期刊文献+

多基站下基于DRL的RAN切片资源分配 被引量:2

RAN slice resource allocation based on DRL in multi base stations
下载PDF
导出
摘要 在第五代移动通信中,网络切片被用来为各种业务提供一个最佳的网络。针对多基站下的RAN切片场景,以往的资源分配方法在切片的数量发生变化时无法满足切片的需求而且只适用于特定的场景,针对这个问题,提出了一种实现最佳资源分配且与切片数无关的方法。该方法先利用Ape-X方法(一种DRL方法)将资源分配给切片,再经过切片到基站的资源映射和用户资源分配来满足用户的需求。仿真结果表明,所提出的方法能够根据切片的状态和需求分配资源,分配了必要数量的RB以满足切片的需求而且不受切片数量变化的影响,同时该方法也具有很高的通用性能和扩展性。 In the 5th generation mobile communication,network slicing is used to provide an optimal network for various ser-vices.For the RAN slice scenario under multi base stations,the previous resource allocation methods couldn’t meet the demand of slices when the number of slices changed,and were only suitable for specific scenarios.To solve this problem,this paper proposed a method to achieve the best resource allocation independent of the number of slices.This method first used Ape-X me-thod(a DRL method)allocate resources to slices,and then met the needs of users through the resource mapping from slices to base stations and user resource allocation.The simulation results show that the proposed method can allocate resources accor-ding to the state and demand of slices,allocate the necessary number of RBs to meet the demand of slices,and is not affected by the change of the number of slices.At the same time,this method also has high general performance and scalability.
作者 马英洪 江凌云 Ma Yinghong;Jiang Lingyun(School of Communications&Information Engineering,Nanjing University of Posts&Telecommunication,Nanjing 210003,China)
出处 《计算机应用研究》 CSCD 北大核心 2022年第9期2791-2798,共8页 Application Research of Computers
基金 江苏省重点研发计划资助项目(BE2020084-4) 国家电网有限公司科研资助项目(DSY2021-005)。
关键词 多基站 网络切片 深度强化学习 无线接入网 资源分配 multi base station network slice deep reinforcement learning radio access network resource allocation
  • 相关文献

参考文献2

共引文献24

同被引文献13

引证文献2

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部