Energy Efficient Power Allocation Based on Machine Learning Generated Clusters for Distributed Antenna Systems
Energy Efficient Power Allocation Based on Machine Learning Generated Clusters for Distributed Antenna Systems
复制标题
基于机器学习生成的分布式天线系统集群的节能功率分配
DOI：
10.1109/access.2019.2914159
复制
发表时间：
2019-01-01
期刊：
影响因子：
3.9
通讯作者：
Feng, Daquan
中科院分区：
文献类型：
--
作者：
He, Chunlong;Zhou, Yuehua;Feng, Daquan
在本文中，我们考虑了机器学习（ML）和无线通信的结合。本文在分布式天线系统（DAS）中设计了一种机器学习生成的聚类模型，该模型由两种不同的机器学习聚类算法构建，即$k$ -means算法和基于高斯混合模型（GMM）算法。在具有ML生成簇模型的DAS通信场景下，我们分别研究了DAS中频谱效率（SE）最大化和能量效率（EE）最大化两种不同的功率分配优化问题。我们比较了DAS与ML生成的聚类模型和常规模型的SE和EE。仿真结果验证了基于ML生成聚类模型的DAS的有效性，与DAS中传统的通信模型相比，该模型可以获得更好的SE和EE性能。
In this paper, we consider the combination of machine learning (ML) and wireless communication. We design a machine learning generated clusters model in a distributed antenna system (DAS), which is constructed by two different ML clustering algorithms, i.e., $k$ -means algorithm and Gaussian mixture model-based (GMM) algorithm. Under the communication scenario of DAS with ML generated clusters model, we investigate two different power allocation optimization problems with the interference of maximizing spectral efficiency (SE) and energy efficiency (EE) in DAS, respectively. We compare the SE and EE of DAS with ML generated clusters model and the conventional model. The simulation results verify the effectiveness of DAS with ML generated clusters model, which can obtain the much better performance of SE and EE compared with the conventional communication model in DAS.