面向RIS的几何感知元学习神经网络用于相位和预编码器联合优化
Geometry Aware Meta-Learning Neural Network for Joint Phase and Precoder Optimization in RIS
AI总结:
本文提出一种几何感知元学习神经网络,用于RIS中相位和预编码器的联合优化,实现更快收敛和更高的加权速率。
摘要:
在受可重构智能表面(RIS)辅助的系统中,基站的预编码矩阵和RIS元件的相位偏移的联合优化涉及显著的复杂性。本文提出了一种复值、几何感知的元学习神经网络,旨在最大化多用户多输入单输出系统中的加权速率。通过利用复圆几何进行相位偏移和球面几何进行预编码,优化发生在黎曼流形上,从而实现更快的收敛。我们使用复值神经网络进行相位偏移,并采用受欧拉启发的更新方法用于预编码网络。我们的方法优于现有的基于神经网络的算法,提供了更高的加权速率、更低的能耗和显著更快的收敛速度。具体来说,它比现有方法快近100个周期收敛,加权速率提高了0.7 bps,功率增益提高了1.8 dB。进一步地,它比最先进交替优化算法在加权速率上高出0.86 bps,功率增益提高2.6 dB。
英文摘要:
In reconfigurable intelligent surface (RIS) aided systems, the joint optimization of the precoder matrix at the base station and the phase shifts of the RIS elements involves significant complexity. In this paper, we propose a complex-valued, geometry aware meta-learning neural network that maximizes the weighted sum rate in a multi-user multiple input single output system. By leveraging the complex circle geometry for phase shifts and spherical geometry for the precoder, the optimization occurs on Riemannian manifolds, leading to faster convergence. We use a complex-valued neural network for phase shifts and an Euler inspired update for the precoder network. Our approach outperforms existing neural network-based algorithms, offering higher weighted sum rates, lower power consumption, and significantly faster convergence. Specifically, it converges faster by nearly 100 epochs, with a 0.7 bps improvement in weighted sum rate and a 1.8 dB power gain when compared with existing work. Further it outperforms the state-of-the-art alternating optimization algorithm by 0.86 bps with a 2.6 dB power gain.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。