{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T01:39:01Z","timestamp":1778549941858,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T00:00:00Z","timestamp":1589500800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T00:00:00Z","timestamp":1589500800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["690116"],"award-info":[{"award-number":["690116"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004901","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004901","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1007\/s11227-020-03307-w","type":"journal-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T11:17:09Z","timestamp":1589541429000},"page":"1321-1353","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Predicting the performance of big data applications on the cloud"],"prefix":"10.1007","volume":"77","author":[{"given":"D.","family":"Ardagna","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E.","family":"Barbierato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E.","family":"Gianniti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Gribaudo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T. B. M.","family":"Pinto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5951-3562","authenticated-orcid":false,"given":"A. P. C.","family":"da Silva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J. M.","family":"Almeida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,5,15]]},"reference":[{"key":"3307_CR1","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1145\/2611567","volume":"57","author":"HV Jagadish","year":"2014","unstructured":"Jagadish HV, Gehrke J, Labrinidis A, Papakonstantinou Y, Patel JM, Ramakrishnan R, Shahabi C (2014) Big data and its technical challenges. Commun ACM 57:86\u201394","journal-title":"Commun ACM"},{"key":"3307_CR2","doi-asserted-by":"crossref","unstructured":"Wang T, Wang J, Nguyen SN, Yang Z, Mi N, Sheng B (2017) Ea2s2: an efficient application-aware storage system for big data processing in heterogeneous clusters. In: 2017 26th International Conference on Computer Communication and Networks (ICCCN)","DOI":"10.1109\/ICCCN.2017.8038371"},{"issue":"4","key":"3307_CR3","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1530873.1530877","volume":"36","author":"M Bertoli","year":"2009","unstructured":"Bertoli M, Casale G, Serazzi G (2009) JMT: performance engineering tools for system modeling. SIGMETRICS Perform Eval Rev 36(4):10\u201315","journal-title":"SIGMETRICS Perform Eval Rev"},{"key":"3307_CR4","unstructured":"Chiola G (1985) A software package for the analysis of generalized stochastic petri net models. In: International Workshop on Timed Petri Nets, Torino, Italy, July 1\u20133, 1985, pp\u00a0136\u2013143"},{"issue":"6","key":"3307_CR5","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1109\/12.2213","volume":"37","author":"RD Nelson","year":"1988","unstructured":"Nelson RD, Tantawi AN (1988) Approximate analysis of fork\/join synchronization in parallel queues. IEEE Trans Comput 37(6):739\u2013743","journal-title":"IEEE Trans Comput"},{"issue":"3","key":"3307_CR6","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/71.80155","volume":"1","author":"V Mak","year":"1990","unstructured":"Mak V, Lundstrom S (1990) Predicting performance of parallel computations. IEEE Trans Parallel Distrib Syst 1(3):257\u2013270","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"5","key":"3307_CR7","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1109\/71.852402","volume":"11","author":"SK Tripathi","year":"2000","unstructured":"Tripathi SK, Liang D-R (2000) On performance prediction of parallel computations with precedent constraints. IEEE Trans Parallel Distrib Syst 11(5):491\u2013508","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"3","key":"3307_CR8","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/71.674321","volume":"9","author":"D Towsley","year":"1998","unstructured":"Towsley D, Lui JC, Muntz RR (1998) Computing performance bounds of fork\u2013join parallel programs under a multiprocessing environment. IEEE Trans Parallel Distrib Syst 9(3):295\u2013311","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3307_CR9","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1145\/233008.233048","volume":"24","author":"E Varki","year":"1996","unstructured":"Varki E, Dowdy LW (1996) Analysis of balanced fork\u2013join queueing networks. SIGMETRICS Perform Eval Rev 24:232\u2013241","journal-title":"SIGMETRICS Perform Eval Rev"},{"key":"3307_CR10","doi-asserted-by":"crossref","unstructured":"Ardagna D, Bernardi S, Gianniti E, Aliabadi SK, Perez-Palacin D, Requeno JI (2016) Modeling performance of hadoop applications: a journey from queueing networks to stochastic well formed nets, In: Algorithms and Architectures for Parallel Processing\u201416th International Conference, ICA3PP 2016, Granada, Spain, December 14\u201316, 2016, Proceedings, pp\u00a0599\u2013613","DOI":"10.1007\/978-3-319-49583-5_47"},{"key":"3307_CR11","unstructured":"Woodie A. A decade later, apache spark still going strong. https:\/\/www.datanami.com\/2019\/03\/08\/a-decade-later-apache-spark-still-going-strong\/. Accessed 7 Apr 2020"},{"key":"3307_CR12","volume-title":"Quantitative system performance","author":"ED Lazowska","year":"1984","unstructured":"Lazowska ED, Zahorjan J, Graham GS, Sevcik KC (1984) Quantitative system performance. Prentice-Hall, Englewood Cliffs"},{"key":"3307_CR13","doi-asserted-by":"crossref","unstructured":"Ardagna D, Barbierato E, Evangelinou A, Gianniti E, Gribaudo M, Pinto TBM, Guimar\u00e3es A, Couto\u00a0da Silva AP, Almeida JM (2018) Performance prediction of cloud-based big data applications, In: Proceedings of the 2018 ACM\/SPEC International Conference on Performance Engineering, ICPE\u201918 (New York, NY, USA). ACM, pp\u00a0192\u2013199","DOI":"10.1145\/3184407.3184420"},{"key":"3307_CR14","doi-asserted-by":"crossref","unstructured":"Trivedi K, Kulkarni V (1993) Fspns: fluid stochastic petri nets. In: Applications and Theory of Petri nets 1993 Proceedings of 14th International Conference (Berlin, Germany), Springer Verlag","DOI":"10.1007\/3-540-56863-8_38"},{"key":"3307_CR15","unstructured":"Badue CS, Almeida JM, Almeida VAF, Baeza-Yates RA, Ribeiro-Neto BA, Ziviani A, Ziviani N (2010) Capacity planning for vertical search engines. CoRR. Arxiv: abs\/1006.5059"},{"key":"3307_CR16","unstructured":"TPC. The TPC-DS benchmark. http:\/\/www.tpc.org\/tpcds\/. Accessed 7 Apr 2020"},{"issue":"3","key":"3307_CR17","doi-asserted-by":"publisher","first-page":"2575","DOI":"10.1007\/s10586-016-0723-1","volume":"20","author":"M Li","year":"2017","unstructured":"Li M, Tan J, Wang Y, Zhang L, Salapura V (2017) Sparkbench: a spark benchmarking suite characterizing large-scale in-memory data analytics. Cluster Comput 20(3):2575\u20132589","journal-title":"Cluster Comput"},{"issue":"14","key":"3307_CR18","first-page":"1678","volume":"6","author":"AD Popescu","year":"2013","unstructured":"Popescu AD, Balmin A, Ercegovac V, Ailamaki A (2013) Predict: towards predicting the runtime of large scale iterative analytics. PVLDB 6(14):1678\u20131689","journal-title":"PVLDB"},{"issue":"3","key":"3307_CR19","doi-asserted-by":"publisher","first-page":"15:1","DOI":"10.1145\/3309684","volume":"29","author":"J Bhimani","year":"2019","unstructured":"Bhimani J, Mi N, Leeser M, Yang Z (2019) New performance modeling methods for parallel data processing applications. ACM Trans Model Comput Simul 29(3):15:1\u201315:24","journal-title":"ACM Trans Model Comput Simul"},{"key":"3307_CR20","doi-asserted-by":"crossref","unstructured":"Wang K, Khan MMH (2015) Performance prediction for apache spark platform. In: HPCC\/CSS\/ICESS. IEEE, pp\u00a0166\u2013173","DOI":"10.1109\/HPCC-CSS-ICESS.2015.246"},{"key":"3307_CR21","doi-asserted-by":"crossref","unstructured":"Malakar P, Balaprakash P, Vishwanath V, Morozov V, Kumaran K (2018) Benchmarking machine learning methods for performance modeling of scientific applications, pp\u00a033\u201344, 11","DOI":"10.1109\/PMBS.2018.8641686"},{"key":"3307_CR22","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/MCI.2017.2773824","volume":"13","author":"J Riihijarvi","year":"2018","unstructured":"Riihijarvi J, Mahonen P (2018) Machine learning for performance prediction in mobile cellular networks. IEEE Comput Intell Mag 13:51\u201360","journal-title":"IEEE Comput Intell Mag"},{"key":"3307_CR23","doi-asserted-by":"crossref","unstructured":"Nemirovsky D, Arkose T, Markovic N, Nemirovsky M, Unsal O, Cristal A (2017) A machine learning approach for performance prediction and scheduling on heterogeneous CPUs. In: Proceedings of 29th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","DOI":"10.1109\/SBAC-PAD.2017.23"},{"key":"3307_CR24","doi-asserted-by":"crossref","unstructured":"Jamshidi P, Siegmund N, Velez M, K\u00e4stner C, Patel A, Agarwal Y (2017) Transfer learning for performance modeling of configurable systems: An exploratory analysis. In: Proceedings of the 32nd IEEE\/ACM International Conference on Automated Software Engineering, ASE 2017. IEEE Press, pp\u00a0497\u2013508","DOI":"10.1109\/ASE.2017.8115661"},{"key":"3307_CR25","doi-asserted-by":"crossref","unstructured":"Marathe A, Anirudh R, Jain N, Bhatele A, Thiagarajan JJ, Kailkhura B, Yeom J-S, Rountree B, Gamblin T (2017) Performance modeling under resource constraints using deep transfer learning. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","DOI":"10.1145\/3126908.3126969"},{"key":"3307_CR26","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1109\/71.852402","volume":"11","author":"D Liang","year":"2000","unstructured":"Liang D, Tripathi SK (2000) On performance prediction of parallel computations with precedent constraints. IEEE Trans Parallel Distrib Syst 11:491\u2013508","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3307_CR27","doi-asserted-by":"crossref","unstructured":"Reisig W, Rozenberg G, Thiagarajan PS (2013) In memoriam: Carl adam petri, In: Transactions on Petri Nets and Other Models of Concurrency VII (K.\u00a0Jensen, W.\u00a0M.\u00a0P. van\u00a0der Aalst, G.\u00a0Balbo, M.\u00a0Koutny, and K.\u00a0Wolf, eds.), pp.\u00a01\u20135, Berlin, Heidelberg: Springer Berlin Heidelberg","DOI":"10.1007\/978-3-642-38143-0_1"},{"key":"3307_CR28","unstructured":"Nicol DM, Miner AS (1995) The fluid stochastic petri net simulator. In: Proceedings of the Sixth International Workshop on Petri Nets and Performance Models, PNPM \u201995, (Washington, DC, USA). IEEE Computer Society, p\u00a0214"},{"key":"3307_CR29","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1016\/j.peva.2005.06.001","volume":"63","author":"G Ciardo","year":"2006","unstructured":"Ciardo G, Jones RL III, Miner AS, Siminiceanu RI (2006) Logic and stochastic modeling with SMART. Perform Eval 63:578\u2013608","journal-title":"Perform Eval"},{"key":"3307_CR30","doi-asserted-by":"crossref","unstructured":"Trivedi KS (2002) SHARPE 2002: symbolic hierarchical automated reliability and performance evaluator. In: DSN \u201902: Proceedings of the 2002 International Conference on Dependable Systems and Networks, (Washington, DC, USA). IEEE Computer Society, p\u00a0544","DOI":"10.1109\/DSN.2002.1028975"},{"key":"3307_CR31","first-page":"820","volume":"2013","author":"G Song","year":"2013","unstructured":"Song G, Meng Z, Huet F, Magoules F, Yu L et al (2013) A hadoop mapreduce performance prediction method. HPCC 2013:820\u2013825","journal-title":"HPCC"},{"issue":"4","key":"3307_CR32","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s10766-012-0227-4","volume":"41","author":"E Vianna","year":"2013","unstructured":"Vianna E, Comarela G, Pontes T, Almeida J, Almeida V, Wilkinson K, Kuno H, Dayal U (2013) Analytical performance models for mapreduce workloads. Int J Parallel Program 41(4):495\u2013525","journal-title":"Int J Parallel Program"},{"issue":"6","key":"3307_CR33","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1109\/TPDS.2013.297","volume":"25","author":"K Chen","year":"2014","unstructured":"Chen K, Powers J, Guo S, Tian F (2014) Cresp: towards optimal resource provisioning for mapreduce computing in public clouds. IEEE Trans Parallel Distrib Syst 25(6):1403\u20131412","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3307_CR34","unstructured":"Wang G, Butt AR, Pandey P, Gupta K (2009) A simulation approach to evaluating design decisions in mapreduce setups. In: MASCOTS. IEEE Computer Society, pp\u00a01\u201311"},{"key":"3307_CR35","volume-title":"Handbook of process algebra","year":"2001","unstructured":"Bergstra JA, Ponse A, Smolka SA (eds) (2001) Handbook of process algebra. Elsevier, New York"},{"key":"3307_CR36","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511569951","volume-title":"A compositional approach to performance modelling","author":"J Hillston","year":"1996","unstructured":"Hillston J (1996) A compositional approach to performance modelling. Cambridge University Press, New York"},{"issue":"11","key":"3307_CR37","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/2934664","volume":"59","author":"M Zaharia","year":"2016","unstructured":"Zaharia M, Xin RS, Wendell P, Das T, Armbrust M, Dave A, Meng X, Rosen J, Venkataraman S, Franklin MJ, Ghodsi A, Gonzalez J, Shenker S, Stoica I (2016) Apache spark: a unified engine for big data processing. Commun ACM 59(11):56\u201365","journal-title":"Commun ACM"},{"key":"3307_CR38","unstructured":"Microsoft (2020) What is PaaS?. https:\/\/azure.microsoft.com\/en-us\/overview\/what-is-paas\/. Accessed 05 Apr 2020"},{"key":"3307_CR39","unstructured":"Top 4 Apache Spark Use Cases. https:\/\/www.knowledgenile.com\/blogs\/apache-spark-use-cases\/. Accessed 9 Apr 2020"},{"key":"3307_CR40","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511810114","volume-title":"Data mining and analysis: fundamental concepts and algorithms","author":"MJ Zaki","year":"2014","unstructured":"Zaki MJ, Wagner Meira J (2014) Data mining and analysis: fundamental concepts and algorithms. Cambridge University Press, Cambridge"},{"key":"3307_CR41","unstructured":"Microsoft. Sizes for Windows virtual machines in Azure. https:\/\/docs.microsoft.com\/en-us\/azure\/virtual-machines\/windows\/sizes. Accessed 7 Apr 2020"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03307-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-020-03307-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03307-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,14]],"date-time":"2021-05-14T23:10:56Z","timestamp":1621033856000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-020-03307-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,15]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["3307"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03307-w","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,15]]},"assertion":[{"value":"15 May 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}