Title: A deadline-based elastic approach for balanced task scheduling in computing cloud environment
Authors: K. Jairam Naik
Addresses: Department of Computer Science and Engineering, National Institute of Technology Raipur, Chhattisgarh, India
Abstract: 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.
Keywords: computing cloud; scheduling; workload balancing; deadline; virtual machines; resources; elastic scaling; utilisation; makespan time; provisioning; deprovisioning; execution ratio.
International Journal of Cloud Computing, 2021 Vol.10 No.5/6, pp.579 - 602
Accepted: 28 Mar 2020
Published online: 19 Jan 2022 *