{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T13:51:02Z","timestamp":1784123462515,"version":"3.55.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T00:00:00Z","timestamp":1605225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T00:00:00Z","timestamp":1605225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s11227-020-03505-6","type":"journal-article","created":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T11:03:22Z","timestamp":1605265402000},"page":"5934-5959","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["The implementation of data storage and analytics platform for big data lake of electricity usage with spark"],"prefix":"10.1007","volume":"77","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9579-4426","authenticated-orcid":false,"given":"Chao-Tung","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tzu-Yang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Endah","family":"Kristiani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shyhtsun Felix","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,13]]},"reference":[{"issue":"10","key":"3505_CR1","doi-asserted-by":"publisher","first-page":"841","DOI":"10.14778\/2732951.2732958","volume":"7","author":"S Alsubaiee","year":"2014","unstructured":"Alsubaiee S, Behm A, Borkar V, Heilbron Z, Kim YS, Carey MJ, Dreseler M, Li C (2014) Storage management in asterixdb. Proc VLDB Endow 7(10):841\u2013852","journal-title":"Proc VLDB Endow"},{"key":"3505_CR2","doi-asserted-by":"crossref","unstructured":"Beheshti A, Benatallah B, Nouri R, Chhieng VM, Xiong H, Zhao X (2017) Coredb: a data lake service. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. ACM, pp 2451\u20132454","DOI":"10.1145\/3132847.3133171"},{"issue":"12","key":"3505_CR3","doi-asserted-by":"publisher","first-page":"1942","DOI":"10.14778\/3229863.3236230","volume":"11","author":"A Beheshti","year":"2018","unstructured":"Beheshti A, Benatallah B, Nouri R, Tabebordbar A (2018) Corekg: a knowledge lake service. Proc VLDB Endow 11(12):1942\u20131945","journal-title":"Proc VLDB Endow"},{"key":"3505_CR4","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.inffus.2017.09.005","volume":"41","author":"F Carcillo","year":"2018","unstructured":"Carcillo F, Dal Pozzolo A, Le Borgne YA, Caelen O, Mazzer Y, Bontempi G (2018) Scarff: a scalable framework for streaming credit card fraud detection with spark. Inf Fusion 41:182\u2013194","journal-title":"Inf Fusion"},{"key":"3505_CR5","doi-asserted-by":"crossref","unstructured":"Chen H, Chiang RH, Storey VC (2012) Business intelligence and analytics: from big data to big impact. MIS quarterly, pp 1165\u20131188","DOI":"10.2307\/41703503"},{"issue":"2","key":"3505_CR6","doi-asserted-by":"publisher","first-page":"77","DOI":"10.3745\/KTSDE.2015.4.2.77","volume":"4","author":"L Chen","year":"2015","unstructured":"Chen L, Ko J, Yeo J (2015) Analysis of the influence factors of data loading performance using apache sqoop. KIPS Trans Softw Data Eng 4(2):77\u201382","journal-title":"KIPS Trans Softw Data Eng"},{"key":"3505_CR7","doi-asserted-by":"crossref","unstructured":"Chen TY, Yang CT, Kristiani E, Cheng CT (2018) On construction of a power data lake platform using spark. In: International Conference on Frontier Computing. Springer, pp 99\u2013108","DOI":"10.1007\/978-981-13-3648-5_11"},{"key":"3505_CR8","doi-asserted-by":"crossref","unstructured":"Chou SC, Yang CT, Jiang FC, Chang CH (2018) The implementation of a data-accessing platform built from big data warehouse of electric loads. In: 2018 IEEE 42nd Annual Computer Software and Applications Conference (COMPSAC), vol\u00a02. IEEE, pp 87\u201392","DOI":"10.1109\/COMPSAC.2018.10208"},{"key":"3505_CR9","doi-asserted-by":"crossref","unstructured":"Fang H (2015) Managing data lakes in big data era: What\u2019s a data lake and why has it became popular in data management ecosystem. In: 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER). IEEE, pp 820\u2013824","DOI":"10.1109\/CYBER.2015.7288049"},{"key":"3505_CR10","doi-asserted-by":"crossref","unstructured":"Gruenheid A, Omiecinski E, Mark L (2011) Query optimization using column statistics in hive. In: Proceedings of the 15th symposium on international database engineering & applications. ACM, pp 97\u2013105","DOI":"10.1145\/2076623.2076636"},{"key":"3505_CR11","unstructured":"Gupta K, Sachdev A, Sureka A (2017) Empirical analysis on comparing the performance of alpha miner algorithm in sql query language and nosql column-oriented databases using apache phoenix. arXiv preprint arXiv:1703.05481"},{"key":"3505_CR12","doi-asserted-by":"crossref","unstructured":"Gupta M, Patwa F, Benson J, Sandhu R (2017) Multi-layer authorization framework for a representative hadoop ecosystem deployment. In: Proceedings of the 22nd ACM on symposium on access control models and technologies. ACM, pp 183\u2013190","DOI":"10.1145\/3078861.3084173"},{"key":"3505_CR13","doi-asserted-by":"crossref","unstructured":"Hai R, Geisler S, Quix C (2016) Constance: an intelligent data lake system. In: Proceedings of the 2016 International Conference on Management of Data. ACM, pp 2097\u20132100","DOI":"10.1145\/2882903.2899389"},{"key":"3505_CR14","doi-asserted-by":"crossref","unstructured":"John Walker S (2014) Big data: a revolution that will transform how we live, work, and think","DOI":"10.2501\/IJA-33-1-181-183"},{"key":"3505_CR15","doi-asserted-by":"crossref","unstructured":"Kathiravelu P, Sharma A (2016) A dynamic data warehousing platform for creating and accessing biomedical data lakes. In: VLDB workshop on data management and analytics for medicine and healthcare. Springer, pp 101\u2013120","DOI":"10.1007\/978-3-319-57741-8_7"},{"key":"3505_CR16","volume-title":"The data warehouse toolkit: the complete guide to dimensional modeling","author":"R Kimball","year":"2011","unstructured":"Kimball R, Ross M (2011) The data warehouse toolkit: the complete guide to dimensional modeling. Wiley, Hoboken"},{"key":"3505_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-018-0852-x","author":"PY Liu","year":"2018","unstructured":"Liu PY, Tsan YT, Chan YW, Chan WC, Shi ZY, Yang CT, Lou BS (2018) Associations of PM2.5 and aspergillosis: ambient fine particulate air pollution and population-based big data linkage analyses. J Ambient Intell Humaniz Comput. https:\/\/doi.org\/10.1007\/s12652-018-0852-x","journal-title":"J Ambient Intell Humaniz Comput"},{"key":"3505_CR18","doi-asserted-by":"crossref","unstructured":"Liu RH, Kuo CF, Yang CT, Chen ST, Liu JC (2016) On construction of an energy monitoring service using big data technology for smart campus. In: 2016 7th International Conference on Cloud Computing and Big Data (CCBD). IEEE, pp 81\u201386","DOI":"10.1109\/CCBD.2016.026"},{"issue":"5","key":"3505_CR19","doi-asserted-by":"publisher","first-page":"2732","DOI":"10.1109\/TFUZZ.2018.2812157","volume":"26","author":"B Ma\u0142ysiak-Mrozek","year":"2018","unstructured":"Ma\u0142ysiak-Mrozek B, Stabla M, Mrozek D (2018) Soft and declarative fishing of information in big data lake. IEEE Trans Fuzzy Syst 26(5):2732\u20132747","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"3505_CR20","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1016\/j.procs.2016.07.439","volume":"88","author":"N Miloslavskaya","year":"2016","unstructured":"Miloslavskaya N, Tolstoy A (2016) Big data, fast data and data lake concepts. Procedia Comput Sci 88:300\u2013305","journal-title":"Procedia Comput Sci"},{"key":"3505_CR21","doi-asserted-by":"crossref","unstructured":"Pal A, Jain K, Agrawal P, Agrawal S (2014) A performance analysis of mapreduce task with large number of files dataset in big data using hadoop. In: 2014 4th International Conference on Communication Systems and Network Technologies (CSNT). IEEE, pp 587\u2013591","DOI":"10.1109\/CSNT.2014.124"},{"key":"3505_CR22","doi-asserted-by":"crossref","unstructured":"Ramakrishnan R, Sridharan B, Douceur JR, Kasturi P, Krishnamachari-Sampath B, Krishnamoorthy K, Li P, Manu M, Michaylov S, Ramos R et al (2017) Azure data lake store: a hyperscale distributed file service for big data analytics. In: Proceedings of the 2017 ACM International Conference on Management of Data. ACM, pp 51\u201363","DOI":"10.1145\/3035918.3056100"},{"key":"3505_CR23","doi-asserted-by":"crossref","unstructured":"Rangarajan S, Liu H, Wang H, Wang CL (2015) Scalable architecture for personalized healthcare service recommendation using big data lake. In: Service research and innovation. Springer, pp 65\u201379","DOI":"10.1007\/978-3-319-76587-7_5"},{"key":"3505_CR24","doi-asserted-by":"crossref","unstructured":"Sun PL, Weng JY, Yang CT, Chen ST, Liu JC (2016) The implementation of air pollution monitoring service using hybrid database converter. In: 2016 7th International Conference on Cloud Computing and Big Data (CCBD). IEEE, pp 269\u2013274","DOI":"10.1109\/CCBD.2016.060"},{"key":"3505_CR25","unstructured":"Terrizzano IG, Schwarz PM, Roth M, Colino JE (2015) Data wrangling: the challenging yourney from the wild to the lake. In: CIDR"},{"key":"3505_CR26","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1016\/j.energy.2016.04.115","volume":"109","author":"LF Tratar","year":"2016","unstructured":"Tratar LF, Strm\u010dnik E (2016) The comparison of holt-winters method and multiple regression method: a case study. Energy 109:266\u2013276","journal-title":"Energy"},{"issue":"12","key":"3505_CR27","doi-asserted-by":"publisher","first-page":"1654","DOI":"10.14778\/2824032.2824063","volume":"8","author":"G Wang","year":"2015","unstructured":"Wang G, Koshy J, Subramanian S, Paramasivam K, Zadeh M, Narkhede N, Rao J, Kreps J, Stein J (2015) Building a replicated logging system with apache kafka. Proc VLDB Endow 8(12):1654\u20131655","journal-title":"Proc VLDB Endow"},{"key":"3505_CR28","doi-asserted-by":"crossref","unstructured":"Wang Y, Xu Y, Liu Y, Chen J, Hu S (2015) Qmapper for smart grid: migrating sql-based application to hive. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data. ACM, pp 647\u2013658","DOI":"10.1145\/2723372.2742792"},{"issue":"9","key":"3505_CR29","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1002\/dac.2417","volume":"25","author":"F Xia","year":"2012","unstructured":"Xia F, Yang LT, Wang L, Vinel A (2012) Internet of things. Int J Commun Syst 25(9):1101","journal-title":"Int J Commun Syst"},{"key":"3505_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2018.10.009","author":"CT Yang","year":"2018","unstructured":"Yang CT, Chen CJ, Tsan YT, Liu PY, Chan YW, Chan WC (2018) An implementation of real-time air quality and influenza-like illness data storage and processing platform. Comput Human Behav. https:\/\/doi.org\/10.1016\/j.chb.2018.10.009","journal-title":"Comput Human Behav"},{"key":"3505_CR31","doi-asserted-by":"crossref","unstructured":"Yang CT, Chen ST, Den W, Wang YT, Kristiani E (2018) Implementation of an intelligent indoor environmental monitoring and management system in cloud. Future Gener Comput Syst","DOI":"10.1016\/j.future.2018.02.041"},{"issue":"2","key":"3505_CR32","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1007\/s10586-017-0846-z","volume":"20","author":"CT Yang","year":"2017","unstructured":"Yang CT, Chen ST, Yan YZ (2017) The implementation of a cloud city traffic state assessment system using a novel big data architecture. Cluster Comput 20(2):1101\u20131121. https:\/\/doi.org\/10.1007\/s10586-017-0846-z","journal-title":"Cluster Comput"},{"issue":"10","key":"3505_CR33","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s10916-017-0777-5","volume":"41","author":"CT Yang","year":"2017","unstructured":"Yang CT, Liu JC, Chen ST, Lu HW (2017) Implementation of a big data accessing and processing platform for medical records in cloud. J Med Syst 41(10):149","journal-title":"J Med Syst"},{"key":"3505_CR34","doi-asserted-by":"crossref","unstructured":"Zhang C, Liu X (2013) Hbasemq: a distributed message queuing system on clouds with hbase. In: INFOCOM, 2013 Proceedings IEEE. IEEE, pp 40\u201344","DOI":"10.1109\/INFCOM.2013.6566731"},{"key":"3505_CR35","volume-title":"Understanding big data: analytics for enterprise class hadoop and streaming data","author":"P Zikopoulos","year":"2011","unstructured":"Zikopoulos P, Eaton C et al (2011) Understanding big data: analytics for enterprise class hadoop and streaming data. McGraw-Hill Osborne Media, New York"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03505-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-020-03505-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03505-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T12:11:16Z","timestamp":1620735076000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-020-03505-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,13]]},"references-count":35,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["3505"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03505-6","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,13]]},"assertion":[{"value":"29 October 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2020","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}