Future wireless systems are trending towards higher carrier frequencies that offer larger communication bandwidth but necessitate the use of large antenna arrays. Existing signal processing techniques for channel estimation do not scale well to this "high-dimensional" regime in terms of performance and pilot overhead. Meanwhile, training deep learning based approaches for channel estimation requires large labeled datasets mapping pilot measurements to clean channel realizations, which can only be generated offline using simulated channels. In this paper, we develop a novel unsupervised over-the-air (OTA) algorithm that utilizes noisy received pilot measurements to train a deep generative model to output beamspace MIMO channel realizations. Our approach leverages Generative Adversarial Networks (GAN), while using a conditional input to distinguish between Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) channel realizations. We also present a federated implementation of the OTA algorithm that distributes the GAN training over multiple users and greatly reduces the user side computation. We then formulate channel estimation from a limited number of pilot measurements as an inverse problem and reconstruct the channel by optimizing the input vector of the trained generative model. Our proposed approach significantly outperforms Orthogonal Matching Pursuit on both LOS and NLOS channel models, and EM-GM-AMP -- an Approximate Message Passing algorithm -- on LOS channel models, while achieving comparable performance on NLOS channel models in terms of the normalized channel reconstruction error. More importantly, our proposed framework has the potential to be trained online using real noisy pilot measurements, is not restricted to a specific channel model and can even be utilized for a federated OTA design of a dataset generator from noisy data.
翻译:未来无线系统正趋向于更高的载体频率,提供更大的通信带宽,但需要使用大型天线阵列。现有用于频道估算的信号处理技术在性能和实验性管理管理上,与这种“高维”的系统不相称。同时,基于频道估算的深层次学习方法的培训需要大型标签数据集绘图试点测量,以清洁频道的实现,这只能通过模拟频道从网上生成。在本文中,我们开发了一种新的无监督的空中(OTA)算法,该算法将GAN培训从多个用户中传播,并大大降低用户的边际计算。我们采用的方法是利用General Adversarial 网络(GAN),同时使用有条件的输入数据来区分Sight-Sight(LOS)和Nn-Sight-Sight(NLOS)频道的实现情况。我们还介绍了OTA 将GAN培训的模型从多个用户中传播,并大大降低了用户的边际计算。我们从有限的试测模型中得出频道的估计数,作为反向问题的模型,并且通过优化的Oral-Mal-Mal-moal lader a a lader a lader a lader a lade lader a lader a lade lade lade lade lader a laction a laut a lader a lader a laction a lad dal dal lad dal lad mal lader lader ladal ladal lader ladal lader lader lady a lady lady lader lader lader lader lader lader lader lader lad lad lad lad lad ladal ladal ladal ladal ladal ladal lad ladal ladal ladal ladal ladal lad lad ladal lad ladal ladal ladal ladal ladal ladal ladal ladal ladal ladal lad