摘要
随着5G时代的到来,移动边缘计算(MEC)在移动网络的RAN侧提供计算、资源存储和IT服务等系统功能,实现高带宽、低时延的业务支撑和本地管理。从长远角度来看,边缘服务器的合理部署可以提高MEC的服务质量,节省运营商的成本,降低网络资源的浪费。为此,文中提出一种加权K⁃means算法来优化边缘服务器的部署问题。所提方案根据基站侧的日统计流量计算不同区域范围内移动终端的权值,通过目标方程和约束进行算法设计。在实验阶段,分别通过加权K⁃means算法、传统K⁃means算法和随机选择的方法得到边缘服务器的部署位置。在不考虑传输链路异常等情况下,基于不同服务器个数和测试时段,分别计算移动设备与边缘服务器的响应时延。评估结果表明,在相同的移动终端分布和资源分配的条件下,相较于传统K⁃means算法和随机选择方法,所提方案能够提供更好的部署位置,减少设备的响应时延。
With the advent of the 5G era,mobile edge computing(MEC)can provide the system functions of computation,resource storage,and IT services on the RAN side of mobile networks to achieve high⁃bandwidth,low⁃latency business support and local management.In the long run,the reasonable deployment of edge server can improve the service quality of MEC,save the cost of operators and reduce the waste of network resources.Therefore,a weighted K⁃means algorithm is proposed to optimize the deployment of edge servers.In the proposed scheme,the weights of mobile terminals in different regions are calculated according to the daily statistical traffic on the base station side,and the algorithm is designed according to the objective equation and constraints.In the experimental stage,the weighted K⁃means algorithm,traditional K⁃means algorithm and random selection method are adopted respectively to obtain the deployment location of edge server.Without considering abnormal transmission link,the response delays of mobile devices and edge servers are calculated respectively based on different number of servers and testing periods.The evaluation results show that,under the same condition of mobile terminal distribution and resource allocation,the proposed scheme can provide a better deployment location and reduce the response delay of the devices in comparison with the traditional K⁃means algorithm and random selection method.
作者
刘乃安
张澍文
李晓辉
吕思婷
LIU Naian;ZHANG Shuwen;LI Xiaohui;LÜSiting(School of Telecommunications Engineering,Xidian University,Xi’an 710071,China;Guangzhou Institute of Technology,Xidian University,Guangzhou 510555,China)
出处
《现代电子技术》
2022年第24期11-15,共5页
Modern Electronics Technique