SURVEY ON PREDICTION AND TASK AWARE SYSTEM FOR RESOURCE MONITORING IN VIRTUAL CLOUD ENVIRONMENT

Huge-rule statistics hubs control virtualization equipment towards reach tremendous source application, scalability, and high accessibility. Ideally, the act of an presentation successively exclusive a Virtual Machine (VM) shall be self-governing of co- located submissions and VM's that share the physical machine. However, adverse interfering ef ects exist and are especially severe for statistics- exhaustive applications in such virtualized environments. In this work, we present TRACON, a novel Task and Resource Allocation control framework that moderates the intrusion possessions from coexisting statistics-exhaustive applications. TRACON exploits modelling and control techniques from algebraic mechanism is demand consists of three major components: the interference prediction model that infers application performance from resource consumption observed from dif erent VMs, the interference-aware scheduler that is designed to utilize the model for effective source management, and the task and resource monitor that collects application characteristics at the runtime for model adaption. The evaluation results show that TRACON can achieve up to 25 percent upgrading on application throughput on virtualized servers.