ZTE Communications ›› 2025, Vol. 23 ›› Issue (2): 20-30.DOI: 10.12142/ZTECOM.202502004

• Special Topic • Previous Articles     Next Articles

A Machine Learning-Based Channel Data Enhancement Platform for Digital Twin Channels

AI Bo1, ZHANG Yuxin1, YANG Mi1(), HE Ruisi1, GUO Rongge2   

  1. 1.School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China
    2.School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, China
  • Received:2025-03-17 Online:2025-06-25 Published:2025-06-10
  • Contact: YANG Mi
  • About author:AI Bo received his MS and PhD degrees from Xidian University, China in 2002 and 2004, respectively. He was an Excellent Postdoctoral Research Fellow with Tsinghua University, China in 2007. He is currently a professor with the State Key Laboratory of Advanced Rail Autonomous Operation and School of Electronic and Information Engineering, Beijing Jiaotong University, China. He has authored or co-authored eight books and published over 300 academic research papers. His five papers have been recognized as ESI highly cited papers. His research interests include channel measurement and channel modeling, and dedicated mobile communications for rail traffic systems.
    ZHANG Yuxin received her MS degree in information and communication engineering from Beijing Jiaotong University (BJTU), China in 2024. She is currently pursuing a PhD degree at the School of Electronics and Information Engineering, BJTU. Her current research focuses on artificial intelligence-based wireless channel modeling.
    YANG Mi ( myang@bjtu.edu.cn) received his MS and PhD degrees from Beijing Jiaotong University, China in 2017 and 2021, respectively. He is currently an associate professor with the State Key Laboratory of Advanced Rail Autonomous Operation and the School of Electronic and Information Engineering, Beijing Jiaotong University. His research interests include wireless channel measurement and modeling.
    HE Ruisi received his BE and PhD degrees from Beijing Jiaotong University (BJTU), China in 2009 and 2015, respectively. He is currently a professor with the School of Electronics and Information Engineering, BJTU. He has been a visiting scholar at Georgia Institute of Technology, USA, University of Southern California, USA, and Université Catholique de Louvain (UCLouvain), Belgium. His research interests include wireless propagation channels, 5G, and 6G communications. He has authored/co-authored eight books, five book chapters, more than 200 journal and conference papers, and several patents.
    GUO Rongge received her BS degree from Sun Yat-sen University, China in 2014, and MS and PhD degrees from Beijing Jiaotong University, China in 2017 and 2021, respectively. She is currently a lecturer with the School of Traffic and Transportation, Beijing Jiaotong University. Her research interests include public transport, intelligent transport systems (ITS), transport planning, transport management, and traffic control.
  • Supported by:
    the National Key R&D Program of China(2023YFB2904802);National Natural Science Foundation of China(62301022);Young Elite Scientists Sponsorship Program by CAST(2022QNRC001);Program for Science & Technology R&D Plan Joint Fund of Henan Province(225200810112)

Abstract:

Reliable channel data helps characterize the limitations and performance boundaries of communication technologies accurately. However, channel measurement is highly costly and time-consuming, and taking actual measurement as the only channel data source may reduce efficiency because of the constraints of high testing difficulty and limited data volume. Although existing standard channel models can generate channel data, their authenticity and diversity cannot be guaranteed. To address this, we use deep learning methods to learn the attributes of limited measured data and propose a generative model based on generative adversarial networks to rapidly synthesize data. A software simulation platform is also established to verify that the proposed model can generate data that are statistically similar to the measured data while maintaining necessary randomness. The proposed algorithm and platform can be applied to channel data enhancement and serve channel modeling and algorithm evaluation applications with urgent needs for data.

Key words: channel measurement, channel modeling, deep learning, data enhancement