EUVIMEDEUVIMED entdecken
Crossref

Achieving Spectral-Efficient URLLC in Air–Ground Cell-Free Massive MIMO Systems

Donggen Li, Xinxin Ma, Ruichen Zhang, Jingfu Li, Chong Huang, Weiheng Jiang, Wenjiang Feng

IEEE Transactions on Cognitive Communications and Networking · 2026 · 12 · 12847-12861

DOI: 10.1109/tccn.2026.3744147 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2026. Verfasst von Donggen Li und 6 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: China Scholarship Council, National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid development of the low-altitude economy (LAE) promotes urban low-altitude logistics (UAL) networks, where uncrewed aerial vehicles (UAVs) support delay-sensitive services such as urban delivery and infrastructure inspection. To ensure reliable and timely operation in such networks, ultra-reliable low-latency communication (URLLC) is required. However, the stringent latency and reliability requirements of URLLC introduce additional transmission and control overhead, which may limit the spectral efficiency (SE) of UAV communication systems. This paper investigates SE maximization in a UAV-based cell-free massive multiple-input multiple-output (mMIMO) system under URLLC constraints. To address the coupled effects of high user mobility, channel aging, and constrained communication resources, we develop a two-stage learning-based optimization framework, referred to as a long short-term memory (LSTM)–transformer self-supervised liquid neural network (LT-SSLNN). In the first stage, an LSTM–transformer network refines the channel state information (CSI) by exploiting temporal channel features and alleviating the CSI mismatch induced by mobility-related channel aging. In the second stage, the refined CSI serves as the input of a self-supervised liquid neural network (SSLNN), which performs power allocation to maximize SE while satisfying URLLC constraints. Numerical results demonstrate that the proposed LT-SSLNN framework achieves a 24.3% improvement in system SE compared with the baseline.

Förderung

  • China Scholarship Council
  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Li, D., Ma, X., Zhang, R., Li, J., Huang, C., Jiang, W., & Feng, W. (2026). Achieving Spectral-Efficient URLLC in Air–Ground Cell-Free Massive MIMO Systems. IEEE Transactions on Cognitive Communications and Networking, 12, 12847-12861. https://doi.org/10.1109/tccn.2026.3744147

Vancouver

Li D, Ma X, Zhang R, Li J, Huang C, Jiang W, et al. Achieving Spectral-Efficient URLLC in Air–Ground Cell-Free Massive MIMO Systems. IEEE Transactions on Cognitive Communications and Networking. 2026;12:12847-12861. doi:10.1109/tccn.2026.3744147

BibTeX
@article{Li2026,
  author = {Li, Donggen and Ma, Xinxin and Zhang, Ruichen and Li, Jingfu and Huang, Chong and Jiang, Weiheng and Feng, Wenjiang},
  title = {Achieving Spectral-Efficient URLLC in Air–Ground Cell-Free Massive MIMO Systems},
  journal = {IEEE Transactions on Cognitive Communications and Networking},
  year = {2026},
  volume = {12},
  pages = {12847--12861},
  doi = {10.1109/tccn.2026.3744147}
}
Kostenlos starten →