天地一体化信息网络 ›› 2021, Vol. 2 ›› Issue (4): 60-65.doi: 10.11959/j.issn.2096-8930.2021044

所属专题: 专题:面向6G的天地一体化信息网络

• 专题:面向6G的天地一体化信息网络 • 上一篇    下一篇

基于条件神经过程的星上多用户检测算法

刘轶伦1, 金亮2, 李佳立2, 朱立东1   

  1. 1 电子科技大学通信抗干扰技术国家级重点实验室,四川 成都 611731
    2 航天恒星科技有限公司,北京 100095
  • 修回日期:2021-11-05 出版日期:2021-12-20 发布日期:2021-12-01
  • 作者简介:刘轶伦(1996-),男,电子科技大学博士生,主要研究方向为卫星通信传输与组网
    金亮(1986-),男,航天恒星科技有限公司高级工程师,主要从事高低轨卫星通信地面系统研究工作
    李佳立(1988-),男,航天恒星科技有限公司中级工程师,主要研究方向为卫星通信系统网络设计
    朱立东(1968-),男,博士,电子科技大学教授,博士生导师,主要研究方向为卫星通信传输与组网、天地一体化信息网络
  • 基金资助:
    国家重点研发计划项目(2019YFB1803102);国家自然科学基金面上项目(61871422)

On-board Multi-User Detection Algorithm Based on Conditional Neural Process

Yilun LIU1, Liang JIN2, Jiali LI2, Lidong ZHU1   

  1. 1 National Key Laboratory of Science and Technology of Communications, University of Electronic Science and Technology of China, Chengdu 611731, China
    2 Space Star Technology Co., Ltd., Beijing 100095, China
  • Revised:2021-11-05 Online:2021-12-20 Published:2021-12-01
  • Supported by:
    National Key R&D Program of China(2019YFB1803102);National Natural Science Foundation of China(61871422)

摘要:

全球全天候无缝覆盖的特性使得卫星通信成为6G潜在的重要组成部分,而实现卫星智能化的一个重要前提是卫星具有星上处理能力。多用户检测是无线通信中抑制多址干扰的经典方法,如最小均方误差、高斯过程回归等算法,由于检测过程中需要求逆矩阵,算法复杂度通常为立方级,难以直接应用到处理能力受限的卫星平台。条件神经过程结合神经网络低复杂度和高斯过程小样本的特性,利用神经网络将高斯过程参数化,避免求逆矩阵,从而降低计算复杂度。研究条件神经过程在多用户检测中的应用,仿真结果表明,在降低复杂度的同时,条件神经过程还极大地提升了多用户检测的误码率性能。

关键词: 卫星通信, 多用户检测, 高斯过程, 条件神经过程, 低复杂度

Abstract:

With the characteristics of all-terrain, all-weather and seamless coverage, satellite communications have become a potentially important part of 6G.An important prerequisite for achieving satellite intelligence is that the satellite have on-board processing capabilities.Multi-user detection (MUD) is a classic method of suppressing multiple access interference (MAI) in wireless communication, such as MMSE, Gaussian processregression (GPR) and other algorithms.Due to the inverse matrix required in the detection process, the algorithm complexity is usually cubic, and it is diff cult to directly apply to satellite platforms because of its limited processing capabilities.The conditional neural process combined the characteristics of the low complexity of the neural network and the data-eff cient of the Gaussian process.The neural network was used to parameterized the Gaussian process to avoided the inversion of the matrix, thereby reduced the computational complexity.The application of conditional neural process in MUD was studied.The simulation results showed that, while reduced complexity, conditional neural process also greatly improved the performance of bit error rate (BER).

Key words: satellite communication, multi-user detection, Gaussian process, conditional neural process, low complexity

中图分类号: 

No Suggested Reading articles found!