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

Jiajia Guo, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li

IEEE Transactions on Wireless Communications · 2020 · 377 citations · 52 references

Concepts

TL;DR

Massive MIMO promises higher capacity and energy efficiency, but its benefits rely on CSI at the base station, requiring bandwidth‑intensive feedback from user equipment, especially with large‑scale antennas. The authors propose a multiple‑rate compressive sensing neural network framework to compress and quantize CSI for more efficient feedback. They introduce two design principles, a new architecture CsiNet+ with a novel quantization framework and training strategy, and two variable‑rate variants (SM‑CsiNet+ and PM‑CsiNet+) that reduce UE parameters by 38–47 % while enabling parameter‑visualization analysis of the compression–reconstruction process. Experimental results show that CsiNet+ improves reconstruction accuracy, reduces UE storage, outperforms state‑of‑the‑art networks with only a slight increase in parameters, and demonstrates enhanced system feasibility.

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.

References

52