D-Band 4.6 km 2 × 2 MIMO Photonic-Assisted Terahertz Wireless Communication Utilizing Iterative Pruning Deep Neural Network-Based Nonlinear Equalization

In this paper, we explore the enhancement of a 4.6 km dual-polarization 2 × 2 MIMO D-band photonic-assisted terahertz communication system using iterative pruning-based deep neural network (DNN) nonlinear equalization techniques. The system employs advanced digital signal processing (DSP) methods, i...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingwen Lin, Sicong Xu, Qihang Wang, Jie Zhang, Jingtao Ge, Siqi Wang, Zhihang Ou, Yuan Ma, Wen Zhou, Jianjun Yu
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Photonics
Subjects:
Online Access:https://www.mdpi.com/2304-6732/11/11/1009
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846152682779181056
author Jingwen Lin
Sicong Xu
Qihang Wang
Jie Zhang
Jingtao Ge
Siqi Wang
Zhihang Ou
Yuan Ma
Wen Zhou
Jianjun Yu
author_facet Jingwen Lin
Sicong Xu
Qihang Wang
Jie Zhang
Jingtao Ge
Siqi Wang
Zhihang Ou
Yuan Ma
Wen Zhou
Jianjun Yu
author_sort Jingwen Lin
collection DOAJ
description In this paper, we explore the enhancement of a 4.6 km dual-polarization 2 × 2 MIMO D-band photonic-assisted terahertz communication system using iterative pruning-based deep neural network (DNN) nonlinear equalization techniques. The system employs advanced digital signal processing (DSP) methods, including down-conversion, resampling, matched filtering, and various equalization algorithms to combat signal distortions. We demonstrate the effectiveness of DNN and iterative pruning techniques in significantly reducing bit error rates (BERs) across a range of symbol rates (10 Gbaud to 30 Gbaud) and polarization states (vertical and horizontal). Before pruning, at 10 GBaud transmission, the lowest BER was 0.0362, and at 30 GBaud transmission, the lowest BER was 0.1826, both of which did not meet the 20% soft-decision forward error correction (SD-FEC) threshold. After pruning, the BER at different transmission rates was reduced to below the hard decision forward error correction (HD-FEC) threshold, indicating a substantial improvement in signal quality. Additionally, the pruning process contributed to a decrease in network complexity, with a maximum reduction of 85.9% for 10 GBaud signals and 63.0% for 30 GBaud signals. These findings indicate the potential of DNN and pruning techniques to enhance the performance and efficiency of terahertz communication systems, providing valuable insights for future high-capacity, long-distance wireless networks.
format Article
id doaj-art-ffe16cfcfab54aecb846c8cec81f44ca
institution Kabale University
issn 2304-6732
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Photonics
spelling doaj-art-ffe16cfcfab54aecb846c8cec81f44ca2024-11-26T18:18:15ZengMDPI AGPhotonics2304-67322024-10-011111100910.3390/photonics11111009D-Band 4.6 km 2 × 2 MIMO Photonic-Assisted Terahertz Wireless Communication Utilizing Iterative Pruning Deep Neural Network-Based Nonlinear EqualizationJingwen Lin0Sicong Xu1Qihang Wang2Jie Zhang3Jingtao Ge4Siqi Wang5Zhihang Ou6Yuan Ma7Wen Zhou8Jianjun Yu9Shanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaShanghai Institute for Advanced Communication and Data Science, Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, ChinaIn this paper, we explore the enhancement of a 4.6 km dual-polarization 2 × 2 MIMO D-band photonic-assisted terahertz communication system using iterative pruning-based deep neural network (DNN) nonlinear equalization techniques. The system employs advanced digital signal processing (DSP) methods, including down-conversion, resampling, matched filtering, and various equalization algorithms to combat signal distortions. We demonstrate the effectiveness of DNN and iterative pruning techniques in significantly reducing bit error rates (BERs) across a range of symbol rates (10 Gbaud to 30 Gbaud) and polarization states (vertical and horizontal). Before pruning, at 10 GBaud transmission, the lowest BER was 0.0362, and at 30 GBaud transmission, the lowest BER was 0.1826, both of which did not meet the 20% soft-decision forward error correction (SD-FEC) threshold. After pruning, the BER at different transmission rates was reduced to below the hard decision forward error correction (HD-FEC) threshold, indicating a substantial improvement in signal quality. Additionally, the pruning process contributed to a decrease in network complexity, with a maximum reduction of 85.9% for 10 GBaud signals and 63.0% for 30 GBaud signals. These findings indicate the potential of DNN and pruning techniques to enhance the performance and efficiency of terahertz communication systems, providing valuable insights for future high-capacity, long-distance wireless networks.https://www.mdpi.com/2304-6732/11/11/1009deep neural networkphotonic-aided terahertz communication systemiterative pruning
spellingShingle Jingwen Lin
Sicong Xu
Qihang Wang
Jie Zhang
Jingtao Ge
Siqi Wang
Zhihang Ou
Yuan Ma
Wen Zhou
Jianjun Yu
D-Band 4.6 km 2 × 2 MIMO Photonic-Assisted Terahertz Wireless Communication Utilizing Iterative Pruning Deep Neural Network-Based Nonlinear Equalization
Photonics
deep neural network
photonic-aided terahertz communication system
iterative pruning
title D-Band 4.6 km 2 × 2 MIMO Photonic-Assisted Terahertz Wireless Communication Utilizing Iterative Pruning Deep Neural Network-Based Nonlinear Equalization
title_full D-Band 4.6 km 2 × 2 MIMO Photonic-Assisted Terahertz Wireless Communication Utilizing Iterative Pruning Deep Neural Network-Based Nonlinear Equalization
title_fullStr D-Band 4.6 km 2 × 2 MIMO Photonic-Assisted Terahertz Wireless Communication Utilizing Iterative Pruning Deep Neural Network-Based Nonlinear Equalization
title_full_unstemmed D-Band 4.6 km 2 × 2 MIMO Photonic-Assisted Terahertz Wireless Communication Utilizing Iterative Pruning Deep Neural Network-Based Nonlinear Equalization
title_short D-Band 4.6 km 2 × 2 MIMO Photonic-Assisted Terahertz Wireless Communication Utilizing Iterative Pruning Deep Neural Network-Based Nonlinear Equalization
title_sort d band 4 6 km 2 2 mimo photonic assisted terahertz wireless communication utilizing iterative pruning deep neural network based nonlinear equalization
topic deep neural network
photonic-aided terahertz communication system
iterative pruning
url https://www.mdpi.com/2304-6732/11/11/1009
work_keys_str_mv AT jingwenlin dband46km22mimophotonicassistedterahertzwirelesscommunicationutilizingiterativepruningdeepneuralnetworkbasednonlinearequalization
AT sicongxu dband46km22mimophotonicassistedterahertzwirelesscommunicationutilizingiterativepruningdeepneuralnetworkbasednonlinearequalization
AT qihangwang dband46km22mimophotonicassistedterahertzwirelesscommunicationutilizingiterativepruningdeepneuralnetworkbasednonlinearequalization
AT jiezhang dband46km22mimophotonicassistedterahertzwirelesscommunicationutilizingiterativepruningdeepneuralnetworkbasednonlinearequalization
AT jingtaoge dband46km22mimophotonicassistedterahertzwirelesscommunicationutilizingiterativepruningdeepneuralnetworkbasednonlinearequalization
AT siqiwang dband46km22mimophotonicassistedterahertzwirelesscommunicationutilizingiterativepruningdeepneuralnetworkbasednonlinearequalization
AT zhihangou dband46km22mimophotonicassistedterahertzwirelesscommunicationutilizingiterativepruningdeepneuralnetworkbasednonlinearequalization
AT yuanma dband46km22mimophotonicassistedterahertzwirelesscommunicationutilizingiterativepruningdeepneuralnetworkbasednonlinearequalization
AT wenzhou dband46km22mimophotonicassistedterahertzwirelesscommunicationutilizingiterativepruningdeepneuralnetworkbasednonlinearequalization
AT jianjunyu dband46km22mimophotonicassistedterahertzwirelesscommunicationutilizingiterativepruningdeepneuralnetworkbasednonlinearequalization