Convolutional Neural Network-Based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis

Abstract

Massive multiple-input multiple-output (MIMO) is a promising technology to increase link capacity and energy efficiency. However, these benefits are based on available channel state information (CSI) at the base station (BS). Therefore, user equipment (UE) needs to keep on feeding CSI back to the BS, thereby consuming precious bandwidth resource. Large-scale antennas at the BS for massive MIMO seriously increase this overhead. In this paper, we propose a multiple-rate compressive sensing neural network framework to compress and quantize the CSI. This framework not only improves reconstruction accuracy but also decreases storage space at the UE, thus enhancing the system feasibility. Specifically, we establish two network design principles for CSI feedback, propose a new network architecture, CsiNet+, according to these principles, and develop a novel quantization framework and training strategy.Next, we further introduce two different variable-rate approaches, namely, SM-CsiNet+ and PM-CsiNet+, which decrease the parameter number at the UE by 38.0% and 46.7%, respectively. Experimental results show that CsiNet+ outperforms the state-of-the-art network by a margin but only slightly increases the parameter number. We also investigate the compression and reconstruction mechanism behind deep learning-based CSI feedback methods via parameter visualization, which provides a guideline for subsequent research.

ELM-Based Superimposed CSI Feedback for FDD Massive MIMO System

“…In [15], a bit-level optimized NN, i.e., the joint convolutional residual network (JC-ResNet), was constructed with both CSI compression and quantization. By employing the multiple-rate CS neural network framework, [16] compressed and quantized the CSI to improve reconstruction accuracy and decrease storage space. The architecture in [17], which was composed of convolutional layers followed by quantization and entropy coding blocks, presented promising performance.…”

“…Reduce downlink CSI interference according to(14) with i = 1, i.e., use the expert knowledge to obtain d Utilize DET-ELM1 to detect UL-US with input d(1) u , i.e., perform a detection to obtain d(1) u , which is expressed in (15) with i = 1. 6): Eliminate UL-US interference according to(16), i.e., use the expert knowledge to obtain h Use CSI-ELM2 to estimate downlink CSI with input h(2)u , which is represented in (13) with i = 2, where the estimated downlink CSI is denoted by h(2) u . 8): Remove downlink CSI interference according to(14) with i = 2,i.e., use the expert knowledge to obtain d Utilize DET-ELM2 to detect UL-US with input d(2) u , i.e., detect to obtain d(2) u , which is expressed in (15) with i = 2.…”

Deep Learning-Based Downlink Channel Prediction for FDD Massive MIMO System

“…has been recognized as a potential solution to deal with the high complexity and overheads of wireless communication system [11]- [28]. Great success has been achieved in various applications such as channel estimation [13], [14], data detection [15], [16], CSI feedback [17]- [19], beamforming [20]- [22], and hybrid precoding [23], etc. Furthermore, AI based downlink CSI prediction for FDD systems has also been studied in many works [25]- [28].…”

CNN-Based Analog CSI Feedback in FDD MIMO-OFDM Systems

“…Following the recent resurgence of machine learning, and more specifically deep learning (DL) techniques for physical layer communications [7], DL-based MIMO CSI compression techniques have been shown to provide significant improvements over previous works utilizing compressive sensing and sparsifying transforms [8], [9]. DL approaches use autoencoder architectures to compress the CSI, and most of them [8]- [13] train the autoencoder assuming ideal feedback of the compressed CSI from the UE to the BS. However, the encoder output is fed back to the BS through the uplink channel, and needs to be encoded to overcome channel impairments (e.g.…”