Deep Reservoir Computing Meets 5G MIMO-OFDM Systems in Symbol Detection

Deep Reservoir Computing Meets 5G MIMO-OFDM Systems in Symbol Detection
复制标题

深储层计算在符号检测中满足 5G MIMO-OFDM 系统

DOI:
10.1609/aaai.v34i01.5481
复制
发表时间:
2020
期刊:
ArXiv
影响因子:
--
通讯作者:
Y. Yi
Y. Yi
中科院分区:
--
文献类型:
--
作者:
Zhou Zhou;Lingjia Liu;V. Chandrasekhar;Jianzhong Zhang;Y. Yi

文献摘要

参考文献

被引文献

相似文献

传统的储层计算(RC)是一种浅层循环神经网络(RNN),具有固定的高维隐藏动态和一个可训练的输出层。它有一个很好的特点,即需要有限的训练,这对于训练数据极其有限且获取成本高昂的某些应用程序至关重要。在本文中,我们考虑了两种将浅层架构扩展到深层 RC 的方法,以在不牺牲潜在收益的情况下提高性能:(1)将输出层扩展到三层结构,从而促进对神经元状态的联合时频处理; (2)依次堆叠RC,形成深度神经网络。由于 MIMO-OFDM 是第五代 (5G) 蜂窝网络的关键支持技术,因此我们使用深度 RC 的新结构重新设计了具有正交频分复用 (MIMO-OFDM) 信号的多输入多输出物理层接收器。 RNN 动态特性与 MIMO-OFDM 信号的时频结构相结合,使得深度 RC 能够处理非线性 MIMO-OFDM 信道中的各种干扰,从而实现比现有技术更高的性能。同时,与依赖大量训练的深度前馈神经网络不同,我们引入的深度 RC 框架可以使用与 5G 系统中传统基于模型的方法相同数量的导频来提供良好的泛化性能。数值实验表明,基于深度 RC 的接收器可以提供更快的学习收敛速度,并有效地减轻未知的非线性射频 (RF) 失真,与浅层 RC 结构相比,在误码率 (BER) 方面产生 20% 的增益。
Conventional reservoir computing (RC) is a shallow recurrent neural network (RNN) with fixed high dimensional hidden dynamics and one trainable output layer. It has the nice feature of requiring limited training which is critical for certain applications where training data is extremely limited and costly to obtain. In this paper, we consider two ways to extend the shallow architecture to deep RC to improve the performance without sacrificing the underlying benefit: (1) Extend the output layer to a three layer structure which promotes a joint time-frequency processing to neuron states; (2) Sequentially stack RCs to form a deep neural network. Using the new structure of the deep RC we redesign the physical layer receiver for multiple-input multiple-output with orthogonal frequency division multiplexing (MIMO-OFDM) signals since MIMO-OFDM is a key enabling technology in the 5th generation (5G) cellular network. The combination of RNN dynamics and the time-frequency structure of MIMO-OFDM signals allows deep RC to handle miscellaneous interference in nonlinear MIMO-OFDM channels to achieve improved performance compared to existing techniques. Meanwhile, rather than deep feedforward neural networks which rely on a massive amount of training, our introduced deep RC framework can provide a decent generalization performance using the same amount of pilots as conventional model-based methods in 5G systems. Numerical experiments show that the deep RC based receiver can offer a faster learning convergence and effectively mitigate unknown non-linear radio frequency (RF) distortion yielding twenty percent gain in terms of bit error rate (BER) over the shallow RC structure.
DOI: 10.1109/tnnls.2017.2766162
发表时间: 2018-10-01
影响因子: 10.4
作者:
Mosleh, Somayeh (Susanna);Liu, Lingjia;Yi, Yang
通讯作者: Yi, Yang
检测学习:通过下行链路导频进行 MIMO-OFDM 符号检测
DOI: 10.1109/twc.2020.2976004
发表时间: 2020
影响因子: 10.4
作者:
Zhou, Zhou;Liu, Lingjia;Chang, Hao-Hsuan
通讯作者: Chang, Hao-Hsuan
DOI: 10.1109/mwc.001.1900323
发表时间: 2020-04-01
影响因子: 12.9
作者:
Shafin, Rubayet;Liu, Lingjia;Zhang, Jianzhong (Charlie)
通讯作者: Zhang, Jianzhong (Charlie)
DOI: 10.1109/twc.2020.2996144
发表时间: 2020-08-01
影响因子: 10.4
作者:
Khani, Mehrdad;Alizadeh, Mohammad;Fleming, Phil
通讯作者: Fleming, Phil