云计算环境中基于改进粒子群优化的任务调度算法  

Task scheduling algorithm based on improved particle swarm optimization in cloud computing environments

作　　者：唐诗咏 索鸿飞 杨健伟 陆海 赵轲 TANG Shiyong;SUO Hongfei;YANG Jianwei;LU Hai;ZHAO Ke(State-owned Changhong Machinery Factory,Guilin 541003,China;School of Construction and Machinery,Chang’an University,Xi’an 710054,China)

机构地区：[1]国营长虹机械厂,广西桂林541003 [2]长安大学工程机械学院,陕西西安710054

出　　处：《电子设计工程》2024年第20期6-10,共5页Electronic Design Engineering

基　　金：陕西省博士后科研基金(2023BSHEDZZ219)。

摘　　要：针对云计算环境中的任务调度目的,采用了一种改进的粒子群优化(PSO)初始化方法,该方法将最长作业优先(LJFP)和最小完成时间(MCT)算法用于初始化PSO,通过与其他任务调度算法进行对比试验,得出所提出的LJFP-PSO和MCT-PSO算法在任务调度方面表现更优,能够实现更少的最大完成时间、更短的执行时间、更低的不平衡程度以及更少的总能耗,并且收敛速度可以加快一倍。In the context of task scheduling in cloud computing environments,an improved Particle Swarm Optimization(PSO)initialization method has been employed.This method incorporates a hybrid approach by integrating the Longest Job to Fastest Processor(LJFP)and Minimum Completion Time(MCT)algorithms for initializing PSO.Through comparative experiments with other task scheduling algorithms,the LJFP-PSO and MCT-PSO algorithms have demonstrated superior performance in terms of achieving reduced maximum completion time,shorter execution time,lower workload imbalance,and decreased overall energy consumption.Additionally,these proposed algorithms exhibit twice the convergence speed.

关 键 词：云计算 任务调度 粒子群优化算法 元启发式算法 最长作业优先 最小完成时 

分 类 号：TN919[电子电信—通信与信息系统]