{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T17:02:44Z","timestamp":1790010164698,"version":"4.0.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2015,4,14]],"date-time":"2015-04-14T00:00:00Z","timestamp":1428969600000},"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":["J Grid Computing"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1007\/s10723-015-9331-1","type":"journal-article","created":{"date-parts":[[2015,4,12]],"date-time":"2015-04-12T23:42:00Z","timestamp":1428882120000},"page":"507-525","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Fault-Tolerant Dynamic Rescheduling for Heterogeneous Computing Systems"],"prefix":"10.1007","volume":"13","author":[{"given":"Jing","family":"Mei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenli","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keqin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,4,14]]},"reference":[{"issue":"11","key":"9331_CR1","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1109\/TC.1984.1676376","volume":"33","author":"H Kasahara","year":"1984","unstructured":"Kasahara, H., Narita, S.: Practical multiprocessor scheduling algorithms for efficient parallel processing. IEEE Trans. Comput. 33(11), 1023\u20131029 (1984)","journal-title":"IEEE Trans. Comput."},{"issue":"3","key":"9331_CR2","doi-asserted-by":"crossref","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)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"4","key":"9331_CR3","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1016\/j.jpdc.2007.05.015","volume":"68","author":"MI Daoud","year":"2008","unstructured":"Daoud, M.I., Kharma, N.: A high performance algorithm for static task scheduling in heterogeneous distributed computing systems. J. Parallel Distrib. Comput. 68(4), 399\u2013409 (2008)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"4","key":"9331_CR4","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1007\/s10723-013-9258-3","volume":"11","author":"S Nesmachnow","year":"2013","unstructured":"Nesmachnow, S., Dorronsoro, B., Pecero, J., Bouvry, P.: Energy-aware scheduling on multicore heterogeneous grid computing systems. J. Grid Comput. 11(4), 653\u2013680 (2013)","journal-title":"J. Grid Comput."},{"issue":"4","key":"9331_CR5","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1007\/s10723-014-9294-7","volume":"12","author":"H Arabnejad","year":"2014","unstructured":"Arabnejad, H., Barbosa, J.: A budget constrained scheduling algorithm for workflow applications. J. Grid Comput. 12(4), 665\u2013679 (2014)","journal-title":"J. Grid Comput."},{"key":"9331_CR6","doi-asserted-by":"crossref","unstructured":"Ranaweera, S., Agrawal, D.: A scalable task duplication based scheduling algorithm for heterogeneous systems. In: Proceedings of 2000 International Conference on Parallel Processing, pp. 383\u2013390 (2000)","DOI":"10.1109\/ICPP.2000.876154"},{"issue":"6","key":"9331_CR7","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1109\/TPDS.2003.1206502","volume":"14","author":"S Bansal","year":"2003","unstructured":"Bansal, S., Kumar, P., Singh, K.: An improved duplication strategy for scheduling precedence constrained graphs in multiprocessor systems. IEEE Trans. Parallel Distrib. Syst. 14(6), 533\u2013544 (2003)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"8","key":"9331_CR8","doi-asserted-by":"crossref","first-page":"1146","DOI":"10.1016\/j.jpdc.2008.04.001","volume":"68","author":"K Shin","year":"2008","unstructured":"Shin, K., Cha, M., Jang, M., Jung, J., Yoon, W., Choi, S.: Task scheduling algorithm using minimized duplications in homogeneous systems. J. Parallel Distrib. Comput. 68(8), 1146\u20131156 (2008)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"4","key":"9331_CR9","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.jpdc.2010.01.003","volume":"70","author":"X Tang","year":"2010","unstructured":"Tang, X., Li, K., Liao, G., Li, R.: List scheduling with duplication for heterogeneous computing systems. J. Parallel Distrib. Comput. 70(4), 323\u2013329 (2010)","journal-title":"J. Parallel Distrib. Comput."},{"key":"9331_CR10","doi-asserted-by":"crossref","unstructured":"Song, I., Yoon, W., Jang, E., Choi, S.: Task scheduling algorithm with minimal redundant duplications in homogeneous multiprocessor system in Grid and Distributed Computing, pp. 238\u2013245. Springer (2011)","DOI":"10.1007\/978-3-642-27180-9_29"},{"issue":"6","key":"9331_CR11","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1109\/TPDS.2003.1206502","volume":"14","author":"S Bansal","year":"2003","unstructured":"Bansal, S., Kumar, P., Singh, K.: An improved duplication strategy for scheduling precedence constrained graphs in multiprocessor systems. IEEE Trans. Parallel Distrib. Syst. 14(6), 533\u2013544 (2003)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"7","key":"9331_CR12","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1016\/j.parco.2005.04.002","volume":"31","author":"T Hagras","year":"2005","unstructured":"Hagras, T., brevecek, J.J.: A high performance, low complexity algorithm for compile-time task scheduling in heterogeneous systems. Parallel Comput. 31(7), 653\u2013670 (2005)","journal-title":"Parallel Comput."},{"key":"9331_CR13","unstructured":"Liou, J., Palis, M.: An efficient task clustering heuristic for scheduling dags on multiprocessors. In: Proceedings of Parallel and Distributed Processing Symposium (1996)"},{"key":"9331_CR14","doi-asserted-by":"crossref","unstructured":"Fangfa, F., Yuxin, B., Xinaan, H., Jinxiang, W., Minyan, Y., Jia, Z.: An objective-flexible clustering algorithm for task mapping and scheduling on cluster-based noc. In: 2010 10th Russian-Chinese Symposium on Laser Physics and Laser Technologies (RCSLPLT) and 2010 Academic Symposium on Optoelectronics Technology (ASOT), 28 2010-aug. 1 2010, pp. 369\u2013373","DOI":"10.1109\/RCSLPLT.2010.5615317"},{"issue":"4","key":"9331_CR15","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.parco.2012.01.001","volume":"38","author":"MA Khan","year":"2012","unstructured":"Khan, M.A.: Scheduling for heterogeneous systems using constrained critical paths. Parallel Comput. 38(4), 175\u2013193 (2012)","journal-title":"Parallel Comput."},{"key":"9331_CR16","unstructured":"Stearley, J.: Defining and measuring supercomputer reliability, availability, and serviceability (ras). In: Proceedings of the Linux Clusters Institute Conference (2005)"},{"issue":"1","key":"9331_CR17","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/s10723-007-9090-8","volume":"6","author":"RM Rahman","year":"2008","unstructured":"Rahman, R.M., Barker, K., Alhajj, R.: Replica placement strategies in data grid. J. Grid Comput. 6(1), 103\u2013123 (2008)","journal-title":"J. Grid Comput."},{"issue":"2","key":"9331_CR18","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/s10723-011-9201-4","volume":"10","author":"H Yang","year":"2012","unstructured":"Yang, H., Luan, Z., Li, W., Qian, D.: Mapreduce workload modeling with statistical approach. J. grid Comput. 10(2), 279\u2013310 (2012)","journal-title":"J. grid Comput."},{"key":"9331_CR19","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/TSE.1987.232562","volume":"1","author":"R Koo","year":"1987","unstructured":"Koo, R., Toueg, S.: Checkpointing and rollback-recovery for distributed systems. IEEE Trans. Softw. Eng. 1, 23\u201331 (1987)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"9331_CR20","doi-asserted-by":"crossref","unstructured":"Chakravorty, S.: A fault tolerance protocol for fast recovery. ProQuest (2008)","DOI":"10.1109\/IPDPS.2007.370310"},{"issue":"6","key":"9331_CR21","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1109\/TC.2011.106","volume":"61","author":"X Yang","year":"2012","unstructured":"Yang, X., Wang, Z., Xue, J., Zhou, Y.: The reliability wall for exascale supercomputing. IEEE Trans. Comput. 61(6), 767\u2013779 (2012)","journal-title":"IEEE Trans. Comput."},{"key":"9331_CR22","doi-asserted-by":"crossref","unstructured":"Benoit, A., Hakem, M., Robert, Y.: Fault tolerant scheduling of precedence task graphs on heterogeneous platforms. In: IEEE International Symposium Parallel Distributed Processing, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/IPDPS.2008.4536133"},{"key":"9331_CR23","doi-asserted-by":"crossref","unstructured":"Zhao, L., Ren, Y., Xiang, Y., Sakurai, K.: Fault-tolerant scheduling with dynamic number of replicas in heterogeneous systems. In: 12th IEEE International Conference High Performance Computing Communications, pp. 434\u2013441. IEEE (2010)","DOI":"10.1109\/HPCC.2010.72"},{"issue":"9","key":"9331_CR24","doi-asserted-by":"crossref","first-page":"1156","DOI":"10.1109\/12.165396","volume":"41","author":"SM Shatz","year":"1992","unstructured":"Shatz, S.M., Wang, J.-P., Goto, M.: Task allocation for maximizing reliability of distributed computer systems. IEEE Trans. Comput. 41(9), 1156\u20131168 (1992)","journal-title":"IEEE Trans. Comput."},{"issue":"8","key":"9331_CR25","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1016\/j.jpdc.2005.02.003","volume":"65","author":"X Qin","year":"2005","unstructured":"Qin, X., Jiang, H.: A dynamic and reliability-driven scheduling algorithm for parallel real-time jobs executing on heterogeneous clusters. J. Parallel Distrib. Comput. 65(8), 885\u2013900 (2005)","journal-title":"J. Parallel Distrib. Comput."},{"key":"9331_CR26","doi-asserted-by":"crossref","unstructured":"Dongarra, J.J., Jeannot, E., Saule, E., Shi, Z.: Bi-objective scheduling algorithms for optimizing makespan and reliability on heterogeneous systems. In: Proceedings of the nineteenth annual ACM symposium on Parallel algorithms and architectures, pp. 280\u2013288. ACM (2007)","DOI":"10.1145\/1248377.1248423"},{"key":"9331_CR27","doi-asserted-by":"crossref","unstructured":"Jeannot, E., Saule, E., Trystram, D.: Bi-objective approximation scheme for makespan and reliability optimization on uniform parallel machines. In: Euro-Par 2008\u2013Parallel Processing, pp. 877\u2013886. Springer (2008)","DOI":"10.1007\/978-3-540-85451-7_94"},{"issue":"3","key":"9331_CR28","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.jpdc.2008.11.002","volume":"69","author":"A Girault","year":"2009","unstructured":"Girault, A., Saule, E., Trystram, D.: Reliability versus performance for critical applications. J. Parallel Distrib. Comput. 69(3), 326\u2013336 (2009)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"9","key":"9331_CR29","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1016\/j.jpdc.2010.05.002","volume":"70","author":"X Tang","year":"2010","unstructured":"Tang, X., Li, K., Li, R., Veeravalli, B.: Reliability-aware scheduling strategy for heterogeneous distributed computing systems. J. Parallel Distrib. Comput. 70(9), 941\u2013952 (2010)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"8","key":"9331_CR30","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/j.parco.2010.10.003","volume":"37","author":"C Boeres","year":"2011","unstructured":"Boeres, C., Sardi\u00f1a, I. M., Drummond, L.: An efficient weighted bi-objective scheduling algorithm for heterogeneous systems. Parallel Comput. 37(8), 349\u2013364 (2011)","journal-title":"Parallel Comput."},{"issue":"2","key":"9331_CR31","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1016\/j.jpdc.2011.11.003","volume":"72","author":"E Jeannot","year":"2012","unstructured":"Jeannot, E., Saule, E., Trystram, D.: Optimizing performance and reliability on heterogeneous parallel systems: Approximation algorithms and heuristics. J. Parallel Distrib. Comput. 72(2), 268\u2013280 (2012)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"1","key":"9331_CR32","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s10723-012-9237-0","volume":"11","author":"Y Tao","year":"2013","unstructured":"Tao, Y., Jin, H., Wu, S., Shi, X., Shi, L.: Dependable grid workflow scheduling based on resource availability. J. Grid Comput. 11(1), 47\u201361 (2013)","journal-title":"J. Grid Comput."},{"key":"9331_CR33","doi-asserted-by":"crossref","unstructured":"Hakem, M., Butelle, F.: Reliability and scheduling on systems subject to failures. In: International Conference on Parallel Processing, pp. 38\u201338. IEEE (2007)","DOI":"10.1109\/ICPP.2007.72"},{"issue":"5","key":"9331_CR34","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/j.parco.2006.06.006","volume":"32","author":"X Qin","year":"2006","unstructured":"Qin, X., Jiang, H.: A novel fault-tolerant scheduling algorithm for precedence constrained tasks in real-time heterogeneous systems. Parallel Comput. 32(5), 331\u2013356 (2006)","journal-title":"Parallel Comput."},{"issue":"3","key":"9331_CR35","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.jpdc.2008.11.007","volume":"69","author":"Q Zheng","year":"2009","unstructured":"Zheng, Q., Veeravalli, B.: On the design of communication-aware fault-tolerant scheduling algorithms for precedence constrained tasks in grid computing systems with dedicated communication devices. J. Parallel Distrib. Comput. 69(3), 282\u2013294 (2009)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"3","key":"9331_CR36","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1109\/TC.2008.172","volume":"58","author":"Q Zheng","year":"2009","unstructured":"Zheng, Q., Veeravalli, B., Tham, C.-K.: On the design of fault-tolerant scheduling strategies using primary-backup approach for computational grids with low replication costs. IEEE Trans. Comput. 58(3), 380\u2013393 (2009)","journal-title":"IEEE Trans. Comput."},{"key":"9331_CR37","doi-asserted-by":"crossref","unstructured":"Benoit, A., Hakem, M., Robert, Y.: Realistic models and efficient algorithms for fault tolerant scheduling on heterogeneous platforms. In: 37th International Conference on Parallel Processing, pp. 246\u2013253. IEEE (2008)","DOI":"10.1109\/ICPP.2008.22"},{"issue":"6","key":"9331_CR38","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/2.214439","volume":"26","author":"A Khokhar","year":"1993","unstructured":"Khokhar, A., Prasanna, V., Shaaban, M., Wang, C.-L.: Heterogeneous computing: challenges and opportunities. Computer 26(6), 18\u201327 (1993)","journal-title":"Computer"},{"key":"9331_CR39","doi-asserted-by":"crossref","unstructured":"Radulescu, A., Van Gemund, A.: Fast and effective task scheduling in heterogeneous systems. In: Proceedings of 9th Heterogeneous Computing Workshop, pp. 229\u2013238 (2000)","DOI":"10.1109\/HCW.2000.843747"},{"key":"9331_CR40","doi-asserted-by":"crossref","unstructured":"Choudhury, P., Chakrabarti, P., Kumar, R.: Online scheduling of dynamic task graphs with communication and contention for multiprocessors, vol. 23, pp. 126\u2013133 (2012)","DOI":"10.1109\/TPDS.2011.104"},{"key":"9331_CR41","doi-asserted-by":"crossref","unstructured":"Young, J.W.: A first order approximation to the optimum checkpoint interval. Commun. ACM 17(9), 530\u2013531","DOI":"10.1145\/361147.361115"},{"key":"9331_CR42","doi-asserted-by":"crossref","unstructured":"Jin, H., Sun, X.-H., Zheng, Z., Lan, Z., Xie, B.: Performance under failures of dag-based parallel computing. In: 9th IEEE\/ACM International Symposium on Cluster Computing and the Grid, pp. 236\u2013243 (2009)","DOI":"10.1109\/CCGRID.2009.55"},{"issue":"4","key":"9331_CR43","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1016\/j.jpdc.2007.05.015","volume":"68","author":"MI Daoud","year":"2008","unstructured":"Daoud, M.I., Kharma, N.: A high performance algorithm for static task scheduling in heterogeneous distributed computing systems. J. Parallel Distrib. Comput. 68(4), 399\u2013409 (2008)","journal-title":"J. Parallel Distrib. Comput."}],"container-title":["Journal of Grid Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10723-015-9331-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10723-015-9331-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10723-015-9331-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,23]],"date-time":"2019-08-23T05:59:19Z","timestamp":1566539959000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10723-015-9331-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4,14]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["9331"],"URL":"https:\/\/doi.org\/10.1007\/s10723-015-9331-1","relation":{},"ISSN":["1570-7873","1572-9184"],"issn-type":[{"value":"1570-7873","type":"print"},{"value":"1572-9184","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,4,14]]}}}