GFDM中基于高阶长短时记忆神经网络的自适应均衡器
2022年电子技术应用第8期
牛安东1,2,苗 硕1,2,刘佳宁1,2,李英善1,2
1.南开大学 电子信息与光学工程学院,天津300350;2.南开大学 光电传感器与传感网络技术重点实验室,天津300350
摘要: 在广义频分复用系统(GFDM)中,为解决5G网络下车载移动通信在Sub-6 GHz频段信道中信号严重失真的问题,提出一种基于高阶长短时记忆神经网络(HO-LSTM)结构的自适应均衡器。HO-LSTM自适应均衡器在传统高阶前馈神经网络(HO-FNN)的基础上,采用复杂度更低的广义记忆多项式模型(GMP)代替Volterra模型,并引入LSTM神经网络使其更适用于复杂非线性模型的预测。结果表明,相比于传统HO-FNN均衡器和LSTM均衡器,所提出的HO-LSTM均衡器的均衡效果显著提升,系统性能也得到进一步改善。
中圖分類號: TN911.7
文獻標識碼: A
DOI:10.16157/j.issn.0258-7998.212382
中文引用格式: 牛安東,苗碩,劉佳寧,等. GFDM中基于高階長短時記憶神經(jīng)網(wǎng)絡(luò)的自適應均衡器[J].電子技術(shù)應用,2022,48(8):95-100.
英文引用格式: Niu Andong,Miao Shuo,Liu Jianing,et al. An adaptive equalizer based on high order LSTM in GFDM[J]. Application of Electronic Technique,2022,48(8):95-100.
文獻標識碼: A
DOI:10.16157/j.issn.0258-7998.212382
中文引用格式: 牛安東,苗碩,劉佳寧,等. GFDM中基于高階長短時記憶神經(jīng)網(wǎng)絡(luò)的自適應均衡器[J].電子技術(shù)應用,2022,48(8):95-100.
英文引用格式: Niu Andong,Miao Shuo,Liu Jianing,et al. An adaptive equalizer based on high order LSTM in GFDM[J]. Application of Electronic Technique,2022,48(8):95-100.
An adaptive equalizer based on high order LSTM in GFDM
Niu Andong1,2,Miao Shuo1,2,Liu Jianing1,2,Li Yingshan1,2
1.College of Electronic Information and Optical Engineering,Nankai University,Tianjin 300350,China; 2.Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology,Nankai University,Tianjin 300350,China
Abstract: In the generalized frequency division multiplexing system(GFDM), in order to solve the problem of severe signal distortion in the sub-6 GHz frequency band channel of the vehicle-mounted mobile communication under the 5G network, an adaptive equalizer based on high order long short-term memory(HO-LSTM) neural network structure is proposed. Based on the traditional high-order feedforward neural network(HO-FNN), HO-LSTM adaptive equalizer uses the generalized memory polynomial model(GMP) with lower complexity instead of Volterra model, and introduces LSTM neural network to make it more suitable for the prediction of complex nonlinear models. The results show that, compared with the traditional HO-FNN equalizer and LSTM equalizer, the equalization effect of the proposed HO-LSTM equalizer is significantly improved, and the system performance is further improved.
Key words : generalized frequency division multiplexing(GFDM);long short-term memory(LSTM);high order neural network;generalized memory polynomial(GMP)
0 引言
近年來,第五代移動通信技術(shù)(5th Generation Mobile Communication Technology,5G)受到了極大的關(guān)注。廣義頻分復用技術(shù)(Generalized Frequency Division Multiplexing,GFDM)作為5G候選波形,由于其能夠有效地克服碼間干擾,讓依賴于超可靠低時延通信的車聯(lián)網(wǎng)等業(yè)務(wù)從中受益[1]。在中國工信部出臺的針對5G通信規(guī)劃中,將Sub-6 GHz頻段作為商用頻段。相比于第四代移動通信(4th Generation Mobile Communication Technology,4G)中1.8 GHz~2.7 GHz的低頻段信道,Sub-6 GHz的高頻段信道導致的信號失真會更加嚴重[2]。
目前接收端均衡技術(shù)是提高通信質(zhì)量的有效方法之一,傳統(tǒng)的均衡器分為線性均衡器和非線性均衡器兩種類型。其中非線性均衡器通常有兩種常用的設(shè)計方式:基于Volterra濾波器的方法[3-4]和基于神經(jīng)網(wǎng)絡(luò)的方法[5-7]。
本文詳細內(nèi)容請下載:http://m.ihrv.cn/resource/share/2000004659。
作者信息:
牛安東1,2,苗 碩1,2,劉佳寧1,2,李英善1,2
(1.南開大學 電子信息與光學工程學院,天津300350;2.南開大學 光電傳感器與傳感網(wǎng)絡(luò)技術(shù)重點實驗室,天津300350)

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。
