发表机构
Beijing Institute of Technology; BIT (Zhuhai); Tsinghua University; Guilin University of Electronic Technology; Yangtze Delta Region Academy, BIT (Jiaxing); Advanced Research Institute of Multidisciplinary Sciences, BIT（北京理工大学; 北京理工大学（珠海）; 清华大学; 桂林电子科技大学; 北京理工大学（嘉兴）长三角研究院; 北京理工大学前沿交叉科学研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出基于Conformer的Tri-PNet，联合设计电磁、模拟和数字预编码，提升多用户MIMO-OFDM频谱效率，性能优于传统方案且对CSI误差鲁棒。
AI 中文摘要
电磁（EM）可重构天线为每个阵元提供多个候选辐射方向图，从而引入额外的电磁域自由度。将辐射方向图可重构性（实现为电磁域预编码）与传统混合模拟-数字预编码相结合，产生三域混合多输入多输出（MIMO）预编码，可显著提升宽带多用户MIMO正交频分复用（OFDM）系统的频谱效率。然而，电磁、模拟和数字预编码的联合设计仍具挑战性。为解决此挑战，我们提出基于Conformer的三域混合预编码网络（Tri-PNet），Conformer是一种新兴神经架构，结合了卷积神经网络的局部建模优势与Transformer的全局依赖建模能力。此外，研究了两种代表性辐射方向图模式，即非规则模式和第三代合作伙伴计划（3GPP）技术报告（TR）38.901模式。Tri-PNet以无监督方式训练，通过最大化平均总频谱效率来联合学习电磁、模拟和数字预编码。其辐射方向图选择网络（RPSNet）采用Conformer编码器捕获频域局部和全局相关性，而其混合模拟-数字预编码网络（HPNet）结合了交叉注意力与双路径处理，并利用奇异值分解（SVD）和迫零（ZF）先验。两种辐射方向图模式下的仿真结果表明，Tri-PNet优于随机电磁预编码和未采用电磁预编码的传统混合MIMO，接近贪婪电磁预编码搜索方案且在线复杂度显著降低，并对不完美的信道状态信息（CSI）保持鲁棒性。
英文摘要
Electromagnetic (EM)-reconfigurable antennas provide multiple candidate radiation patterns per element, thereby introducing an additional EM-domain degree of freedom. Integrating radiation-pattern reconfigurability, realized as EM-domain precoding, with conventional hybrid analog-digital precoding yields tri-hybrid multiple-input multiple-output (MIMO) precoding, which can substantially improve the spectral efficiency of wideband multi-user MIMO orthogonal frequency-division multiplexing (OFDM) systems. However, the joint design of EM, analog, and digital precoding remains challenging. To address this challenge, we propose a tri-hybrid precoding network (Tri-PNet) based on Conformer, an emerging neural architecture that combines the local modeling strength of convolutional neural networks with the global dependency modeling of Transformers. Furthermore, two representative radiation-pattern modes, i.e., the non-regular mode and the 3rd Generation Partnership Project (3GPP) Technical Report (TR) 38.901 mode, are investigated. Tri-PNet is trained in an unsupervised manner to jointly learn EM, analog, and digital precoding by maximizing the average sum spectral efficiency. Its radiation-pattern selection network (RPSNet) employs a Conformer encoder to capture both local and global frequency-domain correlations, whereas its hybrid analog-digital precoding network (HPNet) combines cross-attention and dual-path processing with singular-value-decomposition (SVD) and zero-forcing (ZF) priors. Simulation results under both radiation-pattern modes demonstrate that Tri-PNet outperforms random EM precoding and conventional hybrid MIMO without EM precoding, approaches the greedy EM precoding search scheme with substantially lower online complexity, and remains robust to imperfect channel state information (CSI).
Comments14 pages, 13 figures, 4 tables
