No abstract

No abstract

Cloud computing has emerged as a new paradigm that provides services to the user on pay-as-you-use basis. Cloud computing's Infrastructure as a service provides various resources to user such as computing, storage and bandwidth etc., where Computing services can be provided in the form of Virtual Machines. Parallel applications submitted for execution on these Virtual Machines can be completed without any delays only when the Virtual Machines are available for execution. In general, resources in cloud are shared by various users and their availability is dynamic and unpredictable due to various reasons such as capacity of underlying hardware and number of users sharing the resources and various other reasons. Hence, non-availability of these allocated resources may cause delays in completion of execution of parallel applications. In this scenario, existing algorithms without considering the delays that may occur due to non-availability of Virtual Machines may not perform better and are less reliable in terms of completion of jobs. In this paper, we propose a new heuristic called Workflow Scheduling based on Standard Deviation of Predictive Resource Availability in cloud computing considers the dynamic nature of cloud resources and its dynamic availability in scheduling decisions and produces reliable schedules..

No abstract

Abstract-In cloud environment, availability of resources for job execution is highly dynamic and temporal in nature. Resources in cloud range from processing elements such as Virtual Machines (VMs), Data Servers, Network Bandwidth etc. More over VMs in cloud are extensively available for execution with elastic nature of IaaS cloud. In cloud, VMs share physical resources and they cannot store data required to process the application. In this scenario, when a task is executed on a VM, the data required for execution must be retrieved from cloud data storage servers. As these servers and network bandwidth required for transferring data are shared by the different VMs in the cloud, non-availability of these resources may account to overall task execution delay. In this paper, we propose, a novel static scheduling heuristic called Scheduling workflows with Data Host Reservation in Cloud Computing (SDHR). In the first stage we predict Data storage server's availability and upon requirement request is made to increase the availability of data hosts to avoid delays. In the second stage based on location of data, a VM that is associated with data host is selected and scheduled for execution. Our SDRH algorithm performs better by considering data host reservations than existing heuristics without reservations.