{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T15:53:09Z","timestamp":1743090789199,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030830137"},{"type":"electronic","value":"9783030830144"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-83014-4_2","type":"book-chapter","created":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T16:03:12Z","timestamp":1626969792000},"page":"32-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Scheduling of Scientific Workflow Actions in the Cloud Based on Required Capabilities"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2775-5844","authenticated-orcid":false,"given":"Michel","family":"Kr\u00e4mer","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,23]]},"reference":[{"key":"2_CR1","unstructured":"Altintas, I., Berkley, C., Jaeger, E., Jones, M., Ludascher, B., Mock, S.: Kepler: an extensible system for design and execution of scientific workflows. In: Proceedings. 16th International Conference on Scientific and Statistical Database Management, 2004, pp. 423\u2013424. IEEE (2004)"},{"key":"2_CR2","unstructured":"Apache Airflow: Apache Airflow Website (2020). https:\/\/airflow.apache.org\/. Accessed 14 Apr 2020"},{"key":"2_CR3","unstructured":"Argo Workflows: Argo Website (2020). https:\/\/argoproj.github.io\/. Accessed 21 Oct 2020"},{"key":"2_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/3-540-45726-7_1","volume-title":"Randomization and Approximation Techniques in Computer Science","author":"Z Bar-Yossef","year":"2002","unstructured":"Bar-Yossef, Z., Jayram, T.S., Kumar, R., Sivakumar, D., Trevisan, L.: Counting distinct elements in a data stream. In: Rolim, J.D.P., Vadhan, S. (eds.) RANDOM 2002. LNCS, vol. 2483, pp. 1\u201310. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-45726-7_1"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Berriman, G.B., et al.: Montage: a grid-enabled engine for delivering custom science-grade mosaics on demand. In: Optimizing Scientific Return for Astronomy through Information Technologies, vol. 5493, pp. 221\u2013233. International Society for Optics and Photonics (2004)","DOI":"10.1117\/12.550551"},{"key":"2_CR6","doi-asserted-by":"publisher","unstructured":"Binato, S., Hery, W.J., Loewenstern, D.M., Resende, M.G.C.: A Grasp for Job Shop Scheduling, pp. 59\u201379. Springer, Boston (2002). https:\/\/doi.org\/10.1007\/978-1-4615-1507-4_3","DOI":"10.1007\/978-1-4615-1507-4_3"},{"key":"2_CR7","doi-asserted-by":"publisher","unstructured":"Blythe, J., et al.: Task scheduling strategies for workflow-based applications in grids. In: Proceedings of the IEEE International Symposium on Cluster Computing and the Grid (CCGrid), pp. 759\u2013767 (2005). https:\/\/doi.org\/10.1109\/CCGRID.2005.1558639","DOI":"10.1109\/CCGRID.2005.1558639"},{"issue":"4","key":"2_CR8","first-page":"28","volume":"36","author":"P Carbone","year":"2015","unstructured":"Carbone, P., Katsifodimos, A., Ewen, S., Markl, V., Haridi, S., Tzoumas, K.: Apache Flink: stream and batch processing in a single engine. Bull. IEEE Comput. Soc. Tech. Committee Data Eng. 36(4), 28\u201338 (2015)","journal-title":"Bull. IEEE Comput. Soc. Tech. Committee Data Eng."},{"key":"2_CR9","doi-asserted-by":"publisher","unstructured":"Casanova, H., Legrand, A., Zagorodnov, D., Berman, F.: Heuristics for scheduling parameter sweep applications in grid environments. In: Proceedings of the 9th Heterogeneous Computing Workshop HCW, pp. 349\u2013363 (2000). https:\/\/doi.org\/10.1109\/HCW.2000.843757","DOI":"10.1109\/HCW.2000.843757"},{"key":"2_CR10","unstructured":"Chircu, V.: Understanding the 8 fallacies of distributed systems (2018). https:\/\/dzone.com\/articles\/understanding-the-8-fallacies-of-distributed-syste. Accessed 18 Feb 2020"},{"issue":"1","key":"2_CR11","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1177\/1094342017704893","volume":"32","author":"E Deelman","year":"2018","unstructured":"Deelman, E., et al.: The future of scientific workflows. Int. J. High Perform. Comput. Appl. 32(1), 159\u2013175 (2018)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"2_CR12","doi-asserted-by":"publisher","unstructured":"Deelman, E., et al.: Pegasus: a workflow management system for science automation. Future Gener. Comput. Syst. 46, 17\u201335 (2015). https:\/\/doi.org\/10.1016\/j.future.2014.10.008","DOI":"10.1016\/j.future.2014.10.008"},{"issue":"4","key":"2_CR13","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1038\/nbt.3820","volume":"35","author":"P Di Tommaso","year":"2017","unstructured":"Di Tommaso, P., Chatzou, M., Floden, E.W., Barja, P.P., Palumbo, E., Notredame, C.: Nextflow enables reproducible computational workflows. Nat. Biotechnol. 35(4), 316\u2013319 (2017). https:\/\/doi.org\/10.1038\/nbt.3820","journal-title":"Nat. Biotechnol."},{"volume-title":"The Grid: Blueprint for a New Computing Infrastructure","year":"1998","key":"2_CR14","unstructured":"Foster, I., Kesselman, C. (eds.): The Grid: Blueprint for a New Computing Infrastructure. Morgan Kaufmann Publishers Inc., San Francisco (1998)"},{"key":"2_CR15","unstructured":"Freund, R.F., et al.: Scheduling resources in multi-user heterogeneous computing environments with SmartNet. The NPS Institutional Archive, Calhoun (1998)"},{"key":"2_CR16","doi-asserted-by":"publisher","unstructured":"Gherega, A., Pupezescu, V.: Multi-agent resource allocation algorithm based on the XSufferage heuristic for distributed systems. In: Proceedings of the 13th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, pp. 313\u2013320 (2011). https:\/\/doi.org\/10.1109\/SYNASC.2011.37","DOI":"10.1109\/SYNASC.2011.37"},{"issue":"10","key":"2_CR17","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1101\/gr.4086505","volume":"15","author":"B Giardine","year":"2005","unstructured":"Giardine, B., et al.: Galaxy: a platform for interactive large-scale genome analysis. Genome Res. 15(10), 1451\u20131455 (2005). https:\/\/doi.org\/10.1101\/gr.4086505","journal-title":"Genome Res."},{"issue":"3","key":"2_CR18","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1007\/s00024-010-0161-6","volume":"168","author":"R Graves","year":"2011","unstructured":"Graves, R., et al.: CyberShake: a physics-based seismic hazard model for southern California. Pure Appl. Geophys. 168(3), 367\u2013381 (2011). https:\/\/doi.org\/10.1007\/s00024-010-0161-6","journal-title":"Pure Appl. Geophys."},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"Hamad, S.A., Omara, F.A.: Genetic-based task scheduling algorithm in cloud computing environment. Int. J. Adv. Comput. Sci. Appl. 7(4), 550\u2013556 (2016). https:\/\/doi.org\/10.14569\/IJACSA.2016.070471","DOI":"10.14569\/IJACSA.2016.070471"},{"issue":"2","key":"2_CR20","first-page":"24","volume":"40","author":"M Hemamalini","year":"2012","unstructured":"Hemamalini, M.: Review on grid task scheduling in distributed heterogeneous environment. Int. J. Comput. Appl. 40(2), 24\u201330 (2012)","journal-title":"Int. J. Comput. Appl."},{"key":"2_CR21","doi-asserted-by":"publisher","first-page":"W729","DOI":"10.1093\/nar\/gkl320","volume":"34","author":"D Hull","year":"2006","unstructured":"Hull, D., Wolstencroft, K., Stevens, R., Goble, C., Pocock, M.R., Li, P., Oinn, T.: Taverna: a tool for building and running workflows of services. Nucl. Acids Res. 34, W729\u2013W732 (2006)","journal-title":"Nucl. Acids Res."},{"issue":"2","key":"2_CR22","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1145\/322003.322011","volume":"24","author":"OH Ibarra","year":"1977","unstructured":"Ibarra, O.H., Kim, C.E.: Heuristic algorithms for scheduling independent tasks on nonidentical processors. J. ACM 24(2), 280\u2013289 (1977). https:\/\/doi.org\/10.1145\/322003.322011","journal-title":"J. ACM"},{"key":"2_CR23","unstructured":"Johnson, D.S., Garey, M.R.: Computers and Intractability: A Guide to the Theory of NP-Completeness. WH Freeman (1979)"},{"key":"2_CR24","doi-asserted-by":"publisher","unstructured":"Kane, D.M., Nelson, J., Woodruff, D.P.: An optimal algorithm for the distinct elements problem. In: Proceedings of the 29th ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, PODS 2010, pp. 41\u201352. Association for Computing Machinery (2010). https:\/\/doi.org\/10.1145\/1807085.1807094","DOI":"10.1145\/1807085.1807094"},{"key":"2_CR25","doi-asserted-by":"publisher","unstructured":"Kr\u00e4mer, M.: A microservice architecture for the processing of large geospatial data in the cloud. Ph.D. thesis, Technische Universit\u00e4t Darmstadt (2018). https:\/\/doi.org\/10.13140\/RG.2.2.30034.66248","DOI":"10.13140\/RG.2.2.30034.66248"},{"key":"2_CR26","doi-asserted-by":"publisher","unstructured":"Kr\u00e4mer, M.: Capability-based scheduling of scientific workflows in the cloud. In: Proceedings of the 9th International Conference on Data Science, Technology, and Applications DATA, pp. 43\u201354. INSTICC, SciTePress (2020). https:\/\/doi.org\/10.5220\/0009805400430054","DOI":"10.5220\/0009805400430054"},{"key":"2_CR27","doi-asserted-by":"publisher","unstructured":"Li, K., Xu, G., Zhao, G., Dong, Y., Wang, D.: Cloud task scheduling based on load balancing ant colony optimization. In: Proceedings of the 6th Annual Chinagrid Conference, pp. 3\u20139 (2011). https:\/\/doi.org\/10.1109\/ChinaGrid.2011.17","DOI":"10.1109\/ChinaGrid.2011.17"},{"key":"2_CR28","doi-asserted-by":"publisher","unstructured":"Maheswaran, M., Ali, S., Siegal, H.J., Hensgen, D., Freund, R.F.: Dynamic matching and scheduling of a class of independent tasks onto heterogeneous computing systems. In: Proceedings. Eighth Heterogeneous Computing Workshop (HCW 1999), pp. 30\u201344, April 1999. https:\/\/doi.org\/10.1109\/HCW.1999.765094","DOI":"10.1109\/HCW.1999.765094"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Mell, P.M., Grance, T.: The NIST definition of cloud computing. Technical report, National Institute of Standards & Technology, Gaithersburg, MD, USA (2011)","DOI":"10.6028\/NIST.SP.800-145"},{"issue":"8","key":"2_CR30","first-page":"314","volume":"10","author":"B Nayak","year":"2019","unstructured":"Nayak, B., Padhi, S.K.: Mapping of independent tasks in the cloud computing environment. Int. J. Adv. Comput. Sci. Appl. 10(8), 314\u2013318 (2019)","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"issue":"17","key":"2_CR31","doi-asserted-by":"publisher","first-page":"3045","DOI":"10.1093\/bioinformatics\/bth361","volume":"20","author":"T Oinn","year":"2004","unstructured":"Oinn, T., et al.: Taverna: a tool for the composition and enactment of bioinformatics workflows. Bioinformatics 20(17), 3045\u20133054 (2004). https:\/\/doi.org\/10.1093\/bioinformatics\/bth361","journal-title":"Bioinformatics"},{"key":"2_CR32","doi-asserted-by":"publisher","unstructured":"Page, A.J., Naughton, T.J.: Dynamic task scheduling using genetic algorithms for heterogeneous distributed computing. In: Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (2005). https:\/\/doi.org\/10.1109\/IPDPS.2005.184","DOI":"10.1109\/IPDPS.2005.184"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Russell, N., van van der Aalst, W.M., ter Hofstede, A.H.M. : Workflow Patterns: The Definitive Guide. MIT Press, Cambridge (2016)","DOI":"10.7551\/mitpress\/8085.001.0001"},{"key":"2_CR34","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/s10723-015-9359-2","volume":"14","author":"S Singh","year":"2016","unstructured":"Singh, S., Chana, I.: A survey on resource scheduling in cloud computing: issues and challenges. J. Grid Comput. 14, 217\u2013264 (2016). https:\/\/doi.org\/10.1007\/s10723-015-9359-2","journal-title":"J. Grid Comput."},{"key":"2_CR35","doi-asserted-by":"publisher","unstructured":"Tawfeek, M.A., El-Sisi, A., Keshk, A.E., Torkey, F.A.: Cloud task scheduling based on ant colony optimization. In: Proceedings of the 8th International Conference on Computer Engineering Systems (ICCES), pp. 64\u201369 (2013). https:\/\/doi.org\/10.1109\/ICCES.2013.6707172","DOI":"10.1109\/ICCES.2013.6707172"},{"key":"2_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-020-01678-9","author":"S Thennarasu","year":"2020","unstructured":"Thennarasu, S., Selvam, M., Srihari, K.: A new whale optimizer for workflow scheduling in cloud computing environment. J. Ambient Intell. Humanized Comput. (2020). https:\/\/doi.org\/10.1007\/s12652-020-01678-9","journal-title":"J. Ambient Intell. Humanized Comput."},{"issue":"3","key":"2_CR37","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1109\/71.993206","volume":"13","author":"H Topcuoglu","year":"2002","unstructured":"Topcuoglu, H., Hariri, S., Wu, M.-Y.: Performance-effective and low-complexity task scheduling for heterogeneous computing. IEEE Trans. Parallel Distrib. Syst. 13(3), 260\u2013274 (2002). https:\/\/doi.org\/10.1109\/71.993206","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"3","key":"2_CR38","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1016\/S0022-0000(75)80008-0","volume":"10","author":"J Ullman","year":"1975","unstructured":"Ullman, J.: NP-complete scheduling problems. J. Comput. Syst. Sci. 10(3), 384\u2013393 (1975). https:\/\/doi.org\/10.1016\/S0022-0000(75)80008-0","journal-title":"J. Comput. Syst. Sci."},{"key":"2_CR39","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: cluster computing with working sets. In: Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing. USENIX Association (2010)"}],"container-title":["Communications in Computer and Information Science","Data Management Technologies and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-83014-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,22]],"date-time":"2021-07-22T16:03:42Z","timestamp":1626969822000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-83014-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030830137","9783030830144"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-83014-4_2","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"23 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DATA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Data Management Technologies and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 July 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 July 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"data2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.dataconference.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Primoris","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"70","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"14","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"20% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}