{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T12:49:39Z","timestamp":1790858979693,"version":"4.1.0"},"reference-count":141,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/P016448\/1"],"award-info":[{"award-number":["EP\/P016448\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2020.3046132","type":"journal-article","created":{"date-parts":[[2020,12,21]],"date-time":"2020-12-21T17:20:36Z","timestamp":1608571236000},"page":"15351-15374","source":"Crossref","is-referenced-by-count":18,"title":["Mapping the Big Data Landscape: Technologies, Platforms and Paradigms for Real-Time Analytics of Data Streams"],"prefix":"10.1109","volume":"9","author":[{"given":"Timothee","family":"Dubuc","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4860-0203","authenticated-orcid":false,"given":"Frederic","family":"Stahl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8913-4173","authenticated-orcid":false,"given":"Etienne B.","family":"Roesch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CTS.2013.6567203"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.39"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816764"},{"key":"ref32","year":"2013","journal-title":"The Four V’s of Big Data"},{"key":"ref31","article-title":"Extracting value from chaos","author":"gantz","year":"2011"},{"key":"ref30","article-title":"3D data management: Controlling data volume, velocity, and variety","author":"laney","year":"2001"},{"key":"ref37","year":"2010","journal-title":"Data Data Everywhere"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-73679-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-016-1677-z"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/ACCESS.2014.2332453","article-title":"Toward scalable systems for big data analytics: A technology tutorial","volume":"2","author":"hu","year":"2014","journal-title":"IEEE Access"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2010.5452747"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2764947.2764954"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-016-1742-7"},{"key":"ref20","first-page":"3169","article-title":"Real-time big data processing framework: Challenges and solutions","volume":"9","author":"zheng","year":"2015","journal-title":"Appl Math Inf Sci"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.08.003"},{"key":"ref21","first-page":"647","article-title":"Research status and scientific thinking of big data","volume":"27","author":"li","year":"2012","journal-title":"Bull Chin Acad Sci"},{"key":"ref24","author":"columbus","year":"2017","journal-title":"Big Data & Analytics Is The Most Wanted Expertise By 75% Of IoT Providers"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2014.07.006"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835958"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2014.2350490"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.07.286"},{"key":"ref50","article-title":"Condor: A distributed job scheduler","author":"tannenbaum","year":"2001","journal-title":"Beowulf Cluster Computing With Linux"},{"key":"ref51","year":"2021","journal-title":"HTCondor—Research Publications and Technical Information"},{"key":"ref59","author":"junqueira","year":"2016","journal-title":"Making Sense of Exactly-Once Semantic"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2001.914808"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2595641"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/103720.103722"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/564585.564601"},{"key":"ref54","first-page":"1","article-title":"GPFS: A shared-disk file system for large computing clusters","volume":"2","author":"schmuck","year":"2002","journal-title":"Proc FAST"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454166"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2010.5496972"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2788396"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2463724"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2650204"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.01.015"},{"key":"ref5","first-page":"35","article-title":"The Internet of Everything: How the network unleashes the benefits of Big Data","author":"pepper","year":"2014","journal-title":"Rewards and Risks of Big Data"},{"key":"ref8","first-page":"165","article-title":"Big data: Meaning, challenges, opportunities, tools","volume":"8","author":"parmar","year":"2017","journal-title":"Int J Adv Res Comput Sci"},{"key":"ref49","year":"2017","journal-title":"Apache Hadoop 2 9 0—Hadoop Fair Scheduler"},{"key":"ref7","author":"mashey","year":"1998","journal-title":"Big Data and the Next Wave of InfraStress Problems Solutions Opportunities"},{"key":"ref9","first-page":"180","article-title":"Den samhälleliga självreflexionens möjligheter?: Big data på 1980-talet","author":"gullberg","year":"1991","journal-title":"Fragment 80-Tal"},{"key":"ref46","article-title":"Fast first-come first served arbitration method","author":"khaira","year":"1996"},{"key":"ref45","first-page":"141","article-title":"Workload schedulers-genesis, algorithms and comparisons","volume":"4","author":"sliwko","year":"2015","journal-title":"International Journal of Software Engineering and Computing"},{"key":"ref48","year":"2017","journal-title":"Apache Hadoop 2 9 0—Hadoop Capacity Scheduler"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45540-X_6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfds.2015.07.002"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-014-0008-6"},{"key":"ref44","first-page":"13","volume":"44221","author":"etsion","year":"2005","journal-title":"A Short Survey of Commercial Cluster Batch Schedulers"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1108\/IDD-02-2018-0002"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.03.026"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2019.103451"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972764.29"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012722442-8\/50016-1"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.14778\/2733004.2733016"},{"key":"ref72","author":"marz","year":"2015","journal-title":"Big Data Principles and Best Practices of Scalable Real-time Data Systems"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2999852"},{"key":"ref71","first-page":"133","article-title":"Lambda architecture for real time big data analytic","author":"hasani","year":"2014","journal-title":"Proc ICT Innov Web"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref70","author":"hausenblas","year":"2017","journal-title":"Lambda Architecture"},{"key":"ref76","year":"2017","journal-title":"Welcome to Apache Hadoop!"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02711-1"},{"key":"ref77","first-page":"6","article-title":"HDFS scalability: The limits to growth","volume":"35","author":"shvachko","year":"2010","journal-title":"Login The Magazine of USENIX and SAGE"},{"key":"ref74","author":"kreps","year":"2014","journal-title":"Questioning the lambda architecture"},{"key":"ref75","author":"kleppmann","year":"2014","journal-title":"Turning the Database Inside Out With Apache Samza"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/s00354-006-0002-4"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1080\/10919392.2013.807713"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/507515.507521"},{"key":"ref78","first-page":"2","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"2012","journal-title":"Proc 9th USENIX Conf Netw Syst Des Implement"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972740.28"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522737"},{"key":"ref136","article-title":"MOSDEN: A scalable mobile collaborative platform for opportunistic sensing applications","author":"prakash jayaraman","year":"2014","journal-title":"arXiv 1405 5867"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2010.118"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.3390\/jsan6030017"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/WICT.2014.7077317"},{"key":"ref60","year":"2017","journal-title":"Apache Flink 1 3 Documentation Distributed Runtime Environment"},{"key":"ref139","first-page":"129","article-title":"Security analytics: Big data analytics for cybersecurity","author":"mahmood","year":"2013","journal-title":"Proc 2nd Nat Conf Inf Assurance (NCIA)"},{"key":"ref62","year":"2021","journal-title":"Cluster Mode Overview—Spark 2 2 0 Documentation"},{"key":"ref61","year":"2017","journal-title":"Apache Hadoop—2 9 0 Using CGroups With YARN"},{"key":"ref63","year":"2021","journal-title":"SAMZA"},{"key":"ref64","first-page":"10","article-title":"Spark: Cluster computing with working sets","author":"zaharia","year":"2010","journal-title":"Proc USENIX Conf Hot Topics in cloud Computing (HotCloud)"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/SERVICES.2015.12"},{"key":"ref65","first-page":"1","article-title":"BEOWULF: A parallel workstation for scientific computation","volume":"95","author":"becker","year":"1995","journal-title":"Proc Int Conf Parallel Process"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7295483"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4330020404"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"ref68","article-title":"MPI: A message-passing interface standard version 3.1","author":"schulz","year":"2016"},{"key":"ref2","author":"lohr","year":"2012","journal-title":"Opinion | Big Data’s Impact in the World"},{"key":"ref69","first-page":"107","article-title":"MapReduce: Simplified data processing on large clusters","volume":"51","author":"dean","year":"2004","journal-title":"Proc Symp Operating Syst Design Implementation"},{"key":"ref1","first-page":"24","article-title":"Are you ready for the era of ‘big data","volume":"4","author":"brown","year":"2011","journal-title":"McKinsey Quarterly"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/41.1-2.100"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2012.203"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972771.42"},{"key":"ref94","article-title":"Four trends in cloud computing CIOs should prepare for in 2019","author":"ashok","year":"2019"},{"key":"ref107","author":"han","year":"2011","journal-title":"Data Mining Concepts and Techniques"},{"key":"ref93","year":"2021","journal-title":"DB-Engines—Knowledge Base of Relational and NoSQL Database Management Systems"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398363"},{"key":"ref92","author":"peattie","year":"2021","journal-title":"The Bench Mark Database"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/543614.543615"},{"key":"ref91","year":"2019","journal-title":"Documentation Table of Contents—RabbitMQ"},{"key":"ref104","year":"2021","journal-title":"BigQuery Omni for Multi-Cloud Data Analytics"},{"key":"ref90","first-page":"1","article-title":"Kafka: A distributed messaging system for log processing","author":"kreps","year":"2011","journal-title":"Proc NET"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920886"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2971512"},{"key":"ref111","first-page":"1","article-title":"Stream data classification and adapting to gradual concept drift","volume":"2","author":"dongre","year":"0","journal-title":"Int J"},{"key":"ref112","first-page":"77","article-title":"Early drift detection method","author":"baena-garc\u00eda","year":"2006","journal-title":"Proc of First International Workshop on Knowledge Discovery in Data Streams"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-28645-5_29"},{"key":"ref98","article-title":"How Facebook knows what you really like","author":"metz","year":"2012"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2574766"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2503325"},{"key":"ref97","article-title":"Google’s Dremel makes big data look small","author":"metz","year":"2012"},{"key":"ref10","article-title":"Big data for big business? A taxonomy of data-driven business models used by start-up firms","author":"hartmann","year":"2014","journal-title":"Cambridge Service Alliance"},{"key":"ref11","first-page":"373","article-title":"The glass house effect: Big data, the new oil, and the power of analogy","volume":"66","author":"hirsch","year":"2014","journal-title":"Maine Law Review"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2015.7364082"},{"key":"ref13","author":"sieben","year":"2016","journal-title":"Labor Markets in 2040 Big Data Could Be a Big Deal for Jobseekers Monthly Labor Review U S Bureau of Labor Statistics"},{"key":"ref14","first-page":"1","article-title":"Organizing successfully for big data to transform organizations","author":"alexander","year":"2017","journal-title":"Proc AMCIS"},{"key":"ref15","author":"columbus","year":"2017","journal-title":"IBM Predicts Demand For Data Scientists Will Soar 28% By 2020"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.081"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SYSMART.2016.7894544"},{"key":"ref82","year":"2017","journal-title":"Flink Scalable Batch and Stream Data Processing"},{"key":"ref117","first-page":"1255","article-title":"Learning decision rules from data streams","volume":"22","author":"gama","year":"2011","journal-title":"Proc Int Joint Conf Artif Intell (IJCAI)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1515\/itit-2016-0002"},{"key":"ref81","first-page":"1","article-title":"Apache flink: Stream and batch processing in a single engine","volume":"36","author":"carbone","year":"2015","journal-title":"Bull IEEE Comput Soc Tech Committee Data Eng"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2013.2240732"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2015.2439695"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-013-0489-0"},{"key":"ref83","year":"2017","journal-title":"Apache Hadoop 2 9 0—Apache Hadoop YARN"},{"key":"ref114","first-page":"51","article-title":"VFML—A toolkit for mining high-speed time-changing data streams","volume":"51","author":"hulten","year":"2003","journal-title":"Softw Toolkit"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2900956"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/502512.502529"},{"key":"ref80","year":"2015","journal-title":"Apache Storm"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116900"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623609"},{"key":"ref89","author":"hoffman","year":"2013","journal-title":"Apache Flume Distributed Log Collection for Hadoop"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/2554850.2554855"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2954993"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/235968.233324"},{"key":"ref85","year":"2017","journal-title":"Apache Twill—Home"},{"key":"ref86","year":"2017","journal-title":"Apache Zookeeper"},{"key":"ref87","year":"2018","journal-title":"Apache Curator"},{"key":"ref88","year":"2021","journal-title":"HTCondor—What is HTCondor?"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09300187.pdf?arnumber=9300187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:49:54Z","timestamp":1641988194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9300187\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":141,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3046132","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}