","display_name":"PerTract: Model Extraction and Specification of Big Data Systems for Performance Prediction by the Example of Apache Spark and Hadoop","publication_year":2019,"publication_date":"2019-08-09","ids":{"openalex":"https://openalex.org/W2967212855","doi":"https://doi.org/10.3390/bdcc3030047","mag":"2967212855"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc3030047","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc3030047","pdf_url":"https://www.mdpi.com/2504-2289/3/3/47/pdf?version=1565596354","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/3/3/47/pdf?version=1565596354","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005083186","display_name":"Johannes Kro\u00df","orcid":"https://orcid.org/0000-0002-4382-0995"},"institutions":[{"id":"https://openalex.org/I4210134795","display_name":"Fortiss","ror":"https://ror.org/042x1tp92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210134795"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Johannes Kro\u00df","raw_affiliation_strings":["fortiss, Research Institute of the Free State of Bavaria, Guerickestr. 25, 80805 Munich, Germany"],"affiliations":[{"raw_affiliation_string":"fortiss, Research Institute of the Free State of Bavaria, Guerickestr. 25, 80805 Munich, Germany","institution_ids":["https://openalex.org/I4210134795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077586272","display_name":"Helmut Krcmar","orcid":"https://orcid.org/0000-0002-2754-8493"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Helmut Krcmar","raw_affiliation_strings":["Chair for Information Systems, Technical University of Munich (TUM), Boltzmannstr. 3, 85748 Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Chair for Information Systems, Technical University of Munich (TUM), Boltzmannstr. 3, 85748 Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005083186"],"corresponding_institution_ids":["https://openalex.org/I4210134795"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.238,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81541046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"3","issue":"3","first_page":"47","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":1.0,"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/T10260","display_name":"Software Engineering Research","score":0.9801999926567078,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9787999987602234,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/digital-subscriber-line","display_name":"Digital subscriber line","score":0.8053898215293884},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7945356965065002},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7772561311721802},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7237491607666016},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6234419941902161},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6155476570129395},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4930576980113983},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.4743845760822296},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3967755436897278},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.381302148103714},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3735756278038025},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21052417159080505},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.177891343832016}],"concepts":[{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.8053898215293884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945356965065002},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7772561311721802},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7237491607666016},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6234419941902161},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6155476570129395},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4930576980113983},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.4743845760822296},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3967755436897278},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.381302148103714},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3735756278038025},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21052417159080505},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.177891343832016},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/bdcc3030047","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc3030047","pdf_url":"https://www.mdpi.com/2504-2289/3/3/47/pdf?version=1565596354","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bebbe77905c34d51af6c0929f28c34da","is_oa":true,"landing_page_url":"https://doaj.org/article/bebbe77905c34d51af6c0929f28c34da","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 3, Iss 3, p 47 (2019)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2504-2289/3/3/47/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/bdcc3030047","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"Text"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1652409","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1652409","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/bdcc3030047","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc3030047","pdf_url":"https://www.mdpi.com/2504-2289/3/3/47/pdf?version=1565596354","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2967212855.pdf","grobid_xml":"https://content.openalex.org/works/W2967212855.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1243139153","https://openalex.org/W1437394572","https://openalex.org/W1746258828","https://openalex.org/W1908405131","https://openalex.org/W1936798381","https://openalex.org/W1990405072","https://openalex.org/W2021446094","https://openalex.org/W2028139871","https://openalex.org/W2035282278","https://openalex.org/W2040141901","https://openalex.org/W2043306527","https://openalex.org/W2071598946","https://openalex.org/W2081611182","https://openalex.org/W2084013842","https://openalex.org/W2131975293","https://openalex.org/W2155072926","https://openalex.org/W2163267399","https://openalex.org/W2173213060","https://openalex.org/W2175075972","https://openalex.org/W2207490587","https://openalex.org/W2296078529","https://openalex.org/W2309679942","https://openalex.org/W2312654645","https://openalex.org/W2396186592","https://openalex.org/W2396720400","https://openalex.org/W2470256339","https://openalex.org/W2568700813","https://openalex.org/W2575302115","https://openalex.org/W2604856537","https://openalex.org/W2768471650","https://openalex.org/W2776176772","https://openalex.org/W2796039710","https://openalex.org/W2806583692","https://openalex.org/W3100344569","https://openalex.org/W3151685851","https://openalex.org/W4241337738","https://openalex.org/W4291213652","https://openalex.org/W4299935695","https://openalex.org/W6731414234","https://openalex.org/W6735925873","https://openalex.org/W6884303389"],"related_works":["https://openalex.org/W2119542776","https://openalex.org/W2014596857","https://openalex.org/W2582410692","https://openalex.org/W1485300234","https://openalex.org/W2258960507","https://openalex.org/W2140083133","https://openalex.org/W2460228634","https://openalex.org/W2097052821","https://openalex.org/W3195685258","https://openalex.org/W1573904598"],"abstract_inverted_index":{"Evaluating":[0],"and":[1,15,30,48,82,97,102,112,142,155,186],"predicting":[2,149],"the":[3,22,54,71,130,150,160],"performance":[4,55,114,131,151],"of":[5,26,56,60,73,76,94,132,152,159,166],"big":[6,77],"data":[7,78,83,140],"applications":[8,133,158],"are":[9,88,108],"required":[10],"to":[11,34,45,52,110,117,128,171],"efficiently":[12],"size":[13],"capacities":[14],"manage":[16],"operations.":[17],"Gaining":[18],"profound":[19],"insights":[20],"into":[21],"system":[23,50],"architecture,":[24],"dependencies":[25],"components,":[27],"resource":[28,187],"demands,":[29],"configurations":[31],"cause":[32],"difficulties":[33],"engineers.":[35],"To":[36],"address":[37],"these":[38,106],"challenges,":[39],"this":[40],"paper":[41],"presents":[42],"an":[43],"approach":[44,125,147],"automatically":[46,89],"extract":[47],"transform":[49],"specifications":[51],"predict":[53,129],"applications.":[57],"It":[58],"consists":[59],"three":[61],"components.":[62],"First,":[63],"a":[64],"system-and":[65],"tool-agnostic":[66],"domain-specific":[67],"language":[68],"(DSL)":[69],"allows":[70],"modeling":[72],"performance-relevant":[74],"factors":[75],"applications,":[79],"computing":[80],"resources,":[81],"workload.":[84],"Second,":[85],"DSL":[86,122,168],"instances":[87,107,169],"extracted":[90],"from":[91],"monitored":[92],"measurements":[93],"Apache":[95,98],"Spark":[96],"Hadoop":[99],"(i.e.,":[100],"YARN":[101],"HDFS)":[103],"systems.":[104],"Third,":[105],"transformed":[109],"model-":[111],"simulation-based":[113],"evaluation":[115],"tools":[116],"allow":[118],"predictions.":[119],"By":[120],"adapting":[121],"instances,":[123],"our":[124,146],"enables":[126],"engineers":[127],"for":[134,183],"different":[135],"scenarios":[136],"such":[137],"as":[138],"changing":[139],"input":[141],"resources.":[143],"We":[144],"evaluate":[145],"by":[148],"linear":[153],"regression":[154],"random":[156],"forest":[157],"HiBench":[161],"benchmark":[162],"suite.":[163],"Simulation":[164],"results":[165,173],"adjusted":[167],"compared":[170],"measurement":[172],"show":[174],"accurate":[175],"predictions":[176],"errors":[177],"below":[178],"15%":[179],"based":[180],"upon":[181],"averages":[182],"response":[184],"times":[185],"utilization.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}