跳到主要导航 跳到搜索 跳到主要内容

MD-AirComp+: Adaptive Quantization for Blind Massive Digital Over-the-Air Computation

  • Li Qiao
  • , Yueqing Wang
  • , Hanjun Jiang
  • , Xinhua Liu
  • , Yixuan Xing
  • , Yongpeng Wu
  • , Zhen Gao*
  • *此作品的通讯作者
  • The University of Hong Kong
  • Beijing Institute of Technology
  • State Key Laboratory of Environment Characteristics and Effects for Near-space
  • Shanghai Jiao Tong University
  • Beijing Institute of Technology (Zhuhai)
  • CEMEE State Key Laboratory
  • MIIT Key Laboratory of Complex-Field Intelligent Sensing

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

Unsourced massive access is naturally suited for over-the-air computation (AirComp), since the receiver only needs to recover the aggregated computation result rather than each individual signal. Existing massive digital AirComp (MD-AirComp) schemes have shown promising performance in federated edge learning and are compatible with current digital wireless networks. Nevertheless, these schemes depend on channel pre-equalization, which may amplify computation errors in the presence of channel estimation inaccuracies, thereby limiting its practical use. In this paper, we propose a blind MD-AirComp+ scheme, which takes advantage of the channel hardening effect in massive multiple-input multiple-output systems. We provide an upper bound on the computation mean square error, analyze the tradeoff between computation accuracy and communication overhead, and determine the optimal quantization level. Additionally, we introduce a deep unfolding algorithm to reduce the computational complexity of solving the underdetermined detection problem formulated as a least absolute shrinkage and selection operator optimization problem. Simulation results confirm the effectiveness of the proposed MD-AirComp+ framework, the optimal quantization selection strategy, and the low-complexity detection algorithm.

源语言英语
页(从-至)1917-1928
页数12
期刊Chinese Journal of Electronics
卷35
期5
DOI
出版状态已出版 - 1 9月 2026

学术指纹

探究 'MD-AirComp+: Adaptive Quantization for Blind Massive Digital Over-the-Air Computation' 的科研主题。它们共同构成独一无二的学术指纹。

引用此