针对在大数据的处理过程中,对大数据任务的划分和资源分配缺乏合理性的问题,提出一种面向大数据任务的调度方法。该方法首先引入了调度理论用于处理大数据任务,帮助建立合理的大数据任务管理体系并规范大数据任务处理流程;然后,基于大...针对在大数据的处理过程中,对大数据任务的划分和资源分配缺乏合理性的问题,提出一种面向大数据任务的调度方法。该方法首先引入了调度理论用于处理大数据任务,帮助建立合理的大数据任务管理体系并规范大数据任务处理流程;然后,基于大数据任务的本质对数据集进行分析处理,引入决策表进行属性约简,以减小大数据分析任务的数据量和提高大数据分析效率;最后,采用模糊综合评价方法,将模糊综合评价的结果作为对任务调度的依据,以提高任务资源分配合理性。在UCI(University of California Irvine)数据集上进行测试,实验结果表明,该调度算法在平均预测准确度上比朴素贝叶斯(NB)算法高7.42个百分点,比误差反向传播(BP)算法高5.16个百分点,比均方根传递(RMSProp)算法高3.74个百分点。而对于特征数较多的数据集,所提算法在预测精度上较其他算法有显著提高。所提算法在平均调度长度比(SLR)上较HCPFS(Heterogeneous Critcal Path First Synthesis)算法和HIPLTS(Heterogeneous Improved Priority List for Task Scheduling)算法分别下降了12.14%和4.56%,在平均加速比上分别提升了7.14%和42.56%,表明该算法能有效提高大数据系统中任务调度的效率。综合比较分析,所提方法具有较高的预测精度,且高效可靠。展开更多
Aiming at the problems of low solution accuracy and high decision pressure when facing large-scale dynamic task allocation(DTA)and high-dimensional decision space with single agent,this paper combines the deep reinfor...Aiming at the problems of low solution accuracy and high decision pressure when facing large-scale dynamic task allocation(DTA)and high-dimensional decision space with single agent,this paper combines the deep reinforce-ment learning(DRL)theory and an improved Multi-Agent Deep Deterministic Policy Gradient(MADDPG-D2)algorithm with a dual experience replay pool and a dual noise based on multi-agent architecture is proposed to improve the efficiency of DTA.The algorithm is based on the traditional Multi-Agent Deep Deterministic Policy Gradient(MADDPG)algorithm,and considers the introduction of a double noise mechanism to increase the action exploration space in the early stage of the algorithm,and the introduction of a double experience pool to improve the data utilization rate;at the same time,in order to accelerate the training speed and efficiency of the agents,and to solve the cold-start problem of the training,the a priori knowledge technology is applied to the training of the algorithm.Finally,the MADDPG-D2 algorithm is compared and analyzed based on the digital battlefield of ground and air confrontation.The experimental results show that the agents trained by the MADDPG-D2 algorithm have higher win rates and average rewards,can utilize the resources more reasonably,and better solve the problem of the traditional single agent algorithms facing the difficulty of solving the problem in the high-dimensional decision space.The MADDPG-D2 algorithm based on multi-agent architecture proposed in this paper has certain superiority and rationality in DTA.展开更多
Mobile edge computing(MEC)-enabled satellite-terrestrial networks(STNs)can provide Internet of Things(IoT)devices with global computing services.Sometimes,the network state information is uncertain or unknown.To deal ...Mobile edge computing(MEC)-enabled satellite-terrestrial networks(STNs)can provide Internet of Things(IoT)devices with global computing services.Sometimes,the network state information is uncertain or unknown.To deal with this situation,we investigate online learning-based offloading decision and resource allocation in MEC-enabled STNs in this paper.The problem of minimizing the average sum task completion delay of all IoT devices over all time periods is formulated.We decompose this optimization problem into a task offloading decision problem and a computing resource allocation problem.A joint optimization scheme of offloading decision and resource allocation is then proposed,which consists of a task offloading decision algorithm based on the devices cooperation aided upper confidence bound(UCB)algorithm and a computing resource allocation algorithm based on the Lagrange multiplier method.Simulation results validate that the proposed scheme performs better than other baseline schemes.展开更多
文摘针对在大数据的处理过程中,对大数据任务的划分和资源分配缺乏合理性的问题,提出一种面向大数据任务的调度方法。该方法首先引入了调度理论用于处理大数据任务,帮助建立合理的大数据任务管理体系并规范大数据任务处理流程;然后,基于大数据任务的本质对数据集进行分析处理,引入决策表进行属性约简,以减小大数据分析任务的数据量和提高大数据分析效率;最后,采用模糊综合评价方法,将模糊综合评价的结果作为对任务调度的依据,以提高任务资源分配合理性。在UCI(University of California Irvine)数据集上进行测试,实验结果表明,该调度算法在平均预测准确度上比朴素贝叶斯(NB)算法高7.42个百分点,比误差反向传播(BP)算法高5.16个百分点,比均方根传递(RMSProp)算法高3.74个百分点。而对于特征数较多的数据集,所提算法在预测精度上较其他算法有显著提高。所提算法在平均调度长度比(SLR)上较HCPFS(Heterogeneous Critcal Path First Synthesis)算法和HIPLTS(Heterogeneous Improved Priority List for Task Scheduling)算法分别下降了12.14%和4.56%,在平均加速比上分别提升了7.14%和42.56%,表明该算法能有效提高大数据系统中任务调度的效率。综合比较分析,所提方法具有较高的预测精度,且高效可靠。
基金This research was funded by the Project of the National Natural Science Foundation of China,Grant Number 62106283.
文摘Aiming at the problems of low solution accuracy and high decision pressure when facing large-scale dynamic task allocation(DTA)and high-dimensional decision space with single agent,this paper combines the deep reinforce-ment learning(DRL)theory and an improved Multi-Agent Deep Deterministic Policy Gradient(MADDPG-D2)algorithm with a dual experience replay pool and a dual noise based on multi-agent architecture is proposed to improve the efficiency of DTA.The algorithm is based on the traditional Multi-Agent Deep Deterministic Policy Gradient(MADDPG)algorithm,and considers the introduction of a double noise mechanism to increase the action exploration space in the early stage of the algorithm,and the introduction of a double experience pool to improve the data utilization rate;at the same time,in order to accelerate the training speed and efficiency of the agents,and to solve the cold-start problem of the training,the a priori knowledge technology is applied to the training of the algorithm.Finally,the MADDPG-D2 algorithm is compared and analyzed based on the digital battlefield of ground and air confrontation.The experimental results show that the agents trained by the MADDPG-D2 algorithm have higher win rates and average rewards,can utilize the resources more reasonably,and better solve the problem of the traditional single agent algorithms facing the difficulty of solving the problem in the high-dimensional decision space.The MADDPG-D2 algorithm based on multi-agent architecture proposed in this paper has certain superiority and rationality in DTA.
基金supported by National Key Research and Development Program of China(2018YFC1504502).
文摘Mobile edge computing(MEC)-enabled satellite-terrestrial networks(STNs)can provide Internet of Things(IoT)devices with global computing services.Sometimes,the network state information is uncertain or unknown.To deal with this situation,we investigate online learning-based offloading decision and resource allocation in MEC-enabled STNs in this paper.The problem of minimizing the average sum task completion delay of all IoT devices over all time periods is formulated.We decompose this optimization problem into a task offloading decision problem and a computing resource allocation problem.A joint optimization scheme of offloading decision and resource allocation is then proposed,which consists of a task offloading decision algorithm based on the devices cooperation aided upper confidence bound(UCB)algorithm and a computing resource allocation algorithm based on the Lagrange multiplier method.Simulation results validate that the proposed scheme performs better than other baseline schemes.
