遥感卫星数据预处理系统复杂任务调度模型研究与实现

Research and Implementation of Complex Task Scheduling Model for Remote Sensing Satellite Data Preprocessing System

针对遥感卫星数据预处理系统同时对多卫星数据处理任务进行调度时,因资源分配不合理,导致计算资源浪费、系统吞吐量低、无法满足卫星数据时效性要求的问题,提出了一种基于预处理任务性能及预处理系统工作流特性的调度模型。该模型通过研究预处理任务算法的一般特征,对不同资源分配情况下的任务执行时间进行预估,并根据预处理任务工作流对卫星数据产品所需总时间进行预估;在此基础上,采用基于任务时效性和系统资源利用率的二次资源动态分配算法对预处理任务进行调度。实验结果表明,该调度模型在满足多卫星数据处理的时效性要求的同时,合理地减小调度过程中存在的资源浪费,提高了系统的吞吐量。

In order to solve the problem that the remote sensing satellite data pre-processing system cannot meet the timeliness requirements of satellite data due to the unreasonable resource allocation when scheduling multi-satellite data processing tasks at the same time,a scheduling model based on the performance of pre-processing tasks and workflow characteristics of pre-processing system is proposed.The model estimates the execution time of tasks under different resource allocation conditions by studying the general characteristics of pre-processing task algorithms,and estimates the total time required for satellite data products according to the workflow of pre-processing tasks.On these bases,the pre-processing tasks are scheduled using a secondary resource dynamic allocation algorithm based on task timeliness and system resource utilization.The experimental results show that the scheduling model not only meets the timeliness requirements of multi-satellite data processing,but also reasonably reduces the resource waste in the scheduling process and improves the throughput of the system.