{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:59:34Z","timestamp":1782997174262,"version":"3.54.5"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2017,9,6]],"date-time":"2017-09-06T00:00:00Z","timestamp":1504656000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Information Technologies for Business Intelligence Doctoral College\u201d (IT4BI-DC)"},{"name":"National Science Center","award":["2015\/19\/B\/ST6\/02637"],"award-info":[{"award-number":["2015\/19\/B\/ST6\/02637"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1007\/s00778-017-0477-2","type":"journal-article","created":{"date-parts":[[2017,9,6]],"date-time":"2017-09-06T20:59:14Z","timestamp":1504731554000},"page":"777-801","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["From conceptual design to performance optimization of ETL workflows: current state of research and open problems"],"prefix":"10.1007","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5886-8193","authenticated-orcid":false,"given":"Syed Muhammad Fawad","family":"Ali","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Wrembel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,9,6]]},"reference":[{"key":"477_CR1","volume-title":"Synthesis Lectures on Data Management","author":"CS Jensen","year":"2010","unstructured":"Jensen, C.S., Pedersen, T.B., Thomsen, C.: Synthesis Lectures on Data Management. Morgan & Claypool Publishers, San Rafael (2010)"},{"key":"477_CR2","doi-asserted-by":"crossref","unstructured":"Andzic, J., Fiore, V., Sisto, L.: Extraction, transformation, and loading processes. In: Wrembel, R., Koncilia, C. (eds.) Data Warehouses and OLAP: Concepts, Architectures and Solutions. Idea Group Inc. (2007). ISBN 1-59904-364-5","DOI":"10.4018\/987-1-59904-364-7.ch004"},{"key":"477_CR3","doi-asserted-by":"crossref","unstructured":"Patil, P., Rao, S., Patil, S.: Data integration problem of structural and semantic heterogeneity: data warehousing framework models for the optimization of the ETL processes. In: Proceedings of ACM International Conference and Workshop on Emerging Trends in Technology (2011)","DOI":"10.1145\/1980022.1980130"},{"key":"477_CR4","unstructured":"Gartner magic quadrant for data integration tools (2017)"},{"key":"477_CR5","unstructured":"10 open source ETL tools. Data science central. www.datasciencecentral.com\/profiles\/blogs\/10-open-source-etl-tools . Accessed 10 June 2017 (2015)"},{"key":"477_CR6","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.procs.2010.12.019","volume":"3","author":"MM Awad","year":"2011","unstructured":"Awad, M.M., Abdullah, M.S., Ali, A.B.M.: Extending ETL framework using service oriented architecture. Proc. Comput. Sci. 3, 110\u2013114 (2011)","journal-title":"Proc. Comput. Sci."},{"key":"477_CR7","doi-asserted-by":"crossref","unstructured":"Vassiliadis, P., Simitsis, A., Skiadopoulos, S.: Conceptual modeling for ETL processes. In: Proceedings of ACM International Workshop on Data Warehousing and OLAP (DOLAP) (2002)","DOI":"10.1145\/583890.583893"},{"key":"477_CR8","doi-asserted-by":"crossref","unstructured":"Simitsis, A., Vassiliadis, P.: A methodology for the conceptual modeling of ETL processes. In: Proceedings of the of Conference on Advanced Information Systems Engineering (CAiSE) (2003)","DOI":"10.1145\/583890.583893"},{"issue":"6","key":"477_CR9","doi-asserted-by":"crossref","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":"477_CR10","unstructured":"Halasipuram, R., Deshpande, P.M., Padmanabhan, S.: Determining essential statistics for cost based optimization of an ETL workflow. In: Proceedings of International Conference on Extending Database Technology (EDBT), pp. 307\u2013318 (2014)"},{"key":"477_CR11","doi-asserted-by":"crossref","unstructured":"Kumar, N., Kumar, P.S.: An efficient heuristic for logical optimization of ETL workflows. In: Proceedings of International Conference on Very Large Data Bases (VLDB). Springer, Berlin (2011)","DOI":"10.1007\/978-3-642-22970-1_6"},{"issue":"10","key":"477_CR12","doi-asserted-by":"crossref","first-page":"1404","DOI":"10.1109\/TKDE.2005.169","volume":"17","author":"A Simitsis","year":"2005","unstructured":"Simitsis, A., Vassiliadis, P., Sellis, T.: State-space optimization of ETL workflows. IEEE Trans. Knowl. Data Eng. (TKDE) 17(10), 1404\u20131419 (2005)","journal-title":"IEEE Trans. Knowl. Data Eng. (TKDE)"},{"key":"477_CR13","volume-title":"The Unified Modeling Language Reference Manual","author":"J Rumbaugh","year":"2004","unstructured":"Rumbaugh, J., Jacobson, I., Booch, G.: The Unified Modeling Language Reference Manual. Pearson Higher Education, London (2004)"},{"key":"477_CR14","doi-asserted-by":"crossref","unstructured":"Trujillo, J., Luj\u00e1n-Mora, S.: A UML based approach for modeling ETL processes in data warehouses. In: Proceedings of International Conference on Conceptual Modeling (ER). Springer, Berlin (2003)","DOI":"10.1007\/978-3-540-39648-2_25"},{"key":"477_CR15","doi-asserted-by":"crossref","unstructured":"Skoutas, D., Simitsis, A.: Designing ETL processes using semantic web technologies. In: Proceedings of ACM International Workshop on Data Warehousing and OLAP (DOLAP) (2006)","DOI":"10.1145\/1183512.1183526"},{"key":"477_CR16","unstructured":"McGuinness, D.L., Van\u00a0Harmelen, F., et\u00a0al.: OWL web ontology language overview. W3C recommendation. https:\/\/www.w3.org\/TR\/owl-features\/ . Accessed 05 June 2017 (2004)"},{"issue":"4","key":"477_CR17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4018\/jswis.2007100101","volume":"3","author":"D Skoutas","year":"2007","unstructured":"Skoutas, D., Simitsis, A.: Ontology-based conceptual design of ETL processes for both structured and semi-structured data. Int. J. Semant. Web Inf. Syst. (IJSWIS) 3(4), 1\u201324 (2007)","journal-title":"Int. J. Semant. Web Inf. Syst. (IJSWIS)"},{"key":"477_CR18","doi-asserted-by":"crossref","unstructured":"Skoutas, D., Simitsis, A., Sellis, T.: Ontology-driven conceptual design of ETL processes using graph transformations. In: Journal on Data Semantics XIII. Lecture Notes in Computer Science, pp. 120\u2013146. Springer, Berlin (2009)","DOI":"10.1007\/978-3-642-03098-7_5"},{"key":"477_CR19","doi-asserted-by":"crossref","unstructured":"El\u00a0Akkaoui, Z., Zim\u00e1nyi, E.: Defining ETL workflows using BPMN and BPEL. In: Proceedings of ACM International Workshop on Data Warehousing and OLAP (DOLAP) (2009)","DOI":"10.1145\/1651291.1651299"},{"key":"477_CR20","doi-asserted-by":"crossref","unstructured":"El\u00a0Akkaoui, Z., Zim\u00e0nyi, E., Maz\u00f3n, J.N., Trujillo, J.: A model-driven framework for ETL process development. In: Proceedings of the ACM International Workshop on Data Warehousing and OLAP (DOLAP) (2011)","DOI":"10.1145\/2064676.2064685"},{"key":"477_CR21","doi-asserted-by":"crossref","unstructured":"Oliveira, B., Belo, O.: BPMN patterns for ETL conceptual modelling and validation. In: Foundations of Intelligent Systems. Springer, Berlin (2012)","DOI":"10.1007\/978-3-642-34624-8_50"},{"key":"477_CR22","doi-asserted-by":"crossref","unstructured":"Wilkinson, K., Simitsis, A., Castellanos, M., Dayal, U.: Leveraging business process models for ETL design. In: Proceedings of the International Conference on Conceptual Modeling (ER). Springer, Berlin (2010)","DOI":"10.1007\/978-3-642-16373-9_2"},{"key":"477_CR23","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 ACM SIGMOD International Conference on Management of Data (2009)","DOI":"10.1145\/1559845.1559954"},{"issue":"1","key":"477_CR24","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.datak.2009.08.009","volume":"69","author":"A Simitsis","year":"2010","unstructured":"Simitsis, A., Skoutas, D., Castellanos, M.: Representation of conceptual ETL designs in natural language using semantic web technology. Data Knowl. Eng. (DKE) 69(1), 96\u2013115 (2010)","journal-title":"Data Knowl. Eng. (DKE)"},{"key":"477_CR25","unstructured":"Vassiliadis, P., Simitsis, A., Skiadopoulos, S.: Modeling ETL activities as graphs. In: Proceedings of International Workshop on Design and Management of Data Warehouses (DMDW) (2002)"},{"key":"477_CR26","doi-asserted-by":"crossref","unstructured":"Simitsis, A., Vassiliadis, P., Sellis, T.: Logical optimization of ETL workflows. In: Proceedings of Hellenic Data Management Symposium. Citeseer (2005)","DOI":"10.1109\/TKDE.2005.169"},{"issue":"7","key":"477_CR27","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1016\/j.is.2004.11.002","volume":"30","author":"P Vassiliadis","year":"2005","unstructured":"Vassiliadis, P., Simitsis, A., Georgantas, P., Terrovitis, M., Skiadopoulos, S.: A generic and customizable framework for the design of ETL scenarios. Inf. Syst. 30(7), 492\u2013525 (2005)","journal-title":"Inf. Syst."},{"issue":"1","key":"477_CR28","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.dss.2006.12.002","volume":"45","author":"A Simitsis","year":"2008","unstructured":"Simitsis, A., Vassiliadis, P.: A method for the mapping of conceptual designs to logical blueprints for ETL processes. Decis. Support Syst. 45(1), 22\u201340 (2008)","journal-title":"Decis. Support Syst."},{"key":"477_CR29","doi-asserted-by":"crossref","unstructured":"Vassiliadis, P., Simitsis, A., Georgantas, P., Terrovitis, M.: A framework for the design of ETL scenarios. In: Proceedings of the Conference on Advanced Information Systems Engineering (CAiSE). Springer, Berlin (2003)","DOI":"10.1007\/3-540-45017-3_35"},{"key":"477_CR30","doi-asserted-by":"crossref","unstructured":"Tziovara, V., Vassiliadis, P., Simitsis, A.: Deciding the physical implementation of ETL workflows. In: Proceedings of ACM International Workshop on Data Warehousing and OLAP (DOLAP) (2007)","DOI":"10.1145\/1317331.1317341"},{"key":"477_CR31","doi-asserted-by":"crossref","unstructured":"Simitsis, A., Wilkinson, K., Dayal, U., Castellanos, M.: Optimizing ETL workflows for fault-tolerance. In: Proceedings of IEEE International Conference on Data Engineering (ICDE) (2010)","DOI":"10.1109\/ICDE.2010.5447816"},{"key":"477_CR32","doi-asserted-by":"crossref","unstructured":"Vassiliadis, P., Simitsis, A., Baikousi, E.: A taxonomy of ETL activities. In: Proceedings of ACM International Workshop on Data Warehousing and OLAP (DOLAP) (2009)","DOI":"10.1145\/1651291.1651297"},{"key":"477_CR33","doi-asserted-by":"crossref","unstructured":"Chakrabarti, S., Demmel, J., Yelick, K.: Modeling the benefits of mixed data and task parallelism. In: Proceedings of the Seventh Annual ACM Symposium on Parallel Algorithms and Architectures (1995)","DOI":"10.1145\/215399.215423"},{"issue":"1","key":"477_CR34","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. Commun. ACM 51(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"477_CR35","doi-asserted-by":"crossref","unstructured":"Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The hadoop distributed file system. IEEE Mass Storage Syst. Technol. (MSST) (2010)","DOI":"10.1109\/MSST.2010.5496972"},{"key":"477_CR36","doi-asserted-by":"crossref","unstructured":"Battr\u00e9, D., Ewen, S., Hueske, F., Kao, O., Markl, V., Warneke, D.: Nephele\/pacts: a programming model and execution framework for web-scale analytical processing. In: Proceedings of ACM Symposium on Cloud Computing. ACM (2010)","DOI":"10.1145\/1807128.1807148"},{"key":"477_CR37","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 ACM SIGMOD International Conference on Management of Data (1979)","DOI":"10.1145\/582095.582099"},{"key":"477_CR38","doi-asserted-by":"crossref","unstructured":"Alexandrov, A., Heimel, M., Markl, V., Battr\u00e9, D., Hueske, F., Nijkamp, E., Ewen, S., Kao, O., Warneke, D.: Massively parallel data analysis with pacts on nephele. Proceedings of International Conference on Very Large Data Bases (VLDB) (2010)","DOI":"10.14778\/1920841.1921056"},{"key":"477_CR39","doi-asserted-by":"crossref","unstructured":"Warneke, D., Kao, O.: Nephele: efficient parallel data processing in the cloud. In: Proceedings of ACM International Workshop on Many-Task Computing on Grids and Supercomputers (2009)","DOI":"10.1145\/1646468.1646476"},{"key":"477_CR40","doi-asserted-by":"crossref","unstructured":"Hueske, F., Peters, M., Krettek, A., Ringwald, M., Tzoumas, K., Markl, V., Freytag, J.: Peeking into the optimization of data flow programs with mapreduce-style UDFS. In: Proceedings of IEEE International Conference on Data Engineering (ICDE) (2013)","DOI":"10.1109\/ICDE.2013.6544927"},{"key":"477_CR41","doi-asserted-by":"crossref","unstructured":"Hueske, F., Peters, M., Sax, M.J., Rheinl\u00e4nder, A., Bergmann, R., Krettek, A., Tzoumas, K.: Opening the black boxes in data flow optimization. In: Proceedings of International Conference on Very Large Data Bases (VLDB) (2012)","DOI":"10.14778\/2350229.2350244"},{"key":"477_CR42","unstructured":"Apache Spark\u2014lightning-fast cluster computing. http:\/\/spark.apache.org\/ . Accessed on 22 July 2016"},{"key":"477_CR43","doi-asserted-by":"crossref","unstructured":"Chaiken, R., Jenkins, B., Larson, P.\u00c5., Ramsey, B., Shakib, D., Weaver, S., Zhou, J.: Scope: easy and efficient parallel processing of massive data sets. In: Proceedings of International Conference on Very Large Data Bases (VLDB) (2008)","DOI":"10.14778\/1454159.1454166"},{"key":"477_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, J., Larson, P.A., Chaiken, R.: Incorporating partitioning and parallel plans into the scope optimizer. In: Proceedings of IEEE International Conference on Data Engineering (ICDE) (2010)","DOI":"10.1109\/ICDE.2010.5447802"},{"key":"477_CR45","doi-asserted-by":"crossref","unstructured":"Gro\u00dfe, P., May, N., Lehner, W.: A study of partitioning and parallel UDF execution with the SAP HANA database. In: Proceedings of ACM International Conference on Scientific and Statistical Database Management (SSDBM) (2014)","DOI":"10.1145\/2618243.2618274"},{"key":"477_CR46","unstructured":"Binnig, C., May, N., Mindnich, T.: SQLScript: Efficiently Analyzing Big Enterprise Data in SAP HANA. In: Datenbanksysteme f\u00fcr Business, Technologie und Web (BTW) (2013)"},{"key":"477_CR47","unstructured":"Gro\u00dfe, P., Lehner, W., May, N.: Advanced analytics with the SAP HANA database. In: DATA (2013)"},{"key":"477_CR48","doi-asserted-by":"crossref","unstructured":"Thomsen, C., Pedersen, T.B.: Easy and effective parallel programmable ETL. In: Proceedings of ACM International Workshop on Data Warehousing and OLAP (DOLAP) (2011)","DOI":"10.1145\/2064676.2064684"},{"key":"477_CR49","doi-asserted-by":"crossref","unstructured":"Liu, X., Thomsen, C., Pedersen, T.B.: ETLMR: a highly scalable dimensional ETL framework based on mapreduce. In: Proceedings of International Conference on Data Warehousing and Knowledge Discovery (DaWaK). Springer, Berlin (2011)","DOI":"10.1007\/978-3-642-23544-3_8"},{"key":"477_CR50","doi-asserted-by":"crossref","unstructured":"Liu, X., Thomsen, C., Pedersen, T.B.: ETLMR: a highly scalable dimensional ETL framework based on mapreduce. In: Transactions on Large-Scale Data and Knowledge-Centered Systems, LNCS. Springer, Berlin (2013)","DOI":"10.1007\/978-3-642-37574-3_1"},{"key":"477_CR51","doi-asserted-by":"crossref","unstructured":"Liu, X., Iftikhar, N.: An ETL optimization framework using partitioning and parallelization. In: Proceedings of the 30th Annual Symposium on Applied Computing. ACM (2015)","DOI":"10.1145\/2695664.2695846"},{"key":"477_CR52","unstructured":"Lella, R.: Optimizing BDFS jobs using InfoSphere DataStage Balanced Optimization. IBM Developer Works (2014)"},{"key":"477_CR53","unstructured":"How to Achieve Flexible, Cost-effective Scalability and Performance through Pushdown Processing. Informatica whitepaper. https:\/\/www.informatica.com\/downloads\/pushdown_wp_6650_web.pdf . Accessed 01 June 2017 (2007)"},{"issue":"8","key":"477_CR54","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1016\/j.datak.2011.03.003","volume":"70","author":"S Bergamaschi","year":"2011","unstructured":"Bergamaschi, S., Guerra, F., Orsini, M., Sartori, C., Vincini, M.: A semantic approach to ETL technologies. Data Knowl. Eng. (DKE) 70(8), 717\u2013731 (2011)","journal-title":"Data Knowl. Eng. (DKE)"},{"key":"477_CR55","doi-asserted-by":"publisher","unstructured":"Manousis, P., Vassiliadis, P., Papastefanatos, G.: Impact analysis and policy-conforming rewriting of evolving data-intensive ecosystems. J. Data Semant. (2015). doi: 10.1007\/s13740-015-0050-3","DOI":"10.1007\/s13740-015-0050-3"},{"key":"477_CR56","doi-asserted-by":"publisher","DOI":"10.1007\/s10796-016-9732-0","author":"A Wojciechowski","year":"2017","unstructured":"Wojciechowski, A.: ETL workflow reparation by means of case-based reasoning. Inf. Syst. Front. (2017). doi: 10.1007\/s10796-016-9732-0","journal-title":"Inf. Syst. Front."},{"key":"477_CR57","unstructured":"Terrizzano, I., Schwarz, P., Roth, M., Colino, J.E.: Data wrangling: the challenging journey from the Wild to the lake. In: Proceedings of Conference on Innovative Data Systems Research (CIDR) (2015)"},{"issue":"2","key":"477_CR58","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1145\/2814710.2814713","volume":"44","author":"J Duggan","year":"2015","unstructured":"Duggan, J., Elmore, A.J., Stonebraker, M., Balazinska, M., Howe, B., Kepner, J., Madden, S., Maier, D., Mattson, T., Zdonik, S.: The BigDAWG Polystore system. SIGMOD Rec. 44(2), 11\u201316 (2015)","journal-title":"SIGMOD Rec."},{"issue":"1","key":"477_CR59","doi-asserted-by":"crossref","first-page":"59","DOI":"10.15807\/jorsj.21.59","volume":"21","author":"T Ibaraki","year":"1978","unstructured":"Ibaraki, T., Hasegawa, T., Teranaka, K., Iwase, J.: The multiple choice knapsack problem. J. Oper. Res. Soc. Jpn. 21(1), 59\u201393 (1978)","journal-title":"J. Oper. Res. Soc. Jpn."}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-017-0477-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-017-0477-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-017-0477-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,3]],"date-time":"2019-10-03T01:59:04Z","timestamp":1570067944000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-017-0477-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,6]]},"references-count":59,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["477"],"URL":"https:\/\/doi.org\/10.1007\/s00778-017-0477-2","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9,6]]}}}