In cell-free multiple input multiple output (MIMO) networks, multiple base stations (BSs) can collaborate to achieve high spectral efficiency. Nevertheless, high penetration loss due to large blockages in harsh propagation environments is often an issue that severely degrades communication performance. Considering that intelligent reflecting surface (IRS) is capable of constructing digitally controllable reflection links in a low-cost manner, we investigate an IRS-enhanced downlink cell-free MIMO network in this paper. We aim to maximize the sum rate of all the users by jointly optimizing the transmit beamforming at the BSs and the reflection coefficients at the IRS. To address the optimization problem, we propose a fully distributed machine learning algorithm. Compared with the conventional iterative optimization algorithms that require a central processing at the central processing unit and large amount of channel state information and signaling exchange among the BSs, each BS can locally design its beamforming vector in the proposed algorithm. Meanwhile, the IRS reflection coefficients are determined by one of the BSs. Simulation results show that the deployment of IRS can significantly boost the sum user rate and that the proposed algorithm outperforms the benchmark methods.
翻译:在无细胞多输入多重输出(MIMO)网络中,多个基站(BS)可以合作实现高光谱效率。然而,在严酷的传播环境中,大型阻塞造成的高渗透率损失往往是一个严重降低通信性能的问题。考虑到智能反射表面(IRS)能够以低成本的方式构建可控制的数字反射链,我们调查本文中的IRS加固的无下链接细胞MIMO网络。我们的目标是通过联合优化BS的传输光束和IRS的反射系数,使所有用户的总和率最大化。为了解决优化问题,我们建议了完全分布的机器学习算法。与常规的迭代优化算法相比,该算法需要在中央处理单位进行中央处理,需要大量频道状态信息和信号BS之间的交换,每个BS都可以在本地设计其拟议算法中的成型矢量。与此同时,IRS反射系数是由一个BS Pers决定的。模拟结果显示,IRS的部署可以大大提升用户总比值和拟议算法外的方法。