基于机器学习的分布式星载RTs系统负载调度算法  

Load Scheduling Algorithm for Distributed On-board RTs System Based on Machine Learning

作　　者：谭双杰 林宝军[1,2,3,4,5] 刘迎春 赵帅 TAN Shuang-jie;LIN Bao-jun;LIU Ying-chun;ZHAO Shuai(School of Information Science and Technology,ShanghaiTech University,Shanghai 201210,China;Innovation Academy for Microsatellites,Chinese Academy of Sciences,Shanghai 201203,China;School of Computer Science and Technology,University of Chinese Academy of Sciences,Beijing 100094,China;Shanghai Engineering Center for Microsatellites,Shanghai 201210,China;Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China)

机构地区：[1]上海科技大学信息科学与技术学院,上海201210 [2]中国科学院微小卫星创新研究院,上海201203 [3]中国科学院大学计算机科学与技术学院,北京100094 [4]上海微小卫星工程中心,上海201210 [5]中国科学院空天信息创新研究院,北京100094

出　　处：《计算机科学》2022年第2期336-341,共6页Computer Science

摘　　要：分布式星载多RTs(Remote Terminal)系统的任务主要基于功能进行分配,而数据处理任务的突发性往往会使不同计算机之间负载不均衡。运用灵活的负载调度机制,可以有效调节不同计算机间的负载差异,从而在一定程度上提升计算机系统的整体性能。文中提出了一种基于机器学习的分布式星载RTs系统负载调度算法,包含样本采集、任务吞吐率预测模型构建、吞吐率预测和负载调度等4个步骤。在构建任务吞吐率预测模型环节,通过机器学习的线性回归正规方程获取模型权重,缩短了构建模型消耗的时间。在负载调度环节,若RTs的吞吐率之和大于系统总的负载数据量,则按吞吐率比例给各RTs分配数据,否则只给负载数据量小于自身吞吐率的RTs分配一定量的数据。在多台星载计算机电性能产品构建的地面模拟系统上的实验结果表明,该算法可以使系统所有节点的平均CPU利用率提高23.78%,节点间的CPU利用率方差降低至34.59%,同时目标任务的系统总吞吐量显著提升225.97%。也就是说,该方法在确保系统负载均衡性的同时,可有效提高系统的资源利用率,提升星载计算机系统的数据实时处理性能。The tasks of distributed on-board multi-RTs(remote terminals)system are mainly distributed based on functions,while the burstiness of data processing tasks often leads to unbalanced load among different computers.Using a flexible load scheduling mechanism can effectively adjust the load difference between different computers,thereby improving the overall performance of the computer system to a certain extent.A load scheduling algorithm for distributed on-board RTs system based on machine learning is proposed in this paper,which includes four steps:sample collection,task throughput prediction model construction,throughput prediction and load scheduling.In the process of constructing the task throughput prediction model,the weight of the model is obtained through the linear regression normal equation of machine learning,which reduces the time spent in constructing the model.In the load scheduling link,if the total throughput rate of RTs is greater than the total load data volume of the system,data will be allocated to each RT in proportion to the throughput rate;otherwise,only a certain amount of data will be allocated to RTs whose load data volume is less than their own throughput rate.The test results on the ground simulation system constructed by multiple on-board computers electrical performance products show that the algorithm can increase the average CPU utilization rate of all nodes of the system by 23.78%,and reduce the variance of CPU utilization rate between nodes to 34.59%.The total system throughput of the task is significantly increased by 225.97%.In other words,this method can effectively improve system resource utilization while ensuring system load balance,and improve the real-time data processing performance of the on-board computer system.

关 键 词：分布式系统 星载计算机 机器学习 任务调度 动态负载均衡 

分 类 号：TN927.2[电子电信—通信与信息系统] TP181[电子电信—信息与通信工程]