Research And Application Of Task Scheduling Model For The Cluster Processing Of Remote Sensing Data

In recent years, the satellite remote sensing technology is rapid development in our country, and the remote sensing data is with explosion growth, so the process of remote sensing data tasks more urgent. In the face of such a large remote sensing data processing tasks, the high-performance cluster computing has achieved very good results, and improve the efficiency of data processing greatly. Task scheduling is a very important part of the cluster of remote sensing data processing system, and it also is the key to improvement the performance of the cluster of remote sensing data processing system. However, the existing scheduling algorithms has some problems, such as the load of nodes is imbalance, the utilization of computer is not high, the throughput of tasks is very low, and the average time of task scheduling is very long. To solve the problems above, this paper proposes a task scheduling model which adopts the advanced scheduling algorithm of first come first service, and the node load balance calculation technology. And this model is based on analysis the existing scheduling algorithm, considering the cluster of remote sensing data processing system has the properties such as the task is very heavy and independent, and the nature of the task is unitary, and the performance of node has large differences. By using this model, the utilization rate of system node and the throughput of tasks improve effectively, and reduce the average time of task scheduling effectively.In this paper, the main work and contributions are as follows:1. Research and analysis the scheduling algorithm which are applied to the cluster of remote sensing data processing system, Aim them at the poor utilization, low task throughput, long time of task scheduling, and so on. Therefore, this paper proposes a model which is called two-way task scheduling based on task and node.2. Based on the proposing of the task scheduling model, Firstly, according to the characteristics of the cluster of remote sensing data system, by analyzing the implementation rationale and the advantages and disadvantages of RMI, to design the communication mechanism for the task scheduling model; Then, according to the characteristics of system tasks to complete the design of the task scheduling mode, and consider the load balancing accomplish the load calculation and scheduling of the node. Finally, complete the overall design of the task scheduling model.3. By applying the task scheduling model to the information product production subsystem, and through a large number of test data, prove that the scheduling model can realize the load balance of nodes to the greatest extent, improve the utilization rate of system node and the task throughput, and also reduce the average time of task schedule, the stability of the system is good.