{"id":"https://openalex.org/W4381744387","doi":"https://doi.org/10.1109/cscwd57460.2023.10152783","title":"A Fault-tolerant and Cost-efficient Workflow Scheduling Approach Based on Deep Reinforcement Learning for IT Operation and Maintenance","display_name":"A Fault-tolerant and Cost-efficient Workflow Scheduling Approach Based on Deep Reinforcement Learning for IT Operation and Maintenance","publication_year":2023,"publication_date":"2023-05-24","ids":{"openalex":"https://openalex.org/W4381744387","doi":"https://doi.org/10.1109/cscwd57460.2023.10152783"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd57460.2023.10152783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd57460.2023.10152783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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/A5100572373","display_name":"Yunsong Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunsong Xiang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia,Beijing,China,100876"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032594076","display_name":"Xuemei Yang","orcid":"https://orcid.org/0000-0002-9306-9044"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemei Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia,Beijing,China,100876"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100986476","display_name":"Yan Sun","orcid":"https://orcid.org/0000-0001-6598-7940"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Sun","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia,Beijing,China,100876"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010337399","display_name":"Hong Luo","orcid":"https://orcid.org/0000-0002-0672-3440"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Luo","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia,Beijing,China,100876"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":2.5397,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90041109,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9940000176429749,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9940000176429749,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9933000206947327,"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/T10763","display_name":"Digital Transformation in Industry","score":0.9447000026702881,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/computer-science","display_name":"Computer science","score":0.8341418504714966},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7181794047355652},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6786791086196899},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6468138694763184},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6389586925506592},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.6288802623748779},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.58358234167099},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5804168581962585},{"id":"https://openalex.org/keywords/directed-acyclic-graph","display_name":"Directed acyclic graph","score":0.5082204341888428},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.21882227063179016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20667991042137146},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.182503342628479},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14561781287193298},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10464265942573547},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.09887745976448059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341418504714966},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7181794047355652},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6786791086196899},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6468138694763184},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6389586925506592},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.6288802623748779},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.58358234167099},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5804168581962585},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.5082204341888428},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.21882227063179016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20667991042137146},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.182503342628479},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14561781287193298},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10464265942573547},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.09887745976448059},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd57460.2023.10152783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd57460.2023.10152783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6499999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2731094954","https://openalex.org/W1981780420","https://openalex.org/W2789273959","https://openalex.org/W2182707996","https://openalex.org/W4302345037","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W188202134","https://openalex.org/W2952978498","https://openalex.org/W2774472052"],"abstract_inverted_index":{"With":[0],"the":[1,15,28,44,58,66,69,79,101,107,111,128,132,136,147,159,165,169,192,195,199],"promotion":[2],"of":[3,9,31,53,61,114,135,142,172,194,201],"cloud":[4,16,67],"computing,":[5],"a":[6,88,123],"large":[7],"number":[8],"hardware":[10],"and":[11,19,22,40,63,68,105,131,163],"software":[12],"systems":[13],"in":[14,65,82,146,178],"bring":[17],"massive":[18],"complex":[20],"operation":[21],"maintenance":[23],"(O&M)":[24],"work.":[25],"To":[26],"ensure":[27,164],"O&M":[29,55,84],"efficiency":[30],"IT":[32],"infrastructures,":[33],"it":[34],"is":[35,51],"necessary":[36],"to":[37,99,127,157,167],"implement":[38,106],"automatic":[39],"reliable":[41],"scheduling":[42,91,161],"for":[43],"directed":[45],"acyclic":[46],"graph":[47],"(DAG)":[48],"workflow":[49,90,102,197],"which":[50],"composed":[52],"multiple":[54],"tasks.":[56],"Considering":[57],"changing":[59],"status":[60],"networks":[62],"machines":[64,81],"position":[70,112,170],"constraints":[71,113,171],"that":[72,186],"some":[73,83],"tasks":[74,115,173],"must":[75],"be":[76],"executed":[77],"on":[78,94,198],"specified":[80],"scenarios,":[85],"we":[86,120,151],"propose":[87],"novel":[89],"approach":[92],"based":[93],"Deep":[95],"Reinforcement":[96],"Learning":[97],"(DRL)":[98],"minimize":[100],"execution":[103,174],"makespan":[104,193],"fault":[108],"tolerance":[109],"with":[110,140],"execution.":[116],"In":[117],"our":[118,187],"proposal,":[119],"first":[121],"design":[122],"fault-tolerant":[124,196],"mechanism":[125],"according":[126],"reliability":[129],"requirement":[130],"probability":[133],"distributions":[134],"machine":[137],"failure":[138,144],"parameters":[139],"consideration":[141],"different":[143],"rates":[145],"heterogeneous":[148],"environment.":[149],"Then,":[150],"employ":[152],"proximal":[153,179],"policy":[154,180],"optimization":[155],"(PPO)":[156],"optimize":[158],"task":[160],"strategy":[162,166],"satisfy":[168],"by":[175],"action":[176],"masking":[177],"optimization.":[181],"The":[182],"experimental":[183],"results":[184],"show":[185],"proposal":[188],"can":[189],"effectively":[190],"reduce":[191],"premise":[200],"99.9%":[202],"reliability.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}