arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.01098eess.SPcs.AR
收藏

面向Zynq片上系统中基于导频OFDM的低复杂度深度学习增强无线信道估计

Low Complexity Deep Learning Augmented Wireless Channel Estimation for Pilot-Based OFDM on Zynq System on Chip

Animesh Sharma, Syed Asrar Ul Haq, Sumit J. Darak

AI总结:

本文针对无线OFDM信道估计在Zynq SoC上的部署难题,提出计算高效的LSiDNN算法,在保持或提升MSE/BER性能的同时显著降低执行时间与FPGA资源占用。

摘要:

信道估计(CE)是无线物理层(PHY)的关键信号处理任务之一。近期基于深度学习(DL)的CE在性能上优于最小二乘CE(LS)和线性最小均方误差CE(LMMSE)等统计方法。然而,现有CE方法尚未在片上系统(SoC)上实现。本文的第一项贡献是通过软硬件协同设计和定点分析,在由ARM处理器和现场可编程门阵列(FPGA)组成的Zynq SoC(ZSoC)上高效实现现有最先进的CE算法。我们针对不同信噪比(SNR)和无线信道,以均方误差(MSE)和误码率(BER)验证了基于DL的CE和LMMSE相对LS的优越性。我们还强调了基于DL的CE和LMMSE方法的高复杂度、执行时间和功耗。为解决这一问题,我们提出一种新颖的计算高效的LS增强插值深度神经网络(LSiDNN)CE算法,并在ZSoC上实现。在相同MSE和BER下,所提出的LSiDNN相比最先进的基于DL的CE执行时间降低88–90%,资源利用率降低38–85%。LSiDNN的MSE和BER显著低于LMMSE,并且随着收发器之间移动性的增强,增益进一步提升。相比LMMSE,其执行时间降低75%,资源利用率降低90–94%。

英文摘要:

Channel estimation (CE) is one of the critical signal-processing tasks of the wireless physical layer (PHY). Recent deep learning (DL) based CE have outperformed statistical approaches such as least-square-based CE (LS) and linear minimum mean square error-based CE (LMMSE). However, existing CE approaches have not yet been realized on system-on-chip (SoC). The first contribution of this paper is to efficiently implement the existing state-of-the-art CE algorithms on Zynq SoC (ZSoC), comprising of ARM processor and field programmable gate array (FPGA), via hardware-software co-design and fixed point analysis. We validate the superiority of DL-based CE and LMMSE over LS for various signal-to-noise ratios (SNR) and wireless channels in terms of mean square error (MSE) and bit error rate (BER). We also highlight the high complexity, execution time, and power consumption of DL-based CE and LMMSE approaches. To address this, we propose a novel compute-efficient LS-augmented interpolated deep neural network (LSiDNN) based CE algorithm and realize it on ZSoC. The proposed LSiDNN offers 88-90% lower execution time and 38-85% lower resource utilization than state-of-the-art DL-based CE for identical MSE and BER. LSiDNN offers significantly lower MSE and BER than LMMSE, and the gain improves with increased mobility between transceivers. It offers 75% lower execution time and 90-94% lower resource utilization than LMMSE.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑