arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.20110eess.SPcs.LG
收藏

ISDNN:一种用于大规模 MIMO 系统信道估计的深度神经网络

ISDNN: A Deep Neural Network for Channel Estimation in Massive MIMO systems

Information Technology Institute, Vietnam National University, Hanoi(河内越南国家大学信息技术研究院);University of Engineering and Technology, Vietnam National University, Hanoi(河内越南国家大学工程技术大学)

Do Hai Son, Vu Tung Lam, Tran Thi Thuy Quynh

AI总结:

本文面向大规模 MIMO 信道估计,利用深度展开将投影梯度下降迭代构建为 ISDNN,并提出融合侧信息的 S-ISDNN;实验显示其相较 DetNet 显著降低训练与运行时间并提升精度。

摘要:

大规模多输入多输出(massive MIMO)技术是 5G 及未来系统的基石。尽管 massive MIMO 技术带来了显著进步,但极多的天线数量在信道估计(CE)阶段引入了挑战。本文受数据检测算法最新进展启发,提出一种用于 CE 的单步深度神经网络(DNN),称为迭代序贯 DNN(ISDNN)。ISDNN 是一种基于投影梯度下降算法求解 CE 问题的 DNN,通过深度展开方法将迭代过程转化为 DNN。此外,我们提出结构化信道 ISDNN(S-ISDNN),将 ISDNN 扩展为融合信号方向和天线阵列配置等侧信息,以增强 CE。仿真结果表明,ISDNN 在训练时间(13%)、运行时间(4.6%)和精度(0.43 dB)方面显著优于另一种基于 DNN 的 CE 方法 DetNet。此外,S-ISDNN 在训练时间上比 ISDNN 更快,但其整体性能仍需进一步提升。

英文摘要:

Massive Multiple-Input Multiple-Output (massive MIMO) technology stands as a cornerstone in 5G and beyonds. Despite the remarkable advancements offered by massive MIMO technology, the extreme number of antennas introduces challenges during the channel estimation (CE) phase. In this paper, we propose a single-step Deep Neural Network (DNN) for CE, termed Iterative Sequential DNN (ISDNN), inspired by recent developments in data detection algorithms. ISDNN is a DNN based on the projected gradient descent algorithm for CE problems, with the iterative iterations transforming into a DNN using the deep unfolding method. Furthermore, we introduce the structured channel ISDNN (S-ISDNN), extending ISDNN to incorporate side information such as directions of signals and antenna array configurations for enhanced CE. Simulation results highlight that ISDNN significantly outperforms another DNN-based CE (DetNet), in terms of training time (13%), running time (4.6%), and accuracy (0.43 dB). Furthermore, the S-ISDNN demonstrates even faster than ISDNN in terms of training time, though its overall performance still requires further improvement.

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。

↑