A deadline-based elastic approach for balanced task scheduling in computing cloud environment

The cloud servicing environment allows sharing of parallelised virtual resource among tasks based on quality of service requirements. Proficient resource management and scheduling of tasks to execute within deadline is a challenging issue. Several approaches available at present for scheduling and workload balancing among the virtual machines (VM) in cloud, but most of them are not conforming to emerging features like elasticity for dynamic provisioning or deprovisioning of VM's while allocating workload. The proposed deadline based elastic approach for load balancing and scheduling (DL_ELBalTSch) considers the percentage of VM's overloaded or underloaded as a supporting threshold at that movement and takes decision either to raise or cut the VM's. This approach is competent enough to meet established deadline by raising successful execution rate of tasks on variable number of resources. The extensive simulations performed on CloudSim obtained higher task execution-ratio, and lower makespan-time and execution-cost when compared with existing approaches. Copyright © 2021 Inderscience Enterprises Ltd.