{"id":"https://openalex.org/W2027966202","doi":"https://doi.org/10.1109/noms.2012.6212060","title":"Scalable analysis of network measurements with Hadoop and Pig","display_name":"Scalable analysis of network measurements with Hadoop and Pig","publication_year":2012,"publication_date":"2012-04-01","ids":{"openalex":"https://openalex.org/W2027966202","doi":"https://doi.org/10.1109/noms.2012.6212060","mag":"2027966202"},"language":"en","primary_location":{"id":"doi:10.1109/noms.2012.6212060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/noms.2012.6212060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Network Operations and Management Symposium","raw_type":"proceedings-article"},"type":"article","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/A5082534966","display_name":"Taghrid Samak","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"T. Samak","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA","Lawrence Berkeley National Laboratory,Berkeley, CA 94720"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley, CA 94720","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027568646","display_name":"Dan Gunter","orcid":"https://orcid.org/0000-0002-2779-2744"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Gunter","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA","Lawrence Berkeley National Laboratory,Berkeley, CA 94720"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley, CA 94720","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076780371","display_name":"Valerie Hendrix","orcid":"https://orcid.org/0000-0001-9061-8952"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. Hendrix","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA","Lawrence Berkeley National Laboratory,Berkeley, CA 94720"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley, CA 94720","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082534966"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":2.8368,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90928551,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"6","issue":null,"first_page":"1254","last_page":"1259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998999834060669,"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":0.9998999834060669,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.98580002784729,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.9717000126838684,"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/scalability","display_name":"Scalability","score":0.8717087507247925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8424674272537231},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6654419302940369},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6342464685440063},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.575217068195343},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5430762767791748},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5163646936416626},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.466859370470047},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45440784096717834},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3798397183418274},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37106406688690186},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.33672672510147095},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1887056529521942},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09037703275680542}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8717087507247925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8424674272537231},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6654419302940369},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6342464685440063},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.575217068195343},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5430762767791748},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5163646936416626},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.466859370470047},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45440784096717834},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3798397183418274},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37106406688690186},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33672672510147095},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1887056529521942},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09037703275680542},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/noms.2012.6212060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/noms.2012.6212060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Network Operations and Management Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1504380508","https://openalex.org/W1598064945","https://openalex.org/W1912779191","https://openalex.org/W2020820745","https://openalex.org/W2039157918","https://openalex.org/W2070906292","https://openalex.org/W2119192239","https://openalex.org/W2122465391","https://openalex.org/W4239670432","https://openalex.org/W4249942481"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W3138386522","https://openalex.org/W2499279132"],"abstract_inverted_index":{"The":[0],"deployment":[1],"of":[2,17,46,63,94,98,106,118,121,128],"ubiquitous":[3],"distributed":[4],"monitoring":[5],"infrastructure":[6],"such":[7],"as":[8],"perfSONAR":[9,132],"is":[10,55],"greatly":[11],"increasing":[12],"the":[13,44,69,92,96,101],"availability":[14],"and":[15,30,71,83,100,103,116,137],"quality":[16],"network":[18,36],"performance":[19],"data.":[20],"Cross-cutting":[21],"analyses":[22,42],"are":[23],"now":[24],"possible":[25],"that":[26],"can":[27],"detect":[28],"anomalies":[29],"provide":[31],"real-time":[32],"automated":[33],"alerts":[34],"to":[35,43,85,108],"management":[37],"services.":[38],"However,":[39],"scaling":[40],"these":[41,64],"volumes":[45],"available":[47],"data":[48],"remains":[49],"a":[50,110,125,134],"difficult":[51],"task.":[52],"Although":[53],"there":[54],"significant":[56,111],"research":[57],"into":[58],"offline":[59],"analysis":[60,78,102],"techniques,":[61],"most":[62],"approaches":[65],"do":[66],"not":[67],"address":[68],"systems":[70],"scalability":[72,97],"issues.":[73],"This":[74],"work":[75],"presents":[76],"an":[77],"framework":[79,90,123],"incorporating":[80],"industry":[81],"best-practices":[82],"tools":[84],"perform":[86],"large-scale":[87],"analyses.":[88],"Our":[89],"integrates":[91],"expressiveness":[93],"Pig,":[95],"Hadoop,":[99],"visualization":[104],"capabilities":[105],"R":[107],"achieve":[109],"increase":[112],"in":[113],"both":[114],"speed":[115],"power":[117],"analysis.":[119],"Evaluation":[120],"our":[122],"on":[124],"large":[126,135],"dataset":[127],"real":[129],"measurements":[130],"from":[131],"demonstrate":[133],"speedup":[136],"novel":[138],"statistical":[139],"capabilities.":[140]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
