Approaches for Efficient Workflow Planning and Execution of Scientific Application with Cloud Resources to Maximize Throughput within a Limited Time Limit

Abstract

In Cloud Environment, Resources available to the client on demand with pay per usage. Higher throughput with minimal execution time can reduce the budget cost for client as well as can never violate Service Level Agreement (SLA). For scientific application like weather forecasting maximum calculation within a limited time scope must be requirement. Prediction of incoming future work and its parallel execution with unlimited cloud resources can fulfil our requirement. Various techniques should be developed for this strategy. Usage Pattern [1] scheme use knowledge base for predicting future jobs by pattern matching which help to reduce start-up overhead. Bag of Task [2] scheme provide concept of simultaneous execution of scientific tasks with variable resources on available cloud. Resources can be increased or decreased on demand which can reduce the overall cloud rent cost. Our approach suggests a technique to combine usage pattern with bag of task which can provide efficient result with higher throughput in minimum time. Predict the future work, estimate execution time, divide jobs in small tasks and execute them parallel with on-demand variable resources can provide good results.