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 modelling approach to the problem of resource prediction. Models are based on historical data to forecast shortterm 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.

DOCTORAL DISSERTATION COLLOQUIUM EXTENDED ABSTRACT ABSTRACTCloud computing and virtualization platforms grant on demand access to resources and services independently of complex underlying infrastructure. Resources can be added or removed on the fly. In this paper we propose a cloud monitoring method based on prediction. The goal of this method is to 1.achieve monitoring state alert prediction 2. forecast virtual resource usage of the cloud system

No abstract