移动边缘计算中基于深度强化学习的计算卸载调度方法

Deep reinforcement learning based offloading scheduling in mobile edge computing

针对移动边缘计算中具有依赖关系的任务的卸载决策问题,提出一种基于深度强化学习的任务卸载调度方法,以最小化应用程序的执行时间。任务调度的过程被描述为一个马尔可夫决策过程,其调度策略由所提出的序列到序列深度神经网络表示,并通过近端策略优化(proximal policy optimization)方法进行训练。仿真实验表明,所提出的算法具有良好的收敛能力,并且在不同环境下的表现均优于所对比的六个基线算法,证明了该方法的有效性和可靠性。

Aiming at the problem of task offloading with dependency in mobile edge computing,this paper proposed a deep reinforcement learning based offloading scheduling method to minimize the execution time of mobile applications.This method described the process of task scheduling as a Markov decision process.It adopted a sequence to sequence deep neural network to represent the scheduling policy,and then trained the deep neural network with the proximal policy optimization method.Simulation results show that the proposed method has good convergence ability and outperforms six baseline algorithms in different environments,demonstrating the effectiveness and reliability of the proposed method.