Scientific Workflow Scheduling Based on Data Transformation Graph for Remote Sensing Application.

As the amount of data and computation of workflow applications continue to grow, the inter-cloud environment provide with a great amount of computing resources to respond to the increasing demand, but how to effectively map workflow sub tasks to cloud service providers for better QoS(quality of service) performance is a question. Remote sensing applications have massive data, frequent and large data transfers across the cloud could cause huge performance bottlenecks, will seriously affect the result of QoS such as makespan and cost. By using DTG(data transformation graph) model to study the data transmission process of global drought monitoring application, an optimized scientific workflow scheduling based on genetic algorithm is proposed for inter-cloud environment, experimental results show that this method can significantly optimize makespan and cost for data-intensive applications like remote sensing application and can effectively reduce the impact of performance bottlenecks.