基于霍普菲尔德网络的云作业调度算法  

The Scheduling Algorithm of Cloud Job Based on Hopfield Neural Network

作　　者：郭玉栋[1] 左金平 Guo Yudong;Zuo Jinping(Network Information Center,Jinzhong University,JinZhong 030600,China;School of Information Technology&Engineering,Jinzhong University,JinZhong 030600,China)

机构地区：[1]晋中学院网络信息中心,山西晋中030600 [2]晋中学院信息技术与工程学院,山西晋中030600

出　　处：《系统仿真学报》2019年第12期2859-2867,共9页Journal of System Simulation

基　　金：山西省高等学校科技创新基金(20171118);山西省软科学计划研究基金(2016041008-6);山西省高等学校教学改革创新项目(J2019183)

摘　　要：针对当前云作业调度效率不高,资源利用不够充分,尚不能发挥其最大优势,提出一种基于霍普菲尔德网络的作业调度算法。为了实现系统资源调度能力的提高,分析影响云作业调度相关资源的特点;建立资源条件约束数学模型,再设计霍普菲儿德能量函数,并对其优化;通过标准用例集进行测试分析9个节点的平均利用率,并与3个典型算法进行性能和资源利用方面的比较。实验表明,该方法在效率上较其它3个算法有显著提升。Focusing on the low efficiency of cloud job scheduling and the insufficient utility of resource, a job scheduling algorithm based on Hopfield Neural Network is proposed. In order to improve the resource scheduling ability of the system, The resource characteristics which influence the cloud job scheduling are shown. The mathematical model of resource constraints is established, and the Hopfield energy function is designed and optimized. The average utilization rate of 9 nodes is analyzed by using the standard test cases, and the performance and resource utilization of the proposed strategy are compared with three typical algorithms. The results show that the average efficiency of the cloud job scheduling based on the algorithm is improved significantly.

关 键 词：HADOOP 云调度算法 Hopfield neural network MAPREDUCE 优化算法 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]