{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T18:03:39Z","timestamp":1730225019076,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1109\/hipc.2010.5713169","type":"proceedings-article","created":{"date-parts":[[2011,2,15]],"date-time":"2011-02-15T19:26:36Z","timestamp":1297797996000},"page":"1-10","source":"Crossref","is-referenced-by-count":14,"title":["Anomaly detection in large-scale coalition clusters for dependability assurance"],"prefix":"10.1109","author":[{"given":"Qiang","family":"Guan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Derek","family":"Smith","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1081870.1081927"},{"key":"ref32","article-title":"Beyond availability: Towards a deeper understanding of machine failure characteristics in large distributed systems","author":"yalagandula","year":"2004","journal-title":"Proceedings of USENIX Workshop on Real Large Distributed Systems (WORLDS)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2002.1183991"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1294261.1294275"},{"key":"ref37","article-title":"Failure diagnosis using decision trees","author":"zheng","year":"2004","journal-title":"Proceedings of IEEE International Conference on Automatic Computing (ICAC)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CSO.2010.71"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2010.5470868"},{"key":"ref34","article-title":"Performance implications of failures in large-scale cluster scheduling","author":"zhang","year":"2004","journal-title":"Proceedings of the 10th Workshop on Job Scheduling Strategies for Parallel Processing"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1016\/j.jpdc.2010.01.002","article-title":"Failure-aware resource management for high-availability computing clusters with distributed virtual machines","volume":"70","author":"fu","year":"2010","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362678"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS.2007.18"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ARES.2009.13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2010.06.010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1147\/sj.421.0005"},{"journal-title":"Data Mining Concepts and Techniques","year":"2005","author":"han","key":"ref16"},{"key":"ref17","article-title":"A power-aware run-time system for high-performance computing","author":"hsu","year":"2005","journal-title":"Proceedings of ACM\/IEEE Supercomputing Conference (SC)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2003.1160055"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2006.18"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2004.1311948"},{"key":"ref4","article-title":"Workload and failure characterization on a large-scale federated testbed","author":"chun","year":"2003","journal-title":"Technical Report IRB-TR-03–040"},{"key":"ref27","article-title":"Software failures and the road to a petaflop machine","author":"philp","year":"2005","journal-title":"Proceedings of International Symposium on High Performance Computer Architecture Work-shop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2006.5"},{"key":"ref5","article-title":"Correlating instrumentation data to system states: a building block for automated diagnosis and control","author":"cohen","year":"2004","journal-title":"Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI'02)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2009.21"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007465528199"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZ.2003.1209453"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCC.2010.5546715"},{"year":"0","key":"ref1"},{"key":"ref20","article-title":"Filtering failure logs for a BlueGene\/L prototype","author":"liang","year":"2005","journal-title":"Proceedings of IEEE International Conference on Dependable Systems and Networks (DSN)"},{"key":"ref22","article-title":"Mining partially periodic event patterns with unknown periods","author":"ma","year":"2001","journal-title":"Proceedings of IEEE International Conference on Data Engineering (ICDE)"},{"key":"ref21","article-title":"A log mining approach to failure analysis of enterprise telephony systems","author":"lim","year":"2008","journal-title":"Proceedings of IEEE International Conference on Dependable Systems and Networks (DSN)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2007.103"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/FTCS.1988.5301"},{"key":"ref26","article-title":"Mining logs files for computing system management","author":"peng","year":"2005","journal-title":"Proceedings of IEEE International Conference on Automatic Computing (ICAC)"},{"key":"ref25","article-title":"Why do Internet services fail, and what can be done about it","author":"oppenheimer","year":"2003","journal-title":"Proceedings of USENIX Symposium on Internet Technologies and Systems (USITS)"}],"event":{"name":"2010 International Conference on High Performance Computing (HiPC 2010)","start":{"date-parts":[[2010,12,19]]},"location":"Dona Paula","end":{"date-parts":[[2010,12,22]]}},"container-title":["2010 International Conference on High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5708271\/5713158\/05713169.pdf?arnumber=5713169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,2]],"date-time":"2020-02-02T16:11:41Z","timestamp":1580659901000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/5713169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/hipc.2010.5713169","relation":{},"subject":[],"published":{"date-parts":[[2010,12]]}}}