arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.05652eess.SP
收藏

基于图神经网络的毫米波无蜂窝大规模MIMO下行用户分配的分布式组合优化

Distributed Combinatorial Optimization of Downlink User Assignment in mmWave Cell-free Massive MIMO Using Graph Neural Networks

Bile Peng, Bihan Guo, Karl-Ludwig Besser, Luca Kunz, Ramprasad Raghunath, Anke Schmeink, Eduard A Jorswieck, Giuseppe Caire, H. Vincent Poor

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文针对毫米波无蜂窝大规模MIMO中的接入点-用户分配组合优化问题，提出一种基于定制图神经网络的无监督学习方法，通过层次置换等变架构和增广拉格朗日训练，在总速率上优于GSD算法并接近理论上界。

摘要：

毫米波（mmWave）无蜂窝大规模MIMO（CF mMIMO）是未来无线通信中一种有前景的解决方案。然而，由于毫米波信道具有挑战性的特性，其优化并非易事。我们表明，由于毫米波信道的高路径损耗、放大器的有限输出功率以及大量接入点（AP）天线条件下用户之间几乎正交的信道，毫米波CF mMIMO优化在很大程度上是一个接入点与用户之间的分配问题。该分配问题的组合特性、对可扩展性的要求以及CF mMIMO的分布式实现方式使这一问题变得困难。在本文中，我们提出了一种基于无监督机器学习（ML）的解决方案。具体而言，我们引入了一种针对可扩展性和分布式实现而定制的图神经网络（GNN）。此外，该定制GNN架构具有层次置换等变性（HPE），即如果接入点或某个接入点下的用户被置换，输出分配会自动以相同方式置换。为解决该组合问题，我们将其松弛为连续问题，并引入一个受信息熵启发的惩罚项。随后，利用增广拉格朗日方法（ALM）构建训练目标。测试结果表明，所实现的总速率优于广义串行独裁（GSD）算法，并且在小网络场景中非常接近上界，而在大网络场景中上界无法获得。

英文摘要：

Millimeter wave (mmWave) cell-free massive MIMO (CF mMIMO) is a promising solution for future wireless communications. However, its optimization is non-trivial due to the challenging channel characteristics. We show that mmWave CF mMIMO optimization is largely an assignment problem between access points (APs) and users due to the high path loss of mmWave channels, the limited output power of the amplifier, and the almost orthogonal channels between users given a large number of AP antennas. The combinatorial nature of the assignment problem, the requirement for scalability, and the distributed implementation of CF mMIMO make this problem difficult. In this work, we propose an unsupervised machine learning (ML) enabled solution. In particular, a graph neural network (GNN) customized for scalability and distributed implementation is introduced. Moreover, the customized GNN architecture is hierarchically permutation-equivariant (HPE), i.e., if the APs or users of an AP are permuted, the output assignment is automatically permuted in the same way. To address the combinatorial problem, we relax it to a continuous problem, and introduce an information entropy-inspired penalty term. The training objective is then formulated using the augmented Lagrangian method (ALM). The test results show that the realized sum-rate outperforms that of the generalized serial dictatorship (GSD) algorithm and is very close to the upper bound in a small network scenario, while the upper bound is impossible to obtain in a large network scenario.

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。

↑