{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T22:39:45Z","timestamp":1780439985740,"version":"3.54.1"},"reference-count":114,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,3,6]],"date-time":"2018-03-06T00:00:00Z","timestamp":1520294400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1007\/s41060-018-0107-0","type":"journal-article","created":{"date-parts":[[2018,3,6]],"date-time":"2018-03-06T14:48:40Z","timestamp":1520347720000},"page":"81-107","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["The many faces of data-centric workflow optimization: a survey"],"prefix":"10.1007","volume":"6","author":[{"given":"Georgia","family":"Kougka","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3976-7615","authenticated-orcid":false,"given":"Anastasios","family":"Gounaris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alkis","family":"Simitsis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,3,6]]},"reference":[{"key":"107_CR1","unstructured":"IBM infosphere datastage balanced optimization. http:\/\/www-01.ibm.com\/software\/data\/integration\/info_server\/ (2008). Accessed Jan 2018"},{"issue":"3","key":"107_CR2","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1145\/2694428.2694441","volume":"43","author":"DJ Abadi","year":"2014","unstructured":"Abadi, D.J., Agrawal, R., Ailamaki, A., Balazinska, M., Bernstein, P.A., Carey, M.J., Chaudhuri, S., Dean, J., Doan, A., Franklin, M.J., Gehrke, J., Haas, L.M., Halevy, A.Y., Hellerstein, J.M., Ioannidis, Y.E., Jagadish, H.V., Kossmann, D., Madden, S., Mehrotra, S., Milo, T., Naughton, J.F., Ramakrishnan, R., Markl, V., Olston, C., Ooi, B.C., R\u00e9, C., Suciu, D., Stonebraker, M., Walter, T., Widom, J.: The beckman report on database research. SIGMOD Rec. 43(3), 61\u201370 (2014)","journal-title":"SIGMOD Rec."},{"issue":"1","key":"107_CR3","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.future.2012.05.004","volume":"29","author":"S Abrishami","year":"2013","unstructured":"Abrishami, S., Naghibzadeh, M., Epema, D.H.: Deadline-constrained workflow scheduling algorithms for infrastructure as a service clouds. Future Gener. Comput. Syst. 29(1), 158\u2013169 (2013)","journal-title":"Future Gener. Comput. Syst."},{"issue":"8","key":"107_CR4","doi-asserted-by":"publisher","first-page":"1400","DOI":"10.1109\/TPDS.2011.303","volume":"23","author":"S Abrishami","year":"2012","unstructured":"Abrishami, S., Naghibzadeh, M., Epema, D.H.J.: Cost-driven scheduling of grid workflows using partial critical paths. IEEE Trans. Parallel Distrib. Syst. 23(8), 1400\u20131414 (2012)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"107_CR5","doi-asserted-by":"crossref","unstructured":"Agrawal, K., Benoit, A., Dufoss\u00e9, F., Robert, Y.: Mapping filtering streaming applications with communication costs. In: SPAA, pp. 19\u201328 (2009)","DOI":"10.1145\/1583991.1583997"},{"issue":"1\u20132","key":"107_CR6","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/s00453-010-9453-6","volume":"62","author":"K Agrawal","year":"2012","unstructured":"Agrawal, K., Benoit, A., Dufoss\u00e9, F., Robert, Y.: Mapping filtering streaming applications. Algorithmica 62(1\u20132), 258\u2013308 (2012)","journal-title":"Algorithmica"},{"key":"107_CR7","doi-asserted-by":"crossref","unstructured":"Agrawal, K., Benoit, A., Magnan, L., Robert, Y.: Scheduling algorithms for linear workflow optimization. In: IPDPS, pp. 1\u201312 (2010)","DOI":"10.1109\/IPDPS.2010.5470346"},{"issue":"6","key":"107_CR8","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1007\/s00778-014-0357-y","volume":"23","author":"A Alexandrov","year":"2014","unstructured":"Alexandrov, A., Bergmann, R., Ewen, S., Freytag, J., Hueske, F., Heise, A., Kao, O., Leich, M., Leser, U., Markl, V., Naumann, F., Peters, M., Rheinl\u00e4nder, A., Sax, M.J., Schelter, S., H\u00f6ger, M., Tzoumas, K., Warneke, D.: The stratosphere platform for big data analytics. VLDB J. 23(6), 939\u2013964 (2014)","journal-title":"VLDB J."},{"key":"107_CR9","doi-asserted-by":"crossref","unstructured":"Barker, A., van Hemert, J.I.: Scientific workflow: a survey and research directions. In: PPAM, Lecture Notes in Computer Science, vol. 4967, pp. 746\u2013753 (2007)","DOI":"10.1007\/978-3-540-68111-3_78"},{"issue":"4","key":"107_CR10","doi-asserted-by":"publisher","first-page":"50:1","DOI":"10.1145\/2501654.2501664","volume":"45","author":"A Benoit","year":"2013","unstructured":"Benoit, A., \u00c7ataly\u00fcrek, U.V., Robert, Y., Saule, E.: A survey of pipelined workflow scheduling: models and algorithms. ACM Comput. Surv. 45(4), 50:1\u201350:36 (2013)","journal-title":"ACM Comput. Surv."},{"key":"107_CR11","doi-asserted-by":"crossref","unstructured":"Bhattacharya, K., Hull, R., Su, J.: A data-centric design methodology for business processes. In: Handbook of Research on Business Process Modeling, Chapter 23, 503\u2013531 (2009)","DOI":"10.4018\/978-1-60566-288-6.ch023"},{"key":"107_CR12","unstructured":"B\u00f6hm, M.: Cost-based optimization of integration flows. Ph.D. thesis (2011)"},{"key":"107_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.is.2014.03.005","volume":"45","author":"M B\u00f6hm","year":"2014","unstructured":"B\u00f6hm, M., Habich, D., Lehner, W.: On-demand re-optimization of integration flows. Inf. Syst. 45, 1\u201317 (2014)","journal-title":"Inf. Syst."},{"issue":"7","key":"107_CR14","first-page":"553","volume":"7","author":"M B\u00f6hm","year":"2014","unstructured":"B\u00f6hm, M., Tatikonda, S., Reinwald, B., Sen, P., Tian, Y., Burdick, D., Vaithyanathan, S.: Hybrid parallelization strategies for large-scale machine learning in systemml. PVLDB 7(7), 553\u2013564 (2014)","journal-title":"PVLDB"},{"issue":"1","key":"107_CR15","first-page":"562","volume":"1","author":"D Braga","year":"2008","unstructured":"Braga, D., Ceri, S., Daniel, F., Martinenghi, D.: Optimization of multi-domain queries on the web. PVLDB 1(1), 562\u2013573 (2008)","journal-title":"PVLDB"},{"key":"107_CR16","unstructured":"Burge, J., Munagala, K., Srivastava, U.: Ordering pipelined query operators with precedence constraints. Technical Report 2005-40, Stanford InfoLab (2005)"},{"issue":"7","key":"107_CR17","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.1109\/TPDS.2013.238","volume":"25","author":"RN Calheiros","year":"2014","unstructured":"Calheiros, R.N., Buyya, R.: Meeting deadlines of scientific workflows in public clouds with tasks replication. IEEE Trans. Parallel Distrib. Syst. 25(7), 1787\u20131796 (2014)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"107_CR18","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S.: An overview of query optimization in relational systems. In: Proceedings of the Seventeenth ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems, June 1\u20133, 1998, Seattle, Washington, pp. 34\u201343 (1998)","DOI":"10.1145\/275487.275492"},{"key":"107_CR19","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1145\/1978542.1978562","volume":"54","author":"S Chaudhuri","year":"2011","unstructured":"Chaudhuri, S., Dayal, U., Narasayya, V.: An overview of business intelligence technology. Commun. ACM 54, 88\u201398 (2011)","journal-title":"Commun. ACM"},{"issue":"2","key":"107_CR20","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1145\/320248.320249","volume":"24","author":"S Chaudhuri","year":"1999","unstructured":"Chaudhuri, S., Shim, K.: Optimization of queries with user-defined predicates. ACM Trans. Database Syst. 24(2), 177\u2013228 (1999)","journal-title":"ACM Trans. Database Syst."},{"key":"107_CR21","doi-asserted-by":"crossref","unstructured":"Chen, W., Deelman, E.: Partitioning and scheduling workflows across multiple sites with storage constraints. In: Proceedings of the 9th International Conference on Parallel Processing and Applied Mathematics\u2014Volume Part II, PPAM\u201911, pp. 11\u201320 (2012)","DOI":"10.1007\/978-3-642-31500-8_2"},{"issue":"1","key":"107_CR22","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/TSMCC.2008.2001722","volume":"39","author":"WN Chen","year":"2009","unstructured":"Chen, W.N., Zhang, J.: An ant colony optimization approach to a grid workflow scheduling problem with various qos requirements. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 39(1), 29\u201343 (2009)","journal-title":"IEEE Trans. Syst. Man Cybern. Part C Appl. Rev."},{"key":"107_CR23","doi-asserted-by":"crossref","unstructured":"Chirkin, A.M., Belloum, A., Kovalchuk, S.V., Makkes, M.X.: Execution time estimation for workflow scheduling. In: Proceedings of the 9th Workshop on Workflows in Support of Large-Scale Science, pp. 1\u201310. IEEE Press (2014)","DOI":"10.1109\/WORKS.2014.11"},{"issue":"1","key":"107_CR24","doi-asserted-by":"publisher","first-page":"S12","DOI":"10.1186\/1471-2105-15-S1-S12","volume":"15","author":"S Cohen-Boulakia","year":"2014","unstructured":"Cohen-Boulakia, S., Chen, J., Goble, C., Missier, P., Williams, A., Froidevaux, C.: Distilling structure in taverna scientific workflows: a refactoring approach. BMC Bioinformatics 15(1), S12 (2014)","journal-title":"BMC Bioinformatics"},{"issue":"12","key":"107_CR25","first-page":"1466","volume":"8","author":"A Crotty","year":"2015","unstructured":"Crotty, A., Galakatos, A., Dursun, K., Kraska, T., Binnig, C., \u00c7etintemel, U., Zdonik, S.: An architecture for compiling udf-centric workflows. PVLDB 8(12), 1466\u20131477 (2015)","journal-title":"PVLDB"},{"key":"107_CR26","doi-asserted-by":"crossref","unstructured":"Curcin, V., Ghanem, M.: Scientific workflow systems\u2014can one size fit all? In: Biomedical Engineering Conference, 2008. CIBEC 2008. Cairo International, pp. 1\u20139 (2008)","DOI":"10.1109\/CIBEC.2008.4786077"},{"key":"107_CR27","doi-asserted-by":"crossref","unstructured":"Dayal, U., Castellanos, M., Simitsis, A., Wilkinson, K.: Data integration flows for business intelligence. In: Proceedings of EDBT, pp. 1\u201311 (2009)","DOI":"10.1145\/1516360.1516362"},{"issue":"1","key":"107_CR28","first-page":"61","volume":"3","author":"D Oliveira de","year":"2012","unstructured":"de Oliveira, D., Ogasawara, E.S., Dias, J., Baio, F.A., Mattoso, M.: Ontology-based semi-automatic workflow composition. JIDM 3(1), 61\u201372 (2012)","journal-title":"JIDM"},{"issue":"5","key":"107_CR29","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1016\/j.future.2008.06.012","volume":"25","author":"E Deelman","year":"2009","unstructured":"Deelman, E., Gannon, D., Shields, M., Taylor, I.: Workflows and e-science: an overview of workflow system features and capabilities. Future Gener. Comput. Syst. 25(5), 528\u2013540 (2009)","journal-title":"Future Gener. Comput. Syst."},{"issue":"3","key":"107_CR30","first-page":"219","volume":"13","author":"E Deelman","year":"2005","unstructured":"Deelman, E., Singh, G., Su, M.H., Blythe, J., Gil, Y., Kesselman, C., Mehta, G., Vahi, K., Berriman, G.B., Good, J., Laity, A., Jacob, J.C., Katz, D.S.: Pegasus: a framework for mapping complex scientific workflows onto distributed systems. Sci. Program. 13(3), 219\u2013237 (2005)","journal-title":"Sci. Program."},{"issue":"4","key":"107_CR31","doi-asserted-by":"publisher","first-page":"41:1","DOI":"10.1145\/2344422.2344431","volume":"8","author":"A Deshpande","year":"2012","unstructured":"Deshpande, A., Hellerstein, L.: Parallel pipelined filter ordering with precedence constraints. ACM Trans. Algorithms 8(4), 41:1\u201341:38 (2012)","journal-title":"ACM Trans. Algorithms"},{"key":"107_CR32","unstructured":"Dong, F., Akl, S.G.: Scheduling algorithms for grid computing: state of the art and open problems. Technical report (2006)"},{"issue":"6","key":"107_CR33","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1109\/TPDS.2012.257","volume":"24","author":"H Fard","year":"2013","unstructured":"Fard, H., Prodan, R., Fahringer, T.: A truthful dynamic workflow scheduling mechanism for commercial multicloud environments. IEEE Trans. Parallel Distrib. Syst. 24(6), 1203\u20131212 (2013)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"107_CR34","doi-asserted-by":"crossref","unstructured":"Florescu, D., Levy, A., Manolescu, I., Suciu, D.: Query optimization in the presence of limited access patterns. In: ACM SIGMOD, pp. 311\u2013322 (1999)","DOI":"10.1145\/304182.304210"},{"key":"107_CR35","volume-title":"Database Systems: The Complete Book","author":"H Garcia-Molina","year":"2001","unstructured":"Garcia-Molina, H., Ullman, J.D., Widom, J.D.: Database Systems: The Complete Book. Prentice Hall, Upper Saddle River (2001)"},{"key":"107_CR36","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2647939","author":"A Gounaris","year":"2017","unstructured":"Gounaris, A., Kougka, G., Tous, R., Tripiana, C., Torres, J.: Dynamic configuration of partitioning in spark applications. IEEE Trans. Parallel Distrib. Syst. (2017). https:\/\/doi.org\/10.1109\/TPDS.2017.2647939","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"3","key":"107_CR37","doi-asserted-by":"publisher","first-page":"37:1","DOI":"10.1145\/2480741.2480754","volume":"45","author":"X Grehant","year":"2013","unstructured":"Grehant, X., Demeure, I., Jarp, S.: A survey of task mapping on production grids. ACM Comput. Surv. 45(3), 37:1\u201337:25 (2013)","journal-title":"ACM Comput. Surv."},{"key":"107_CR38","doi-asserted-by":"crossref","unstructured":"Gu, Y., Wu, Q., Rao, N.S.V.: Analyzing execution dynamics of scientific workflows for latency minimization in resource sharing environments. In: Proceedings of the 2011 IEEE World Congress on Services, pp. 153\u2013160 (2011)","DOI":"10.1109\/SERVICES.2011.54"},{"key":"107_CR39","unstructured":"Halasipuram, R., Deshpande, P.M., Padmanabhan, S.: Determining essential statistics for cost based optimization of an ETL workflow. In: EDBT, pp. 307\u2013318 (2014)"},{"issue":"2","key":"107_CR40","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1145\/292481.277627","volume":"23","author":"JM Hellerstein","year":"1998","unstructured":"Hellerstein, J.M.: Optimization techniques for queries with expensive methods. ACM Trans. Database Syst. 23(2), 113\u2013157 (1998)","journal-title":"ACM Trans. Database Syst."},{"issue":"11","key":"107_CR41","first-page":"1111","volume":"4","author":"H Herodotou","year":"2011","unstructured":"Herodotou, H., Babu, S.: Profiling, what-if analysis, and cost-based optimization of mapreduce programs. PVLDB 4(11), 1111\u20131122 (2011)","journal-title":"PVLDB"},{"key":"107_CR42","doi-asserted-by":"crossref","unstructured":"Holl, S., Zimmermann, O., Hofmann-Apitius, M.: A new optimization phase for scientific workflow management systems. In: eScience, pp. 1\u20138 (2012)","DOI":"10.1109\/eScience.2012.6404479"},{"key":"107_CR43","doi-asserted-by":"crossref","unstructured":"Holzinger, A., Stocker, C., Ofner, B., Prohaska, G., Brabenetz, A., Hofmann-Wellenhof, R.: Combining HCI, natural language processing, and knowledge discovery\u2014potential of IBM content analytics as an assistive technology in the biomedical field. In: Human\u2013Computer Interaction and Knowledge Discovery in Complex, Unstructured, Big Data\u2014Third International Workshop, HCI-KDD, pp. 13\u201324 (2013)","DOI":"10.1007\/978-3-642-39146-0_2"},{"key":"107_CR44","doi-asserted-by":"crossref","unstructured":"Huang, B., Babu, S., Yang, J.: Cumulon: optimizing statistical data analysis in the cloud. In: Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, pp. 1\u201312 (2013)","DOI":"10.1145\/2463676.2465273"},{"key":"107_CR45","doi-asserted-by":"crossref","unstructured":"Huang, B., B\u00f6hm, M., Tian, Y., Reinwald, B., Tatikonda, S., Reiss, F.R.: Resource elasticity for large-scale machine learning. In: SIGMOD\u201915, pp. 137\u2013152 (2015)","DOI":"10.1145\/2723372.2749432"},{"issue":"3","key":"107_CR46","doi-asserted-by":"publisher","first-page":"156","DOI":"10.14778\/2850583.2850590","volume":"9","author":"B Huang","year":"2015","unstructured":"Huang, B., Jarrett, N.W.D., Babu, S., Mukherjee, S., Yang, J.: C\u00fcm\u00fcl\u00f6n: Matrix-based data analytics in the cloud with spot instances. Proc. VLDB Endow. 9(3), 156\u2013167 (2015)","journal-title":"Proc. VLDB Endow."},{"issue":"11","key":"107_CR47","first-page":"1256","volume":"5","author":"F Hueske","year":"2012","unstructured":"Hueske, F., Peters, M., Sax, M., Rheinl\u00e4nder, A., Bergmann, R., Krettek, A., Tzoumas, K.: Opening the black boxes in data flow optimization. PVLDB 5(11), 1256\u20131267 (2012)","journal-title":"PVLDB"},{"key":"107_CR48","unstructured":"Informatica: How to achieve flexible, cost-effective scalability and performance through pushdown processing. White Paper (2007)"},{"issue":"1","key":"107_CR49","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1145\/234313.234367","volume":"28","author":"YE Ioannidis","year":"1996","unstructured":"Ioannidis, Y.E.: Query optimization. ACM Comput. Surv. 28(1), 121\u2013123 (1996)","journal-title":"ACM Comput. Surv."},{"key":"107_CR50","doi-asserted-by":"crossref","unstructured":"Jin, T., Zhang, F., Sun, Q., Bui, H., Parashar, M., Yu, H., Klasky, S., Podhorszki, N., Abbasi, H.: Using cross-layer adaptations for dynamic data management in large scale coupled scientific workflows. In: International Conference for High Performance Computing, Networking, Storage and Analysis, SC\u201913, p.\u00a074 (2013)","DOI":"10.1145\/2503210.2503301"},{"key":"107_CR51","doi-asserted-by":"crossref","unstructured":"Jovanovic, P., Romero, O., Abell\u00f3, A.: A unified view of data-intensive flows in business intelligence systems: a survey. In: Transactions on Large-Scale Data- and Knowledge-Centered Systems XXIX, pp. 66\u2013107. Springer, Berlin (2016)","DOI":"10.1007\/978-3-662-54037-4_3"},{"issue":"5","key":"107_CR52","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1109\/TKDE.2016.2515609","volume":"28","author":"P Jovanovic","year":"2016","unstructured":"Jovanovic, P., Romero, O., Simitsis, A., Abell, A.: Incremental consolidation of data-intensive multi-flows. IEEE Trans. Knowl. Data Eng. 28(5), 1203\u20131216 (2016)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"107_CR53","doi-asserted-by":"crossref","unstructured":"Jovanovic, P., Simitsis, A., Wilkinson, K.: Babbleflow: a translator for analytic data flow programs. In: SIGMOD, pp. 713\u2013716 (2014)","DOI":"10.1145\/2588555.2594534"},{"key":"107_CR54","doi-asserted-by":"crossref","unstructured":"Jovanovic, P., Simitsis, A., Wilkinson, K.: Engine independence for logical analytic flows. In: ICDE, pp. 1060\u20131071 (2014)","DOI":"10.1109\/ICDE.2014.6816723"},{"issue":"3","key":"107_CR55","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1016\/j.future.2012.08.015","volume":"29","author":"G Juve","year":"2013","unstructured":"Juve, G., Chervenak, A.L., Deelman, E., Bharathi, S., Mehta, G., Vahi, K.: Characterizing and profiling scientific workflows. Future Gener. Comput. Syst. 29(3), 682\u2013692 (2013)","journal-title":"Future Gener. Comput. Syst."},{"issue":"6","key":"107_CR56","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1016\/j.is.2012.12.001","volume":"38","author":"A Karagiannis","year":"2013","unstructured":"Karagiannis, A., Vassiliadis, P., Simitsis, A.: Scheduling strategies for efficient ETL execution. Inf. Syst. 38(6), 927\u2013945 (2013)","journal-title":"Inf. Syst."},{"key":"107_CR57","doi-asserted-by":"crossref","unstructured":"Kllapi, H., Sitaridi, E., Tsangaris, M.M., Ioannidis, Y.: Schedule optimization for data processing flows on the cloud. In: Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data, pp. 289\u2013300 (2011)","DOI":"10.1145\/1989323.1989355"},{"key":"107_CR58","doi-asserted-by":"crossref","unstructured":"Kougka, G., Gounaris, A.: Declarative expression and optimization of data-intensive flows. In: DaWaK, pp. 13\u201325 (2013)","DOI":"10.1007\/978-3-642-40131-2_2"},{"key":"107_CR59","doi-asserted-by":"crossref","unstructured":"Kougka, G., Gounaris, A.: Optimization of data-intensive flows: is it needed? is it solved? In: Proceedings of the 17th International Workshop on Data Warehousing and OLAP, DOLAP 2014, Shanghai, November 3\u20137, 2014, pp. 95\u201398 (2014)","DOI":"10.1145\/2666158.2666174"},{"key":"107_CR60","doi-asserted-by":"crossref","unstructured":"Kougka, G., Gounaris, A.: Cost optimization of data flows based on task re-ordering. In: LNCS Transactions on Large-Scale Data- and Knowledge-Centered Systems (2017, to appear)","DOI":"10.1007\/978-3-662-55696-2_4"},{"key":"107_CR61","doi-asserted-by":"crossref","unstructured":"Kougka, G., Gounaris, A.: Optimal task ordering in chain data flows: exploring the practicality of non-scalable solutions. In: DaWaK (2017)","DOI":"10.1007\/978-3-319-64283-3_2"},{"key":"107_CR62","doi-asserted-by":"crossref","unstructured":"Kougka, G., Gounaris, A., Leser, U.: Modeling data flow execution in a parallel environment. In: DaWaK (2017)","DOI":"10.1007\/978-3-319-64283-3_14"},{"key":"107_CR63","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/j.future.2014.11.011","volume":"45","author":"G Kougka","year":"2015","unstructured":"Kougka, G., Gounaris, A., Tsichlas, K.: Practical algorithms for execution engine selection in data flows. Future Gener. Comput. Syst. 45, 133\u2013148 (2015)","journal-title":"Future Gener. Comput. Syst."},{"key":"107_CR64","unstructured":"Krishnamurthy, R., Boral, H., Zaniolo, C.: Optimization of nonrecursive queries. In: VLDB, pp. 128\u2013137 (1986)"},{"key":"107_CR65","doi-asserted-by":"crossref","unstructured":"Kumar, N., Kumar, P.S.: An efficient heuristic for logical optimization of ETL workflows. In: BIRTE, pp. 68\u201383 (2010)","DOI":"10.1007\/978-3-642-22970-1_6"},{"key":"107_CR66","doi-asserted-by":"crossref","unstructured":"Kumar, V.S., Sadayappan, P., Mehta, G., Vahi, K., Deelman, E., Ratnakar, V., Kim, J., Gil, Y., Hall, M., Kurc, T., Saltz, J.: An integrated framework for parameter-based optimization of scientific workflows. In: HPDC, pp. 177\u2013186 (2009)","DOI":"10.1145\/1551609.1551638"},{"key":"107_CR67","doi-asserted-by":"crossref","unstructured":"Kumbhare, A.G., Simmhan, Y., Prasanna, V.K.: Exploiting application dynamism and cloud elasticity for continuous dataflows. In: SC, p.\u00a057 (2013)","DOI":"10.1145\/2503210.2503240"},{"issue":"6","key":"107_CR68","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1016\/j.future.2007.07.009","volume":"24","author":"D Kyriazis","year":"2008","unstructured":"Kyriazis, D., Tserpes, K., Menychtas, A., Litke, A., Varvarigou, T.A.: An innovative workflow mapping mechanism for grids in the frame of quality of service. Future Gener. Comput. Syst. 24(6), 498\u2013511 (2008)","journal-title":"Future Gener. Comput. Syst."},{"issue":"3","key":"107_CR69","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s00778-002-0085-6","volume":"12","author":"C Li","year":"2003","unstructured":"Li, C.: Computing complete answers to queries in the presence of limited access patterns. VLDB J. 12(3), 211\u2013227 (2003)","journal-title":"VLDB J."},{"issue":"11","key":"107_CR70","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.14778\/2350229.2350239","volume":"5","author":"H Lim","year":"2012","unstructured":"Lim, H., Herodotou, H., Babu, S.: Stubby: a transformation-based optimizer for mapreduce workflows. Proc. VLDB Endow. 5(11), 1196\u20131207 (2012)","journal-title":"Proc. VLDB Endow."},{"issue":"4","key":"107_CR71","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10723-015-9329-8","volume":"13","author":"J Liu","year":"2015","unstructured":"Liu, J., Pacitti, E., Valduriez, P., Mattoso, M.: A survey of data-intensive scientific workflow management. J. Grid Comput. 13(4), 457\u2013493 (2015)","journal-title":"J. Grid Comput."},{"key":"107_CR72","doi-asserted-by":"crossref","unstructured":"Liu, X., Iftikhar, N.: An ETL optimization framework using partitioning and parallelization. In: SAC\u201915 (2015)","DOI":"10.1145\/2695664.2695846"},{"key":"107_CR73","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1613\/jair.4377","volume":"51","author":"P Nguyen","year":"2014","unstructured":"Nguyen, P., Hilario, M., Kalousis, A.: Using meta-mining to support data mining workflow planning and optimization. J. Artif. Intell. Res. 51, 605\u2013644 (2014)","journal-title":"J. Artif. Intell. Res."},{"issue":"12","key":"107_CR74","first-page":"1328","volume":"4","author":"ES Ogasawara","year":"2011","unstructured":"Ogasawara, E.S., de Oliveira, D., Valduriez, P., Dias, J., Porto, F., Mattoso, M.: An algebraic approach for data-centric scientific workflows. PVLDB 4(12), 1328\u20131339 (2011)","journal-title":"PVLDB"},{"key":"107_CR75","doi-asserted-by":"crossref","unstructured":"Olston, C., Reed, B., Srivastava, U., Kumar, R., Tomkins, A.: Pig latin: a not-so-foreign language for data processing. In: SIGMOD Conference, pp. 1099\u20131110 (2008)","DOI":"10.1145\/1376616.1376726"},{"key":"107_CR76","doi-asserted-by":"crossref","unstructured":"Pietri, I., Juve, G., Deelman, E., Sakellariou, R.: A performance model to estimate execution time of scientific workflows on the cloud. In: Proceedings of the 9th Workshop on Workflows in Support of Large-Scale Science, pp. 11\u201319. IEEE Press (2014)","DOI":"10.1109\/WORKS.2014.12"},{"issue":"5","key":"107_CR77","doi-asserted-by":"publisher","first-page":"890","DOI":"10.1109\/TPDS.2011.221","volume":"23","author":"K Plankensteiner","year":"2012","unstructured":"Plankensteiner, K., Prodan, R.: Meeting soft deadlines in scientific workflows using resubmission impact. IEEE Trans. Parallel Distrib. Syst. 23(5), 890\u2013901 (2012)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"107_CR78","doi-asserted-by":"crossref","unstructured":"Preda, N., Kasneci, G., Suchanek, F.M., Neumann, T., Yuan, W., Weikum, G.: Active knowledge: dynamically enriching RDF knowledge bases by web services. In: Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2010, Indianapolis, IN, June 6\u201310, 2010, pp. 399\u2013410 (2010)","DOI":"10.1145\/1807167.1807212"},{"key":"107_CR79","doi-asserted-by":"crossref","unstructured":"Quiroz, A., Huang, E., Ceriani, L.: A robust and extensible tool for data integration using data type models. In: Proceedings of the Twenty-Ninth AAAI, pp. 3993\u20133998 (2015)","DOI":"10.1609\/aaai.v29i2.19060"},{"issue":"13","key":"107_CR80","doi-asserted-by":"publisher","first-page":"1816","DOI":"10.1002\/cpe.3003","volume":"25","author":"M Rahman","year":"2013","unstructured":"Rahman, M., Hassan, M.R., Ranjan, R., Buyya, R.: Adaptive workflow scheduling for dynamic grid and cloud computing environment. Concurr. Comput. Pract. Exp. 25(13), 1816\u20131842 (2013)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"107_CR81","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.is.2015.04.002","volume":"52","author":"A Rheinl\u00e4nder","year":"2015","unstructured":"Rheinl\u00e4nder, A., Heise, A., Hueske, F., Leser, U., Naumann, F.: SOFA: an extensible logical optimizer for udf-heavy data flows. Inf. Syst. 52, 96\u2013125 (2015)","journal-title":"Inf. Syst."},{"key":"107_CR82","doi-asserted-by":"publisher","first-page":"1837","DOI":"10.1002\/cpe.1317","volume":"20","author":"E Schikuta","year":"2008","unstructured":"Schikuta, E., Wanek, H., Ul Haq, I.: Grid workflow optimization regarding dynamically changing resources and conditions. Concurr. Comput. Pract. Exp. 20, 1837\u20131849 (2008)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"107_CR83","doi-asserted-by":"crossref","unstructured":"Selinger, P.G., Astrahan, M.M., Chamberlin, D.D., Lorie, R.A., Price, T.G.: Access path selection in a relational database management system. In: Proceedings of the 1979 ACM SIGMOD International Conference on Management of Data, pp. 23\u201334 (1979)","DOI":"10.1145\/582095.582099"},{"issue":"13","key":"107_CR84","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.14778\/2733004.2733005","volume":"7","author":"J Shi","year":"2014","unstructured":"Shi, J., Zou, J., Lu, J., Cao, Z., Li, S., Wang, C.: MRTuner: a toolkit to enable holistic optimization for mapreduce jobs. Proc. VLDB Endow. 7(13), 1319\u20131330 (2014)","journal-title":"Proc. VLDB Endow."},{"key":"107_CR85","unstructured":"Shivam, P., Babu, S., Chase, J.S.: Active and accelerated learning of cost models for optimizing scientific applications. In: VLDB, pp. 535\u2013546 (2006)"},{"key":"107_CR86","doi-asserted-by":"crossref","unstructured":"Simitsis, A., Vassiliadis, P., Dayal, U., Karagiannis, A., Tziovara, V.: Benchmarking ETL workflows. In: TPCTC 2009, 199\u2013220 (2009)","DOI":"10.1007\/978-3-642-10424-4_15"},{"issue":"10","key":"107_CR87","doi-asserted-by":"publisher","first-page":"1404","DOI":"10.1109\/TKDE.2005.169","volume":"17","author":"A Simitsis","year":"2005","unstructured":"Simitsis, A., Vassiliadis, P., Sellis, T.K.: State-space optimization of ETL workflows. IEEE Trans. Knowl. Data Eng. 17(10), 1404\u20131419 (2005)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"107_CR88","doi-asserted-by":"crossref","unstructured":"Simitsis, A., Wilkinson, K.: Revisiting ETL benchmarking: the case for hybrid flows. In: TPCTC, pp. 75\u201391 (2012)","DOI":"10.1007\/978-3-642-36727-4_6"},{"key":"107_CR89","doi-asserted-by":"crossref","unstructured":"Simitsis, A., Wilkinson, K., Castellanos, M., Dayal, U.: QoX-driven ETL design: reducing the cost of ETL consulting engagements. In: Proceedings of the SIGMOD, pp. 953\u2013960 (2009)","DOI":"10.1145\/1559845.1559954"},{"key":"107_CR90","doi-asserted-by":"crossref","unstructured":"Simitsis, A., Wilkinson, K., Castellanos, M., Dayal, U.: Optimizing analytic data flows for multiple execution engines. In: SIGMOD Conference, pp. 829\u2013840 (2012)","DOI":"10.1145\/2213836.2213963"},{"issue":"3","key":"107_CR91","first-page":"303","volume":"128","author":"A Simitsis","year":"2013","unstructured":"Simitsis, A., Wilkinson, K., Dayal, U.: Hybrid analytic flows\u2014the case for optimization. Fund. Inf. 128(3), 303\u2013335 (2013)","journal-title":"Fund. Inf."},{"key":"107_CR92","doi-asserted-by":"crossref","unstructured":"Simitsis, A., Wilkinson, K., Dayal, U., Castellanos, M.: Optimizing ETL workflows for fault-tolerance. In: ICDE, pp. 385\u2013396 (2010)","DOI":"10.1109\/ICDE.2010.5447816"},{"key":"107_CR93","doi-asserted-by":"crossref","unstructured":"Simitsis, A., Wilkinson, K., Dayal, U., Hsu, M.: HFMS: managing the lifecycle and complexity of hybrid analytic data flows. In: ICDE, pp. 1174\u20131185 (2013)","DOI":"10.1109\/ICDE.2013.6544907"},{"key":"107_CR94","unstructured":"Srivastava, U., Munagala, K., Widom, J., Motwani, R.: Query optimization over web services. In: Proceedings of VLDB, pp. 355\u2013366 (2006)"},{"key":"107_CR95","doi-asserted-by":"crossref","unstructured":"Tan, W., Sun, Y., Lu, G., Tang, A., Cui, L.: Trust services-oriented multi-objects workflow scheduling model for cloud computing. In: ICPCA\/SWS, pp. 617\u2013630 (2012)","DOI":"10.1007\/978-3-642-37015-1_54"},{"key":"107_CR96","doi-asserted-by":"crossref","unstructured":"Tao, F., Zhang, L., Laili, Y.: Configurable Intelligent Optimization Algorithm: Design and Practice in Manufacturing. Springer, New York, Incorporated (2014)","DOI":"10.1007\/978-3-319-08840-2"},{"key":"107_CR97","doi-asserted-by":"crossref","unstructured":"Tsamoura, E., Gounaris, A., Manolopoulos, Y.: Brief announcement: on the quest of optimal service ordering in decentralized queries. In: Proceedings of the 29th Annual ACM Symposium on Principles of Distributed Computing, PODC 2010, Zurich, July 25\u201328, 2010, pp. 277\u2013278 (2010)","DOI":"10.1145\/1835698.1835763"},{"issue":"3","key":"107_CR98","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1016\/j.future.2010.07.009","volume":"27","author":"E Tsamoura","year":"2011","unstructured":"Tsamoura, E., Gounaris, A., Manolopoulos, Y.: Decentralized execution of linear workflows over web services. Future Gener. Comput. Syst. 27(3), 341\u2013347 (2011)","journal-title":"Future Gener. Comput. Syst."},{"issue":"2","key":"107_CR99","first-page":"1","volume":"1","author":"E Tsamoura","year":"2011","unstructured":"Tsamoura, E., Gounaris, A., Manolopoulos, Y.: Optimal service ordering in decentralized queries over web services. IJKBO 1(2), 1\u201316 (2011)","journal-title":"IJKBO"},{"key":"107_CR100","doi-asserted-by":"crossref","unstructured":"Tsamoura, E., Gounaris, A., Manolopoulos, Y.: Queries over web services. In: New Directions in Web Data Management, vol. 1, pp. 139\u2013169 (2011)","DOI":"10.1007\/978-3-642-17551-0_6"},{"key":"107_CR101","doi-asserted-by":"crossref","unstructured":"Tziovara, V., Vassiliadis, P., Simitsis, A.: Deciding the physical implementation of ETL workflows. In: Proceedings of the ACM 10th International Workshop on Data Warehousing and OLAP DOLAP, pp. 49\u201356 (2007)","DOI":"10.1145\/1317331.1317341"},{"issue":"1","key":"107_CR102","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1093\/comjnl\/24.1.83","volume":"24","author":"YL Varol","year":"1981","unstructured":"Varol, Y.L., Rotem, D.: An algorithm to generate all topological sorting arrangements. Comput. J. 24(1), 83\u201384 (1981)","journal-title":"Comput. J."},{"issue":"3","key":"107_CR103","first-page":"1","volume":"5","author":"P Vassiliadis","year":"2009","unstructured":"Vassiliadis, P.: A survey of extract\u2013transform\u2013load technology. IJDWM 5(3), 1\u201327 (2009)","journal-title":"IJDWM"},{"key":"107_CR104","unstructured":"Vassiliadis, P., Simitsis, A., Baikousi, E.: A taxonomy of ETL activities. In: DOLAP 2009, ACM 12th International Workshop on Data Warehousing and OLAP, Hong Kong, November 6, 2009, Proceedings, pp. 25\u201332 (2009)"},{"key":"107_CR105","doi-asserted-by":"crossref","unstructured":"vom Brocke, J., Sonnenberg, C.: Business process management and business process analysis. In: Information Systems and Information Technology. Computing Handbook, 3rd edn., pp. 26: 1\u201331 (2014)","DOI":"10.1201\/b16768-31"},{"key":"107_CR106","doi-asserted-by":"crossref","unstructured":"Vrhovnik, M., Schwarz, H., Radesch\u00fctz, S., Mitschang, B.: An overview of SQL support in workflow products. In: Proceedings of ICDE, pp. 1287\u20131296 (2008)","DOI":"10.1109\/ICDE.2008.4497538"},{"key":"107_CR107","unstructured":"Vrhovnik, M., Schwarz, H., Suhre, O., Mitschang, B., Markl, V., Maier, A., Kraft, T.: An approach to optimize data processing in business processes. In: VLDB, pp. 615\u2013626 (2007)"},{"key":"107_CR108","doi-asserted-by":"crossref","unstructured":"Vu, L.H., Hauswirth, M., Aberer, K.: Qos-based service selection and ranking with trust and reputation management. In: Proceedings of the Cooperative Information System Conference (CoopIS05, pp. 466\u2013483 (2005)","DOI":"10.1007\/11575771_30"},{"key":"107_CR109","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.future.2013.10.004","volume":"31","author":"A Whrer","year":"2014","unstructured":"Whrer, A., Brezany, P., Janciak, I., Mehofer, E.: Modeling and optimizing large-scale data flows. Future Gener. Comput. Syst. 31, 12\u201327 (2014)","journal-title":"Future Gener. Comput. Syst."},{"key":"107_CR110","doi-asserted-by":"crossref","unstructured":"Wohlin, C.: Guidelines for snowballing in systematic literature studies and a replication in software engineering. In: Proceedings of the 18th International Conference on Evaluation and Assessment in Software Engineering, EASE\u201914, pp. 38:1\u201338:10 (2014)","DOI":"10.1145\/2601248.2601268"},{"key":"107_CR111","doi-asserted-by":"crossref","unstructured":"Yerneni, R., Li, C., Ullman, J.D., Garcia-Molina, H.: Optimizing large join queries in mediation systems. In: ICDT, pp. 348\u2013364 (1999)","DOI":"10.1007\/3-540-49257-7_22"},{"key":"107_CR112","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.jnca.2015.01.001","volume":"50","author":"L Zeng","year":"2015","unstructured":"Zeng, L., Veeravalli, B., Zomaya, A.Y.: An integrated task computation and data management scheduling strategy for workflow applications in cloud environments. J. Netw. Comput. Appl. 50, 39\u201348 (2015)","journal-title":"J. Netw. Comput. Appl."},{"issue":"1","key":"107_CR113","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/TCC.2015.2404807","volume":"4","author":"AC Zhou","year":"2016","unstructured":"Zhou, A.C., He, B., Liu, C.: Monetary cost optimizations for hosting workflow-as-a-service in IaaS clouds. IEEE Trans. Cloud Comput. 4(1), 34\u201348 (2016)","journal-title":"IEEE Trans. Cloud Comput."},{"key":"107_CR114","doi-asserted-by":"crossref","unstructured":"Zinn, D., Bowers, S., McPhillips, T., Lud\u00e4scher, B.: Scientific workflow design with data assembly lines. In: Proceedings of the 4th Workshop on Workflows in Support of Large-Scale Science, pp. 14:1\u201314:10 (2009)","DOI":"10.1145\/1645164.1645178"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s41060-018-0107-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-018-0107-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-018-0107-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T11:52:48Z","timestamp":1660564368000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s41060-018-0107-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3,6]]},"references-count":114,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["107"],"URL":"https:\/\/doi.org\/10.1007\/s41060-018-0107-0","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"value":"2364-415X","type":"print"},{"value":"2364-4168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,3,6]]},"assertion":[{"value":"26 May 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}