CR-GAN Complex Wireless Channel Modeling with Hidden Space Sampling and Hidden Feature Extraction

JIANG Bin; CHENG Zi-wei; BAO Jian-rong; LÜ Xin; ZHAO Yi-nan

doi:10.12263/DZXB.20230406

您当前的位置：

首页 >

文章列表页 >

CR-GAN Complex Wireless Channel Modeling with Hidden Space Sampling and Hidden Feature Extraction

PAPERS | 更新时间：2025-12-11

- CR-GAN Complex Wireless Channel Modeling with Hidden Space Sampling and Hidden Feature Extraction
- ACTA ELECTRONICA SINICA Vol. 52, Issue 6, Pages: 1817-1823(2024)
- 作者机构：
  
  1.杭州电子科技大学通信工程学院，浙江杭州 310018
  2.杭州电子科技大学电子信息学院，浙江杭州 310018
- 作者简介：
- 基金信息：
  
  Natural Science Foundation of Zhejiang Province(LZ24F010005)
- DOI：10.12263/DZXB.20230406
  CLC： TN929.5
- Received：06 May 2023，
  
  Revised：2024-01-12，
  
  Published：25 June 2024
- 稿件说明：
移动端阅览
姜斌,程子巍,包建荣,等. 隐空间采样与隐蔽特征提取的CR-GAN复杂无线信道建模[J]. 电子学报,2024,52(06):1817-1823.

JIANG Bin, CHENG Zi-wei, BAO Jian-rong, et al. CR-GAN Complex Wireless Channel Modeling with Hidden Space Sampling and Hidden Feature Extraction[J]. Acta Electronica Sinica, 2024, 52(06): 1817-1823.
姜斌,程子巍,包建荣,等. 隐空间采样与隐蔽特征提取的CR-GAN复杂无线信道建模[J]. 电子学报,2024,52(06):1817-1823. DOI：10.12263/DZXB.20230406

JIANG Bin, CHENG Zi-wei, BAO Jian-rong, et al. CR-GAN Complex Wireless Channel Modeling with Hidden Space Sampling and Hidden Feature Extraction[J]. Acta Electronica Sinica, 2024, 52(06): 1817-1823. DOI：10.12263/DZXB.20230406

摘要

为了更准确地建模随机无线信道，提出一种自适应增强条件生成对抗网络信道建模方法.其采用扩展的生成对抗网络（Generative Adversarial Network，GAN）开展训练，以近似估计无线信道响应，模拟真实无线环境信道.为了改善GAN训练稳定性和学习能力，引入条件信息和梯度惩罚项，并提出一种增强条件生成对抗网络框架，用于提取信道隐蔽特征.此外，还提出隐空间采样策略，以增加随机变量与生成数据的互信息量，提高所提框架的信道建模性能.仿真表明：所提框架能很好地模拟复杂无线信道分布.在信噪比为10 dB时，与现有GAN训练方法相比，其归一化均方误差性能改善约24%.

Abstract

To accurately model random wireless channels

an adaptive channel modeling framework based on a strengthened conditional generative adversarial network (GAN) is proposed. It utilizes the extended GAN for training to approximately estimate the response of wireless channels and thus stimulate the actual wireless channels. To improve both the GAN training stability and learning capability

conditional information and gradient penalty terms are introduced. Besides

a strengthened conditional GAN frame

named condition reinforcement GAN (CR-GAN)

is proposed to extract the essential hidden characteristics of wireless channels. In addition

a hidden space sampling strategy is utilized to increase the mutual information between the potential variables and generative data for the improved channel modeling performance of the proposed framework. Simulation results demonstrate that

at a signal-to-noise ratio of 10 dB

the proposed CR-GAN framework outperforms current GAN-based models by reducing 24% of the normalized mean squared error.

关键词

Keywords

references

赵雄文 , 张钰 , 秦鹏 , 等 . 空天地一体化无线光通信网络关键技术及其发展趋势 [J ] . 电子学报 , 2022 , 50 ( 1 ): 1 - 17 .

ZHAO X , ZHANG Y , QIN P , et al . Key technologies and development trends for a space-air-ground integrated wireless optical communication network [J ] . Acta Electronica Sinica , 2022 , 50 ( 1 ): 1 - 17 . (in Chinese)

张文茹 , 汪莞乔 , 官科 , 等 . 城市交通环境下23GHz 信道仿真建模 [J ] . 电子学报 , 2021 , 49 ( 10 ): 2069 - 2080 .

ZHANG W , WANG W , GUAN K , et al . Channel simulation modeling at 23GHz in urban scenarios [J ] . Acta Electronica Sinica , 2021 , 49 ( 10 ): 2069 - 2080 . (in Chinese)

程芳芳 , 王旭东 , 吴楠 . 基于最小二乘支持向量机的时变信道建模DCGAN信道下的端到端通信系统设计 [J ] . 电讯技术 , 2022 , 62 ( 6 ): 742 - 748 .

CHENG F , WANG X , WU N . Design of an end-to-end communication system in DCGAN channel [J ] . Telecommunication Engineering , 2022 , 62 ( 6 ): 742 - 748 . (in Chinese)

GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial networks [J ] . Communications of the ACM , 2020 , 63 ( 11 ): 139 - 144 .

O’SHEA T J , ROY T , WEST N . Approximating the void: Learning stochastic channel models from observation with variational generative adversarial networks [C ] // 2019 International Conference on Computing, Networking and Communications (ICNC) . Piscataway : IEEE , 2019 : 681 - 686 .

O’SHEA T , HOYDIS J . An introduction to deep learning for the physical layer [J ] . IEEE Transactions on Cognitive Communications and Networking , 2017 , 3 ( 4 ): 563 - 575 .

NAIR V , HINTON G E . Rectified linear units improve restricted boltzmann machines [C ] // Proceedings of the 27th International Conference on Machine Learning . New York : ACM , 2010 : 807 - 814 .

CRESWELL A , WHITE T , DUMOULIN V , et al . Generative adversarial networks: An overview [J ] . IEEE Signal Processing Magazine , 2018 , 35 ( 1 ): 53 - 65 .

ARJOVSKY M , BOTTOU L . Towards principled methods for training generative adversarial networks [EB/OL ] . [2023 ] . http://arxiv.org/abs/1701.04862.pdf http://arxiv.org/abs/1701.04862.pdf .

MIRZA M , OSINDERO S . Conditional generative adversarial nets [EB/OL ] . [2023 ] . http://arxiv.org/abs/1411.1784.pdf http://arxiv.org/abs/1411.1784.pdf .

ARJOVSKY M , CHINTALA S , BOTTOU L . Wasserstein generative adversarial networks [C ] // International Conference on Machine Learning . New York : ACM , 2017 : 214 - 223 .

FOURNIER N , GUILLIN A . On the rate of convergence in Wasserstein distance of the empirical measure [J ] . Probability Theory and Related Fields , 2015 , 162 ( 3 ): 707 - 738 .

GULRAJANI I , AHMED F , ARJOVSKY M , et al . Improved training of Wasserstein GANs [J ] . Advances in Neural Information Processing Systems , 2017 , 30 ( 1 ): 703 - 715 .

KINGMA D P , WELLING M . Auto-encoding variational Bayes [EB/OL ] . [2023 ] . http://arxiv.org/abs/1312.6114.pdf http://arxiv.org/abs/1312.6114.pdf .

BEVROYE L . An automatic method for generating random variates with a given characteristic function [J ] . SIAM Journal on Applied Mathematics , 1986 , 46 ( 4 ): 698 - 719 .

HU T Y , HUANG Y , ZHU Q M , et al . Channel estimation enhancement with generative adversarial networks [J ] . IEEE Transactions on Cognitive Communications and Networking , 2021 , 7 ( 1 ): 145 - 156 .

WU N , WANG X , LIN B , et al . A CNN-based end-to-end learning framework toward intelligent communication systems [J ] . IEEE Access , 2019 , 7 : 110197 - 110204 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Pedestrian Trajectory Prediction Method Using Dynamic Scene Information Based Transformer Generative Adversarial Network

Efficient Solution of Electromagnetic Response for Composite Structures Based on High-Order M-HODLR Algorithm

The Inevitability of Side-Channel Leakage in Encrypted Traffic

Automatic Modulation Recognition Method via Conceal-Truth-While-Showing-Fake Strategy in Non-Cooperative Adversarial Scenarios

Feature Masking and Contrastive Learning Integrating Multi-Dimensional Decorrelation in Sequential Recommendation

Related Author

PEI Zhao

QIU Wen-tao

WANG Miao

MA Miao

ZHANG Yan-ning

Zhao PEI

Wen-tao QIU

Miao WANG

Related Institution

National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology

Key Laboratory of Modern Teaching Technology（Ministry of Education）, Shaanxi Normal University

School of Computer Science, Shaanxi Normal University

School of Aeronautics and Astronautics, Shanghai Jiao Tong University

School of Computer Science, Northwestern Polytechnical University

⁰