arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.04591cs.ITcs.LGeess.SPmath.IT
收藏

迈向节能大规模 MIMO:用于缓解非线性 PA 失真的图神经网络预编码

Toward Energy-Efficient Massive MIMO: Graph Neural Network Precoding for Mitigating Non-Linear PA Distortion

KU Leuven(鲁汶大学)

Thomas Feys, Liesbet Van der Perre, François Rottenberg

AI总结:

提出一种 GNN 预编码器,在高阶非线性 PA 模型下最大化大规模 MIMO 和速率,通过将失真导向非用户方向显著提升速率、降低功耗与复杂度。

摘要:

大规模 MIMO 系统通常在假设线性功率放大器(PA)的情况下设计。然而,PA 在接近饱和时能效最高,而此时会产生非线性失真。对于传统预编码器,这种失真可能在用户位置相干叠加,从而限制性能。我们提出一种图神经网络(GNN),利用高阶多项式 PA 模型学习信道矩阵与预编码矩阵之间的映射,使受非线性失真影响的和速率最大化。在失真受限区域,这种基于 GNN 的预编码器优于迫零(ZF)、ZF 加数字预失真(DPD)以及现有最先进的失真感知波束赋形(DAB)预编码器。在 -3 dB 输入回退条件下,所提预编码器与 ZF 相比,在两个和四个用户场景下分别使和速率提升 8.60 和 8.84 比特/信道使用。辐射方向图表明,这些增益是通过将非线性失真发射到非用户方向实现的。在四用户场景中,对于固定和速率,GNN 预编码器的总消耗功率(PA 与处理)分别比 ZF 和 ZF 加 DPD 低 3.24 倍和 1.44 倍。复杂度分析表明,与 DAB 预编码相比,其复杂度降低了六个数量级。这为让 PA 在更接近饱和的状态下工作开辟了前景,可大幅提高其能效。

英文摘要:

Massive MIMO systems are typically designed assuming linear power amplifiers (PAs). However, PAs are most energy efficient close to saturation, where non-linear distortion arises. For conventional precoders, this distortion can coherently combine at user locations, limiting performance. We propose a graph neural network (GNN) to learn a mapping between channel and precoding matrices, which maximizes the sum rate affected by non-linear distortion, using a high-order polynomial PA model. In the distortion-limited regime, this GNN-based precoder outperforms zero forcing (ZF), ZF plus digital pre-distortion (DPD) and the distortion-aware beamforming (DAB) precoder from the state-of-the-art. At an input back-off of -3 dB the proposed precoder compared to ZF increases the sum rate by 8.60 and 8.84 bits/channel use for two and four users respectively. Radiation patterns show that these gains are achieved by transmitting the non-linear distortion in non-user directions. In the four user-case, for a fixed sum rate, the total consumed power (PA and processing) of the GNN precoder is 3.24 and 1.44 times lower compared to ZF and ZF plus DPD respectively. A complexity analysis shows six orders of magnitude reduction compared to DAB precoding. This opens perspectives to operate PAs closer to saturation, which drastically increases their energy efficiency.

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。

↑