{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T05:26:59Z","timestamp":1770960419608,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["New Gener. Comput."],"published-print":{"date-parts":[[2012,1]]},"DOI":"10.1007\/s00354-012-0105-z","type":"journal-article","created":{"date-parts":[[2012,2,6]],"date-time":"2012-02-06T12:26:12Z","timestamp":1328531172000},"page":"73-94","source":"Crossref","is-referenced-by-count":8,"title":["Predicting Job Failures in AuverGrid Based on Workload Log Analysis"],"prefix":"10.1007","volume":"30","author":[{"given":"Hamid","family":"Saadatfar","sequence":"first","affiliation":[]},{"given":"Hamid","family":"Fadishei","sequence":"additional","affiliation":[]},{"given":"Hossein","family":"Deldari","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,2,7]]},"reference":[{"key":"105_CR1","unstructured":"The Large Hadron Collider Grid (LCG) website. Availaible on: http:\/\/lcg.web.cern.ch\/LCG\/ ."},{"key":"105_CR2","unstructured":"The Lawrence Livermore National Laboratory BlueGene\/L supercomputer website. Availaible on: http:\/\/asc.llnl.gov\/computing_resources\/bluegenel\/ ."},{"key":"105_CR3","unstructured":"The AuverGrid website. Availaible on: http:\/\/www.auvergrid.fr\/ ."},{"key":"105_CR4","unstructured":"The EGEE (Enabling Grid for E-Science) project website. Availaible on: http:\/\/www.eu-egee.org\/ ."},{"key":"105_CR5","doi-asserted-by":"crossref","unstructured":"Fu, S. and Xu, C.-Z., \u201cExploring Event Correlation for Failure Prediction in Coalitions of Clusters,\u201d in Proc. of the International Conference on Supercomputing, 41, ACM\/IEEE, 2007.","DOI":"10.1145\/1362622.1362678"},{"key":"105_CR6","doi-asserted-by":"crossref","unstructured":"Asadzadeh, P., Buyya, R., Kei, C. L., Nayar, D. and Venugopal, S., \u201cGlobal Grids and Software Toolkits: A Study of Four Grid Middleware Technologies,\u201d Wiley Series on Parallel and Distributed Computing, Chap. 22, 2006.","DOI":"10.1002\/0471732710.ch22"},{"key":"105_CR7","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1016\/j.future.2008.02.003","volume":"24","author":"A. Iosup","year":"2008","unstructured":"Iosup A., Li H., Jan M., Anoep S., Dumitrescu C., Wolters L., Epema D.H.J.: \u201cThe Grid Workloads Archive\u201d. Elsevier Journal of Future Generation Computer Systems 24, 672\u2013686 (2008)","journal-title":"Elsevier Journal of Future Generation Computer Systems"},{"key":"105_CR8","doi-asserted-by":"crossref","unstructured":"Gunter, D., Tierney, B. L., Brown, A., Swany, M., Bresnahan, J. and Schopf, J. M., \u201cLog Summarization and Anomaly Detection for Troubleshooting Distributed Systems,\u201d in Proc. of the International Conference on Grid Computing, IEEE\/ACM, pp. 226\u2013234, 2007.","DOI":"10.1109\/GRID.2007.4354137"},{"key":"105_CR9","doi-asserted-by":"crossref","unstructured":"Chawla, N. V., Thain, D., Lichtenwalter, R. and Cieslak, D. A., \u201cData Mining on the Grid for the Grid,\u201d in Proc. of International Symposium on Parallel and Distributed Processing, IEEE, pp. 1\u20138, 2008.","DOI":"10.1109\/IPDPS.2008.4536427"},{"key":"105_CR10","doi-asserted-by":"crossref","unstructured":"Zeinalipour-Yazti, D., Neocleous, K., Georgiou, C. and Dikaiakos, M. D., \u201cIdentifying Failures in Grids through Monitoring and Ranking,\u201d in Proc. of International Symposium on Network Computing and Applications, IEEE, pp. 291\u2013298, 2008.","DOI":"10.1109\/NCA.2008.10"},{"key":"105_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sebag, M. and Germain, C., \u201cToward Behavioral Modeling of A Grid System: Mining the Logging and Bookkeeping Files,\u201d in Proc. of International Conference on Data Mining, IEEE, pp. 581\u2013588, 2007.","DOI":"10.1109\/ICDMW.2007.52"},{"key":"105_CR12","doi-asserted-by":"crossref","unstructured":"Kang, W. and Grimshaw, A., \u201cFailure Prediction in Computational Grids,\u201d in Proc. of Annual Simulation Symposium, IEEE, pp. 275\u2013282, 2007.","DOI":"10.1109\/ANSS.2007.21"},{"key":"105_CR13","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Wu, Y., Yang, G. and Zheng, W., \u201cAdaptive Hybrid Model for Long Term Load Prediction in Computational Grid,\u201d in Proc. of International Symposium on Cluster Computing and the Grid, IEEE, pp. 340\u2013347, 2008.","DOI":"10.1109\/CCGRID.2008.60"},{"key":"105_CR14","doi-asserted-by":"crossref","unstructured":"Akioka, S. and Muraoka, Y., \u201cExtended Forecast of CPU and Network Load on Computational Grid,\u201d in Proc. of International Symposium on Cluster Computing and the Grid, IEEE, pp. 765\u2013772, 2004.","DOI":"10.1109\/CCGrid.2004.1336711"},{"key":"105_CR15","doi-asserted-by":"crossref","unstructured":"Iosup, A., Dumitrescu, C. and Epema., D., \u201cHow are real grids used? The Analysis of Four Grid Traces and Its Implications,\u201d in Proc. of International Conference on Grid Computing, IEEE\/ACM, pp. 262\u2013269, 2006.","DOI":"10.1109\/ICGRID.2006.311024"},{"key":"105_CR16","doi-asserted-by":"crossref","unstructured":"Wolski, R., Spring, N. and Hayes, J., \u201cPredicting the CPU availability of Timeshared UNIX Systems,\u201d in Proc. of International Symposium on High Performance and Distributed Computing, IEEE, pp. 105\u2013112, 1999.","DOI":"10.1109\/HPDC.1999.805288"},{"key":"105_CR17","doi-asserted-by":"crossref","unstructured":"Dinda, P. A., \u201cThe Statistical Properties of Host Load,\u201d in Journal of Scientific Programming, 7, (3,4), pp. 211\u2013229, 1998.","DOI":"10.1155\/1999\/386856"},{"key":"105_CR18","doi-asserted-by":"crossref","unstructured":"Nadeem, F., Prodan, R. and Fahringer, T., \u201cCharacterizing, Modeling and Predicting Dynamic Resource Availability in a Large Scale Multi-purpose Grid,\u201d in Proc. of International Symposium on Cluster Computing and the Grid, IEEE, pp. 348\u2013357, 2008.","DOI":"10.1109\/CCGRID.2008.29"},{"key":"105_CR19","doi-asserted-by":"crossref","unstructured":"Domingues, P., Marques, P. and Silva, L., \u201cDGSchedSim: A Trace-Driven Simulator to Evaluate Scheduling Algorithms for Desktop Grid Environments,\u201d in Proc. of International Conference on Parallel, Distributed, and Network-Based Processing, IEEE, pp. 8\u201315, 2006.","DOI":"10.1109\/PDP.2006.28"},{"key":"105_CR20","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Shao, G. and Yang, G., \u201cA Survey of Methods and Applications for Trace Analysis in Grid Systems,\u201d in Proc. of ChinaGrid Annual Conference, IEEE, pp. 264\u2013271, 2008.","DOI":"10.1109\/ChinaGrid.2008.41"},{"key":"105_CR21","unstructured":"Andrzejak, A., Domingues, P. and Silva, L., \u201cClassifier-Based Capacity Prediction for Desktop Grids,\u201d in Proc. of Integrated Research in Grid Computing, CoreGRID Workshop, pp. 135\u2013144, 2005."},{"key":"105_CR22","unstructured":"Rood, B., Walters, J. P., Chaudhary, V. and Lewis, M. J., \u201cFailure Prediction and Scalable Checkpointing for Reliable Large-Scale Grid Computing,\u201d in HPDC\u201907, IEEE, 2007."},{"key":"105_CR23","doi-asserted-by":"crossref","unstructured":"Rood, B. and Lewis, M. J., \u201cResource Availability Prediction for Improved Grid Scheduling,\u201d in Proc. of eScience\u201908, IEEE, pp. 711\u2013718, 2008.","DOI":"10.1109\/eScience.2008.66"},{"key":"105_CR24","doi-asserted-by":"crossref","unstructured":"Li, H., Groep, D. and Wolters, L., \u201cMining Performance Data for Metascheduling Decision Support in the Grid,\u201d in FGCS, 23, 1, Elsevier, pp. 92\u201399, 2007.","DOI":"10.1016\/j.future.2006.04.009"},{"key":"105_CR25","doi-asserted-by":"crossref","unstructured":"Spooner, D. P., Jarvis, S. A., Cao, J., Saini, S. and Nudd, G. R., \u201cLocal Grid Scheduling Techniques using Performance Prediction,\u201d in Proc. on Computers and Digital Techniques, IEE, pp. 87\u201396, 2003.","DOI":"10.1049\/ip-cdt:20030280"},{"key":"105_CR26","unstructured":"Leangsuksun, C., Liu, T., Rao, T., Scott, S. L. and Libby, R., \u201cA Failure Predictive and Policy-Based High Availability Strategy For Linux HPC Cluster,\u201d in Proc. of the International Conference on Linux Clusters, pp. 1\u201312, 2004."},{"key":"105_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.-T. Y. and Siewiorek, D. P., \u201cError Log Analysis: Statistical Modeling and Heuristic Trend Analysis,\u201d in IEEE Transactions on Reliability, 39, 4, pp. 419\u2013432, 1990.","DOI":"10.1109\/24.58720"},{"key":"105_CR28","doi-asserted-by":"crossref","unstructured":"Brevik, J., Nurmi, D. and Wolski, R., \u201cAutomatic methods for predicting machine availability in desktop Grid and peer to-peer systems,\u201d in Proc. of CCGRID\u2019 04, IEEE, pp. 190\u2013199, 2004.","DOI":"10.1109\/CCGrid.2004.1336566"},{"key":"105_CR29","unstructured":"Li, H., \u201cWorkload Characterization, Modeling, and Prediction in Grid Computing,\u201d Ph.D. Thesis, Leiden University, 2008."},{"key":"105_CR30","doi-asserted-by":"crossref","unstructured":"Li, H., Groep, D., Wolters, L., and Templon, J., \u201cJob Failure Analysis and Its Implications in a Large-Scale Production Grid,\u201d in Proc. of International Conference on e-Science and Grid Computing, IEEE, pp. 27\u201334, 2006.","DOI":"10.1109\/E-SCIENCE.2006.261111"},{"key":"105_CR31","doi-asserted-by":"crossref","unstructured":"Cieslak, D. A., Chawla, N. V. and Thain, D. L., \u201cTroubleshooting Thousands of Jobs on Production Grids Using Data Mining Techniques,\u201d in GRID\u201908, IEEE, pp. 217\u2013224, 2008.","DOI":"10.1109\/GRID.2008.4662802"},{"key":"105_CR32","doi-asserted-by":"crossref","unstructured":"Cieslak, D. A., Thain, D. L. and Chawla, N. V., \u201cShort Paper: Troubleshooting Distributed Systems via Data Mining,\u201d in HDPC\u201906, IEEE, pp. 309\u2013312, 2006.","DOI":"10.1109\/HPDC.2006.1652163"},{"key":"105_CR33","unstructured":"Lan, Z., Gujrati, P., Li, Y., Zheng, Z., Thakur, R. and White, J., \u201cA Fault Diagnosis and Prognosis Service for TeraGrid Clusters,\u201d in TeraGrid\u201907 Conference, 2007."},{"key":"105_CR34","doi-asserted-by":"crossref","unstructured":"Dabrowski, C., \u201cReliability in Grid Computing Systems,\u201d Concurrency and Computation, Special OGF Issue, Wiley, pp. 927\u2013959, 2009.","DOI":"10.1002\/cpe.1410"},{"key":"105_CR35","unstructured":"Smith, W. and Wong, P., \u201cResource selection using execution and queue wait time predictions,\u201d Technical Report NAS-02-003, NAS, 2002."},{"issue":"2","key":"105_CR36","first-page":"155","volume":"9","author":"M. Kiran","year":"2009","unstructured":"Kiran M., A. Hashim A.-H., Kuan L.M., Jiun Y.Y.: \u201cExecution Time Prediction of Imperative Paradigm Tasks for Grid Scheduling Optimization\u201d. International Journal of Computer Science and Network Security 9(2), 155\u2013163 (2009)","journal-title":"International Journal of Computer Science and Network Security"},{"key":"105_CR37","doi-asserted-by":"crossref","unstructured":"Sonmez, O., Yigitbasi, N., Iosup, A. and Epema, D., \u201cTrace-Based Evaluation of Job Runtime and Queue Wait Time Predictions in Grids,\u201d in Proc. of the 18th International Symposium on High Performance Distributed Computing (HPDC\u201909), ACM, pp. 111\u2013120, 2009.","DOI":"10.1145\/1551609.1551632"},{"key":"105_CR38","first-page":"309","volume":"9","author":"G. Cooper","year":"1992","unstructured":"Cooper G., Herskovits E.: \u201cA Bayesian Method for the Induction of Probabilistic Networks from Data\u201d. Journal of Machine Learning 9, 309\u2013347 (1992)","journal-title":"Journal of Machine Learning"},{"key":"105_CR39","unstructured":"Witten, I. H., Frank, E., Data Mining: Practical Machine Learning Tools and Techniques (Second Edition), Elsevier, 2005."},{"key":"105_CR40","doi-asserted-by":"crossref","unstructured":"Jensen, F. V., Nielsen, T. D., Bayesian Networks and Decision Graphs, (Second Edition), Springer-Verlag, 2007.","DOI":"10.1007\/978-0-387-68282-2"},{"issue":"4","key":"105_CR41","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1016\/j.jpdc.2010.01.002","volume":"70","author":"S. Fu","year":"2010","unstructured":"Fu S.: \u201cFailure-aware resource management for high-availability computing clusters with distributed virtual machines\u201d. Journal of Parallel and Distributed Computing 70(4), 384\u2013393 (2010)","journal-title":"Journal of Parallel and Distributed Computing"},{"issue":"3","key":"105_CR42","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.jpdc.2009.11.003","volume":"70","author":"B.T.B. Khoo","year":"2010","unstructured":"Khoo B.T.B., Veeravalli B.: \u201cPro-active failure handling mechanisms for scheduling in grid computing environments\u201d. Journal of Parallel and Distributed Computing 70(3), 189\u2013200 (2010)","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"105_CR43","doi-asserted-by":"crossref","unstructured":"Wu, L., Ren, C, Meng, D, Jianfeng, Z. and Tu, B., \u201cThe Failure-Rate Aware Scheduling Policies for Large-Scale Cluster Systems,\u201d in Proc. of the 7th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT\u201906), IEEE, pp. 364\u2013367, 2006.","DOI":"10.1109\/PDCAT.2006.109"},{"key":"105_CR44","doi-asserted-by":"crossref","unstructured":"Shrinivas, L., Naughton, J. F., \u201cIssues in Applying Data Mining to Grid Job Failure Detection and Diagnosis,\u201d in Proc. of the International Symposium on High Performance and Distributed Computing (HDPC\u201908), ACM, pp. 239\u2013240, 2008.","DOI":"10.1145\/1383422.1383464"},{"key":"105_CR45","unstructured":"Duan, R., Prodan, R., Fahringer T., \u201cShort Paper: Data Mining-based Fault Prediction and Detection on the Grid,\u201d in Proc. of the 15th International Conference on High Performance Distributed Computing (HPDC\u201906), IEEE, pp. 305\u2013308, 2006."},{"key":"105_CR46","doi-asserted-by":"crossref","unstructured":"Gu, J., Zheng, Z., Lan, Z., White, J., Hocks, E., Park, B.-H., \u201cDynamic Meta-Learning for Failure Prediction in Large-Scale Systems: A Case Study,\u201d in Proc. of the 37th International Conference on Parallel Processing (ICPP\u201908), IEEE, pp. 157\u2013164, 2008.","DOI":"10.1109\/ICPP.2008.17"}],"container-title":["New Generation Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00354-012-0105-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00354-012-0105-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00354-012-0105-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T23:04:54Z","timestamp":1742425494000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00354-012-0105-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,1]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2012,1]]}},"alternative-id":["105"],"URL":"https:\/\/doi.org\/10.1007\/s00354-012-0105-z","relation":{},"ISSN":["0288-3635","1882-7055"],"issn-type":[{"value":"0288-3635","type":"print"},{"value":"1882-7055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,1]]}}}