• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Distributed Computing Systems >Learning for Exception: Dynamic Service Caching in 5G-Enabled MECs with Bursty User Demands
【24h】

Learning for Exception: Dynamic Service Caching in 5G-Enabled MECs with Bursty User Demands

机译：学习例外：动态服务缓存在5G启用的MEC中，具有突发用户需求

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Mobile edge computing (MEC) is envisioned as an enabling technology for extreme low-latency services in the next generation 5G access networks. In a 5G-enabled MEC, computing resources are attached to base stations. In this way, network service providers can cache their services from remote data centers to base stations in the MEC to serve user tasks in their close proximity, thereby reducing the service latency. However, mobile users usually have various dynamic hidden features, such as their locations, user group tags, and mobility patterns. Such hidden features normally lead to uncertainties of the 5G-enabled MEC, such as user demand and processing delay. This poses significant challenges for the service caching and task offloading in a 5G-enabled MEC. In this paper, we investigate the problem of dynamic service caching and task offloading in a 5G-enabled MEC with user demand and processing delay uncertainties. We first propose an online learning algorithm for the problem with given user demands by utilizing the technique of Multi-Armed Bandits (MAB), and theoretically analyze the regret bound of the algorithm. We also propose a novel architecture of Generative Adversarial Networks (GAN) to accurately predict the user demands based on small samples of hidden features of mobile users. Based on the proposed GAN model, we then devise an efficient heuristic for the problem with the uncertainties of both user demand and processing delay. We finally evaluate the performance of the proposed algorithms by simulations based on a realistic dataset of user data. Experiment results show that the performance of the proposed algorithms outperform existing algorithms by around 15%.
机译：移动边缘计算（MEC）是设想为一个有利的技术，用于下一代5G接入网络极端低延迟服务。在启用5G-MEC，计算资源被连接到基站。通过这种方式，网络服务提供者可以从远程数据中心在MEC基站缓存服务，以满足他们的接近用户的任务，从而降低了服务延迟。然而，手机用户通常有各种动态隐藏的功能，比如它们的位置，用户群的标签，以及流动模式。这种隐藏的功能通常导致启用5G-MEC的不确定性，如用户需求和处理延迟。这给在启用5G-MEC服务缓存和任务卸载显著的挑战。在本文中，我们研究了动态服务缓存和任务卸载的启用5G-MEC用户需求及处理延迟的不确定性问题。我们首先通过利用多武装匪徒（MAB）的技术提出的问题，给予用户需求的在线学习算法，并从理论上分析约束算法的遗憾。我们还建议剖成对抗性网络（GAN）的一种新颖的体系结构，以准确地预测用户需求的基础上移动用户隐藏的功能小样本。基于提出的GAN模式，那么，我们制定了与两个用户的需求和处理延迟的不确定性问题的有效启发式。最后，我们评估基于用户数据的真实数据集所提出的算法通过模拟性能。实验结果表明，该算法的性能在15％左右优于现有的算法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号