Scholarlink

DL-based CSI feedback has the potential to improve the recovery accuracy and reduce the feedback overhead in massive MIMO-OFDM systems. This chapter first focuses on the eigenvector-based CSI feedback and designs a DL-based lightweight network, referred to as MixerNet, where the joint eigenvector composed of multiple subbands is compressed at the UE and then recovered at the gNB. On the other hand, an adaptive bidirectional long short-term memory network (ABLNet) for CSI feedback is designed to process various input CSI lengths. Then, to realize a more flexible feedback bit number, a feedback bit control unit (FBCU) module is proposed to control the output length of feedback bits. Based on which, a target feedback performance can be adaptively achieved by a designed bit number adjusting (BNA) algorithm.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Intelligent CSI Feedback Technology for FDD Systems

  • 章节

  • 发表日期：

    2025年

查看全文
  • Long Zhao,
  • Hongrui Shen,
  • Kan Zheng

摘要

DL-based CSI feedback has the potential to improve the recovery accuracy and reduce the feedback overhead in massive MIMO-OFDM systems. This chapter first focuses on the eigenvector-based CSI feedback and designs a DL-based lightweight network, referred to as MixerNet, where the joint eigenvector composed of multiple subbands is compressed at the UE and then recovered at the gNB. On the other hand, an adaptive bidirectional long short-term memory network (ABLNet) for CSI feedback is designed to process various input CSI lengths. Then, to realize a more flexible feedback bit number, a feedback bit control unit (FBCU) module is proposed to control the output length of feedback bits. Based on which, a target feedback performance can be adaptively achieved by a designed bit number adjusting (BNA) algorithm.