基于机器学习的集群双向DAS能效技术

Machine learning generated clusters-based energy efficient power allocation for bidirectional DAS

双向分布式天线系统(bidirectional distributed antenna system,BDAS)是构建未来绿色通信的重要技术之一,但其在提高能效和降低能耗的同时,也给小区中的远程接入单元(remote access unit,RAU)与用户带来严重干扰.本研究提出在BDAS中构建基于机器学习的集群通信模式.首先,通过对BDAS中的用户进行聚类分析,将每个用户都归属一个集群;然后,根据集群中心与每个RAU的距离为集群中的用户选择通信所需的唯一服务基站;最后,在加入机器学习的集群BDAS中,对以最大化系统能量效率(energy efficiency,EE)和频谱效率(spectral efficiency,SE)为优化目标的功率分配方案进行求解.仿真结果表明,相比单一的BDAS,基于机器学习的集群双向分布式天线系统(BDAS based on machine learning generated clusters,BDAS-MLGC)能更有效地提高系统的SE和EE.

The bidirectional distributed antenna system(BDAS)is one of the important technologies for building the green communication system in the future.However,BDAS also causes serious interference to the remote access units(RAU)and users while bringing the improvement of energy efficiency and reduction of energy consumption.In this paper,we propose a communication mode based on machine learning generated clusters.Firstly,each user belongs to a cluster through clustering analysis of users in BDAS.And then,according to the distance between the cluster center and each RAU,we chose the only serving base station for users in the cluster,and finally we solve out the power allocation scheme with the optimization objectives of maximizing the system energy efficiency(EE)and spectral efficiency(SE).Simulation results show that the BDAS-MLGC,which is called the bidirectional distributed antenna system based on machine learning generated clusters,can improve SE and EE of the system more effectively than single BDAS.