ZTE

ZTE Communications ›› 2025, Vol. 23 ›› Issue (4): 37-47.DOI: 10.12142/ZTECOM.202504006

• Special Topic • Previous Articles     Next Articles

Root Cause Analysis of Poor FTTR Quality Based on Transformer Mechanisms

YU Weichao, LIU Yang, ZHANG Junxiong, YE Junliang, GE Xiaohu()   

  1. School of Electronic Information and Communication, Huazhong University of Science and Technology, Wuhan 430074, China
  • Received:2025-11-11 Online:2025-12-25 Published:2025-12-22
  • About author:YU Weichao received his BS degree in communication engineering from the School of Electronic Information and Communications, Huazhong University of Science and Technology, China in 2024, where he is currently pursuing his MS degree. His research interests include FTTR, Wi-Fi, and artificial intelligence.
    LIU Yang received his BS degree in electronics science and technology from Huazhong University of Science and Technology, China in 2018, where he is currently pursuing his PhD degree. His research interests include Wi-Fi 7 and FTTR technologies.
    ZHANG Junxiong received his ME degree in electronic information engineering from Huazhong University of Science and Technology, China in 2021. He is currently pursuing his PhD degree at the same institution. His research interests include Det-Wi-Fi and FTTR technologies.
    YE Junliang received his BS degree in communication engineering from China University of Geosciences in 2011, and PhD degree from Huazhong University of Science and Technology, China in 2018. His research interests include heterogeneous networks, stochastic geometry, mobility-based access models of cellular networks, millimeter wave communications, and next-generation wireless communications.
    GE Xiaohu (xhge@mail.hust.edu.cn) received his PhD degree in communication and information engineering from Huazhong University of Science and Technology (HUST), China in 2003. He was a researcher at Ajou University, Republic of Korea, and Politecnico di Torino, Italy from 2004 to 2005. He has been with HUST since 2005 and is currently a full professor at the School of Electronic Information and Communications, HUST. He is also an adjunct professor with the Faculty of Engineering and Information Technology, University of Technology Sydney, Australia. His research interests include mobile communications, traffic modeling in wireless networks, green communications, and interference modeling in wireless communications. He was the recipient of the Best Paper Award at IEEE Globecom 2010. Prof. GE is the Chinese representative for the International Federation for Information Processing (IFIP). He serves as an associate editor for IEEE Wireless Communications, IEEE Transactions on Vehicular Technology, and IEEE Access.
  • Supported by:
    the National Key R&D Program of China(2024YFE0200504);NSFC key international joint project(62120106007);Interdisciplinary Research Program of HUST(2024JCYJ022)

RichHTML

PDF

Abstract:

Fiber-to-the-Room (FTTR) has emerged as the core architecture for next-generation home and enterprise networks, offering gigabit-level bandwidth and seamless wireless coverage. However, the complex multi-device topology of FTTR networks presents significant challenges in identifying sources of network performance degradation and conducting accurate root cause analysis. Conventional approaches often fail to deliver efficient and precise operational improvements. To address this issue, this paper proposes a Transformer-based multi-task learning model designed for automated root cause analysis in FTTR environments. The model integrates multidimensional time-series data collected from access points (APs), enabling the simultaneous detection of APs experiencing performance degradation and the classification of underlying root causes, such as weak signal coverage, network congestion, and signal interference. To facilitate model training and evaluation, a multi-label dataset is generated using a discrete-event simulation platform implemented in MATLAB. Experimental results demonstrate that the proposed Transformer-based multi-task learning model achieves a root cause classification accuracy of 96.75%, significantly outperforming baseline models including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Random Forest, and eXtreme Gradient Boosting (XGBoost). This approach enables the rapid identification of performance degradation causes in FTTR networks, offering actionable insights for network optimization, reduced operational costs, and enhanced user experience.

Key words: FTTR, root cause analysis, Transformer mechanisms, Wi-Fi, multi-task learning