首页> 美国卫生研究院文献>Sensors (Basel Switzerland) >Hierarchical MEC Servers Deployment and User-MEC Server Association in C-RANs over WDM Ring Networks
【2h】

Hierarchical MEC Servers Deployment and User-MEC Server Association in C-RANs over WDM Ring Networks

机译:WDM环网上的C-RAN中的分层MEC服务器部署和用户MEC服务器关联

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

With the increasing number of Internet of Things (IoT) devices, a huge amount of latency-sensitive and computation-intensive IoT applications have been injected into the network. Deploying mobile edge computing (MEC) servers in cloud radio access network (C-RAN) is a promising candidate, which brings a number of critical IoT applications to the edge network, to reduce the heavy traffic load and the end-to-end latency. The MEC server’s deployment mechanism is highly related to the user allocation. Therefore, in this paper, we study hierarchical deployment of MEC servers and user allocation problem. We first formulate the problem as a mixed integer nonlinear programming (MINLP) model to minimize the deployment cost and average latency. In terms of the MINLP model, we then propose an enumeration algorithm and approximate algorithm based on the improved entropy weight and TOPSIS methods. Numerical results show that the proposed algorithms can reduce the total cost, and the approximate algorithm has lower total cost comparing the heaviest-location first and the latency-based algorithms.
机译:随着物联网(IoT)设备数量的增加,向网络中注入了大量对延迟敏感且计算密集型的IoT应用程序。在云无线电接入网络(C-RAN)中部署移动边缘计算(MEC)服务器是一个有前途的候选方案,它将为边缘网络带来许多关键的IoT应用程序,以减少繁重的流量负载和端到端延迟。 MEC服务器的部署机制与用户分配高度相关。因此,在本文中,我们研究了MEC服务器的分层部署和用户分配问题。我们首先将问题表述为混合整数非线性规划(MINLP)模型,以最大程度地降低部署成本和平均延迟。根据MINLP模型,我们提出了一种基于改进的熵权和TOPSIS方法的枚举算法和近似算法。数值结果表明,与重载优先算法和时延算法相比,该算法可以降低总成本,并且近似算法的总成本较低。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

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