Quality of Service Optimization in Mobile Edge Computing Networks via Deep Reinforcement Learning
Quality of Service Optimization in Mobile Edge Computing Networks via Deep Reinforcement Learning
复制标题
DOI：
10.1007/978-3-030-59016-1_13
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Li-Tse Hsieh;Hang Liu;Yang Guo;Robert Gazda
中科院分区：
文献类型：
--
作者：
Li-Tse Hsieh;Hang Liu;Yang Guo;Robert Gazda
移动的边缘计算（MEC）是一种新兴的范例，其将计算资源集成在无线接入网络中，以在接近移动的用户处以低延迟处理计算任务。在本文中，我们提出了一种基于在线双深度Q网络（DDQN）的学习方案，用于动态MEC网络中的任务分配，该方案使多个分布式边缘节点和云数据中心能够联合处理用户任务，以实现最佳的长期服务质量（QoS）。该方案捕获了广泛的动态网络参数，包括非静态节点计算能力、网络延迟统计和任务到达。它学习最优的任务分配策略，而不需要对底层动态知识进行假设。此外，该算法兼顾了性能和复杂度，并解决了传统Q学习中的状态和动作空间爆炸问题。评估结果表明，所提出的DDQN为基础的任务分配方案显着提高了QoS性能，相比现有的计划，不考虑网络动态的影响，预期的长期回报，而规模合理以及网络规模的增加。
Mobile edge computing (MEC) is an emerging paradigm that integrates computing resources in wireless access networks to process computational tasks in close proximity to mobile users with low latency. In this paper, we propose an online double deep Q networks (DDQN) based learning scheme for task assignment in dynamic MEC networks, which enables multiple distributed edge nodes and a cloud data center to jointly process user tasks to achieve optimal long-term quality of service (QoS). The proposed scheme captures a wide range of dynamic network parameters including non-stationary node computing capabilities, network delay statistics, and task arrivals. It learns the optimal task assignment policy with no assumption on the knowledge of the underlying dynamics. In addition, the proposed algorithm accounts for both performance and complexity, and addresses the state and action space explosion problem in conventional Q learning. The evaluation results show that the proposed DDQN-based task assignment scheme significantly improves the QoS performance, compared to the existing schemes that do not consider the effects of network dynamics on the expected long-term rewards, while scaling reasonably well as the network size increases.