面向混合毫米波大规模MIMO的预算感知联邦双边信道估计
Budget-Aware Federated Dual-Side Channel Estimation for Hybrid mmWave Massive MIMO
浏览论文内容
中文总结 AI 辅助
针对混合毫米波大规模MIMO的通信受限联邦双边CSI估计，提出BARRNet，其在5dB SNR下可降低28.9%的累积通信量，实现更优的NMSE-通信权衡。
中文摘要 AI 辅助
本研究针对混合毫米波（mmWave）大规模多输入多输出（MIMO）系统中通信受限的联邦双边信道状态信息（CSI）估计问题展开研究。由于混合波束成形会产生压缩且含噪的观测结果，同时联邦学习（FL）中重复的模型交换使得通信效率高度依赖估计器规模，因此准确恢复CSI颇具挑战性。我们未开发新的联邦优化算法，而是聚焦于标准联邦平均（FedAvg）框架下的估计器设计，研究如何在重复模型交换场景下有效利用有限的参数预算。基于该视角，我们提出了预算感知重校准细化网络（BARRNet），其将紧凑的残差骨干网络与轻量的通道级重校准模块相结合，用于双边CSI细化。仿真结果表明，BARRNet相比仅含骨干网络的对照组及更重的卷积神经网络（CNN）基线，能实现更优的归一化均方误差（NMSE）-通信权衡。在5dB信噪比（SNR）下，针对-13dB的下行链路（DL）NMSE目标，与架构匹配的仅骨干网络对照组相比，BARRNet所需的累积通信量降低了28.9%。这些结果表明，通信高效的联邦CSI估计不仅取决于模型紧凑性，还取决于重复模型交换场景下有限模型容量的利用方式。
英文摘要
This work studies communication-constrained federated dual-side channel state information (CSI) estimation in hybrid millimeter-wave (mmWave) massive multiple input multiple output (MIMO) systems. Accurate CSI recovery is challenging because hybrid beamforming yields compressed and noisy observations, while repeated model exchange in federated learning (FL) makes communication efficiency strongly dependent on estimator size. Rather than developing a new federated optimization algorithm, we focus on estimator design under standard federated averaging (FedAvg) and study how to use a limited parameter budget effectively under repeated model exchange. Based on this perspective, we propose a budget-aware recalibrated refinement network (BARRNet), which combines a compact residual backbone with lightweight channel-wise recalibration for dual-side CSI refinement. Simulation results show that BARRNet achieves a better normalized mean squared error (NMSE)--communication tradeoff than the backbone-only control and heavier convolutional neural network (CNN) baselines. At 5 dB SNR, for the -13 dB DL NMSE target, it reduces the cumulative communication required by 28.9\% relative to the architecture-matched backbone-only control. These results indicate that communication-efficient federated CSI estimation depends not only on model compactness, but also on how limited model capacity is used under repeated model exchange.
