{"id":"https://openalex.org/W2072426277","doi":"https://doi.org/10.1109/softcom.2014.7039136","title":"Web page download scheduling policies for green web crawling","display_name":"Web page download scheduling policies for green web crawling","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2072426277","doi":"https://doi.org/10.1109/softcom.2014.7039136","mag":"2072426277"},"language":"en","primary_location":{"id":"doi:10.1109/softcom.2014.7039136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/softcom.2014.7039136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 22nd International Conference on Software, Telecommunications and Computer Networks (SoftCOM)","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/A5051012437","display_name":"Vassiliki Hatzi","orcid":null},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Vassiliki Hatzi","raw_affiliation_strings":["CERTH and University of Thessaly, Greece","CERTH and University of Thessaly Greece"],"affiliations":[{"raw_affiliation_string":"CERTH and University of Thessaly, Greece","institution_ids":["https://openalex.org/I145722265","https://openalex.org/I4210134249"]},{"raw_affiliation_string":"CERTH and University of Thessaly Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015615642","display_name":"B. Barla Cambazo\u011flu","orcid":"https://orcid.org/0000-0003-2192-3819"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"B. Barla Cambazoglu","raw_affiliation_strings":["Yahoo Labs, Barcelona, Spain",", Yahoo! Labs, Barcelona, Spain#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo Labs, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]},{"raw_affiliation_string":", Yahoo! Labs, Barcelona, Spain#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057979014","display_name":"Iordanis Koutsopoulos","orcid":"https://orcid.org/0000-0001-7699-5276"},"institutions":[{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Iordanis Koutsopoulos","raw_affiliation_strings":["Athens University of Economics and Business, and CERTH, Greece","[Athens University of Economics and Business and CERTH, Greece]"],"affiliations":[{"raw_affiliation_string":"Athens University of Economics and Business, and CERTH, Greece","institution_ids":["https://openalex.org/I73142707","https://openalex.org/I4210134249"]},{"raw_affiliation_string":"[Athens University of Economics and Business and CERTH, Greece]","institution_ids":["https://openalex.org/I73142707"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051012437"],"corresponding_institution_ids":["https://openalex.org/I145722265","https://openalex.org/I4210134249"],"apc_list":null,"apc_paid":null,"fwci":1.6361,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88616506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":null,"first_page":"56","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T11478","display_name":"Caching and Content Delivery","score":0.9962999820709229,"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/T12238","display_name":"Green IT and Sustainability","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.825336217880249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7973953485488892},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7835575342178345},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.696692943572998},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.6807903051376343},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.617107093334198},{"id":"https://openalex.org/keywords/download","display_name":"Download","score":0.5995385050773621},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5757548213005066},{"id":"https://openalex.org/keywords/carbon-footprint","display_name":"Carbon footprint","score":0.5639931559562683},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4258146286010742},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.40125104784965515},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.35703712701797485},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.27731263637542725}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.825336217880249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973953485488892},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7835575342178345},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.696692943572998},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.6807903051376343},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.617107093334198},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.5995385050773621},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5757548213005066},{"id":"https://openalex.org/C2780936489","wikidata":"https://www.wikidata.org/wiki/Q310667","display_name":"Carbon footprint","level":3,"score":0.5639931559562683},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4258146286010742},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.40125104784965515},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.35703712701797485},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.27731263637542725},{"id":"https://openalex.org/C47737302","wikidata":"https://www.wikidata.org/wiki/Q167336","display_name":"Greenhouse gas","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/softcom.2014.7039136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/softcom.2014.7039136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 22nd International Conference on Software, Telecommunications and Computer Networks (SoftCOM)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.719.2574","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.719.2574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.aueb.gr/%7Ejordan/PAPERS/SOFTCOM-2014.pdf","raw_type":"text"},{"id":"pmh:oai:ir.lib.uth.gr:11615/28451","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/28451","pdf_url":null,"source":{"id":"https://openalex.org/S4306400243","display_name":"University of Thessaly Institutional Repository (University of Thessaly)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145722265","host_organization_name":"University of Thessaly","host_organization_lineage":["https://openalex.org/I145722265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.scopus.com/inward/record.url?eid=2-s2.0-84933558291&partnerID=40&md5=790d358cddcd7fbac3386c016d1c9b24","raw_type":"conferenceItem"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1566984846","https://openalex.org/W1929352279","https://openalex.org/W1977836056","https://openalex.org/W2018928332","https://openalex.org/W2029341294","https://openalex.org/W2066238258","https://openalex.org/W2091812828","https://openalex.org/W2107128713","https://openalex.org/W2119012894","https://openalex.org/W2127536142","https://openalex.org/W2128384372","https://openalex.org/W4211026344","https://openalex.org/W6634031162"],"related_works":["https://openalex.org/W1994958611","https://openalex.org/W2402678663","https://openalex.org/W3199173531","https://openalex.org/W2277785728","https://openalex.org/W2379145789","https://openalex.org/W4200125296","https://openalex.org/W2610451498","https://openalex.org/W2945544759","https://openalex.org/W2109463504","https://openalex.org/W1547088227"],"abstract_inverted_index":{"A":[0],"web":[1,8,84,91,106],"crawler":[2,179],"is":[3,96],"responsible":[4],"for":[5,16,134,198],"discovering":[6],"new":[7],"pages":[9,117],"on":[10,154],"the":[11,18,38,41,48,52,61,66,70,80,94,99,136,145,173,190,199],"Web":[12],"as":[13,15,54,140],"well":[14],"refreshing":[17],"content":[19],"of":[20,33,51,68,73,82,89,115,148,192,201],"already":[21],"downloaded":[22,116],"pages.":[23,63,168,193],"During":[24],"these":[25],"operations,":[26],"it":[27],"can":[28,184],"issue":[29],"a":[30,87,104,110,141,155,161,178],"huge":[31],"number":[32],"page":[34,137],"download":[35,138],"requests":[36,139],"to":[37,97,125,143,209],"servers":[39,53,123],"in":[40,45],"Web.":[42],"These":[43],"requests,":[44],"turn,":[46],"increase":[47],"energy":[49],"consumption":[50],"hardware":[55],"resources":[56],"are":[57],"used":[58],"when":[59],"serving":[60],"requested":[62],"This":[64],"has":[65],"side-effect":[67],"increasing":[69],"carbon":[71,100,119,174],"footprint":[72,101,175],"servers.":[74],"In":[75],"this":[76],"work,":[77],"we":[78],"introduce":[79],"problem":[81],"green":[83],"crawling":[85],"from":[86],"set":[88,158],"remote":[90,122],"servers,":[92],"where":[93,112],"goal":[95],"reduce":[98],"incurred":[102],"by":[103,177],"large-scale":[105,202],"crawler.":[107],"We":[108,130,151],"consider":[109],"scenario":[111],"both":[113],"freshness":[114,191],"and":[118],"emissions":[120],"at":[121],"need":[124,208],"be":[126,185],"taken":[127],"into":[128],"account.":[129],"present":[131],"various":[132],"heuristics":[133],"prioritizing":[135],"means":[142],"study":[144],"relative":[146],"importance":[147],"different":[149],"parameters.":[150],"conduct":[152],"experiments":[153],"real":[156],"data":[157],"that":[159,172],"involves":[160],"large":[162],"server":[163],"collection":[164],"involving":[165],"two":[166],"billion":[167],"The":[169],"results":[170],"indicate":[171],"generated":[176],"during":[180],"its":[181],"external":[182],"operations":[183],"considerably":[186],"reduced":[187],"without":[188],"compromising":[189],"Our":[194],"work":[195],"draws":[196],"guidelines":[197],"design":[200],"commercial":[203],"search":[204],"engine":[205],"companies,":[206],"which":[207],"comply":[210],"with":[211],"certain":[212],"greenness":[213],"regulations.":[214]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}