Changes between Version 5 and Version 6 of JINO-1

Timestamp:

Jun 26, 2012, 11:02:55 AM (6 years ago)

Author:

frederic.loulergue@…

Comment:

--

JINO-1

@@ -9 +9 @@
 == Programme ==
 
+* 11h30-12h15 '''A Resource Prediction Model for Virtualization Servers''' [[BR]] ''Sayanta Mallick, Gaetan Hains, Cheikh Sadibou Deme'' [[BR]] Monitoring and predicting resource consumption is a fundamental need when running a virtualized system. Predicting resources is necessary because cloud infrastructures use virtual resources on demand. Current monitoring tools are insufficient to predict resource usage of virtualized systems so, without proper monitoring, virtualized systems can suffer down time, which can directly affect cloud infrastructure.We propose a new modeling approach to the problem of resource prediction. Models are based on historical data to forecast short-term resource usages. We present here in detail three of our prediction models to forecast and monitor resources. We also show experimental results by using real-life data and an overall evaluation of this approach. 
 * 10h45-11h30 '''Vers des environnements infonuagiques vérifiés''' [[BR]] ''Frédéric Loulergue, Frédéric Gava, Nikolay Kosmatov, Matthieu Lemerre'' [[BR]] As the usage of the cloud becomes pervasive in our lives, it is needed to ensure the reliability, safety and security of cloud environments. In this paper we study a usual software stack of a cloud environment from the perspective of formal verification. This software stack ranges from applications to the hypervisor.  We argue that most of the layers could be practically formally verified, even if the work to verify all levels is huge.
-* 11h30-12h15 '''A Resource Prediction Model for Virtualization Servers''' [[BR]] ''Sayanta Mallick, Gaetan Hains, Cheikh Sadibou Deme'' [[BR]] Monitoring and predicting resource consumption is a fundamental need when running a virtualized system. Predicting resources is necessary because cloud infrastructures use virtual resources on demand. Current monitoring tools are insufficient to predict resource usage of virtualized systems so, without proper monitoring, virtualized systems can suffer down time, which can directly affect cloud infrastructure.We propose a new modeling approach to the problem of resource prediction. Models are based on historical data to forecast short-term resource usages. We present here in detail three of our prediction models to forecast and monitor resources. We also show experimental results by using real-life data and an overall evaluation of this approach. 
 * 12h15-14h00 '''Déjeuner'''
 * 14h00-14h45 '''Requêtes relationnelles et informatique dans les nuages''' [[BR]] ''Abdeljallil Abajjane, Mostafa Bamha''[[BR]]Résumé à venir