运用蒙特卡洛模拟法的数据流调度优化模型研究  

Research on Data Flow Scheduling Optimization Model Based on Monte Carlo Simulation

作　　者：施健[1] 孟庆强[1] 吕顺利[1] SHI Jian;MENG Qingqiang;LV Sunli(NARI Group(State Grid Electric Power Research Institute),Nanjing 210024)

机构地区：[1]南瑞集团公司(国网电力科学研究院),南京210024

出　　处：《计算机与数字工程》2018年第4期779-782,817,共5页Computer & Digital Engineering

基　　金：国家电网公司科技项目"电力大数据实时处理及智能分析技术研究"(编号:524606150119)资助

摘　　要：传统的静态数据流任务调度方法,其任务执行时间是可预知的。但在实时流计算平台中,数据流的顺序与数据量的大小都是不确定的,导致任务的执行时间也是不确定的。论文提出一种运用蒙特卡洛模拟法的数据流任务调度方法,该方法利用随机数生成算法,在一定约束条件下大量模拟生成任务执行时间,通过经典的静态调度算法(HEFT)产生相应的预调度方案,经过综合比较最终得到一种最优的预调度方案。实验结果表明:论文提出的方法不仅大大缩短了任务的调度时间,而且具有非常强的通用性。The task execution time of the traditional static data flow task scheduling method is predictable.But in the real-time flow computing platform,the order of the data flow and the size of the data are uncertain,leading to the task execution time is uncertain.This paper presents a data flow task scheduling method based on Monte Carlo simulation method.This method generates a large amount of task execution time under a certain constraint condition by using a random number generation algorithm,and generates a corresponding precondition by the classical static scheduling algorithm(HEFT).Finally,an optimal pre-scheduling scheme is obtained through comprehensive comparison.The experimental results show that the method proposed in this paper not only greatly shortens the task scheduling time,but also has a very strong universality.

关 键 词：流计算 实时处理 任务调度 蒙特卡洛模拟法 

分 类 号：O141.4[理学—数学]