Resource Provisioning Based Scheduling Framework for Execution of Heterogeneous and Clustered Workloads in Clouds: from Fundamental to Autonomic Offering

Provisioning of adequate resources to cloud workloads depends on the Quality of Service (QoS) requirements of these cloud workloads. Based on workload requirements (QoS) of cloud users, discovery and allocation of best workload-resource pair is an optimization problem. Acceptable QoS can be offered only if provisioning of resources is appropriately controlled. So, there is a need for a QoS-based resource provisioning framework for the autonomic scheduling of resources to observe the behavior of the services and adjust it dynamically in order to satisfy the QoS requirements. In this paper, framework for self-management of cloud resources for execution of clustered workloads named as SCOOTER is proposed that efficiently schedules the provisioned cloud resources and maintains the Service Level Agreement (SLA) by considering properties of self-management and the maximum possible QoS parameters are required to improve cloud based services. Finally, the performance of SCOOTER has been evaluated in a cloud environment that demonstrates the optimized QoS parameters such as execution cost, energy consumption, execution time, SLA violation rate, fault detection rate, intrusion detection rate, resource utilization, resource contention, throughput and waiting time.