面向移动云计算任务调度的改进鸟群算法研究  

Research on task scheduling of improved bird group algorithm for mobile cloud computing

作　　者：陈暄[1] 赵文君 龙丹[3] Chen Xuan;Zhao Wenjun;Long Dan(Zhejiang Industry Polytechnic College,Shaoxing Zhejiang 312000,China;Beijing Information Science&Technology University,Beijing 100101,China;Zhejiang University,Hangzhou 310058,China)

机构地区：[1]浙江工业职业技术学院,浙江绍兴312000 [2]北京信息科技大学,北京100101 [3]浙江大学,杭州310058

出　　处：《计算机应用研究》2021年第3期751-754,781,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(LQ18A010003,11426205)。

摘　　要：针对移动云计算环境下的任务调度存在耗时长、设备能耗高的问题,提出了一种基于改进的鸟群算法(improved bird swarm algorithm,IBSA)的任务调度策略。首先,构建了以能耗和时间为主的移动云任务调度模型;其次,提出了自适应感知系数和社会系数,避免了算法陷入局部最优;构建了学习因子优化飞行行为,保证了个体寻优能力;最后,任务调度目标函数作为鸟群个体的适应度函数参与算法的迭代更新。仿真结果表明相比于蚁群算法、粒子群算法、鲸鱼算法等,改进的鸟群算法在移动云计算任务调度方面具有良好的效果,能够有效地节省时间和降低能耗。Aiming at the problem of long time-consuming and high equipment energy consumption for task scheduling in mobile cloud computing environment,this paper proposed a task scheduling strategy based on improved bird swarm algorithm(IBSA).Firstly,the method constructed a mobile cloud task scheduling model based on energy consumption and time.Secondly,it proposed adaptive sensing coefficients and social coefficients to prevent the algorithm from falling into a local optimum.It optimized the learning factors to optimize flight behavior and ensure that superior ability.Finally,it used the task scheduling objective function as the fitness function of the bird group to participate in the iterative updating of the algorithm.The simulation results show that the IBSA has good effects in mobile cloud computing task scheduling compared with ant colony algorithm,particle swarm algorithm,whale algorithm and bird swarm algorithm,which can effectively save time and reduce energy consumption.

关 键 词：移动云计算 鸟群算法 自适应 学习因子 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]