arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.05036cs.NIeess.SP
收藏

基于多智能体强化学习的6 G in-X子网动态资源管理

Multi-agent Reinforcement Learning for Dynamic Resource Management in 6G in-X Subnetworks

Xiao Du, Ting Wang, Qiang Feng, Chenhui Ye, Tao Tao, Yuanming Shi, Mingsong Chen

摘要:

6 G网络实现了子网范围的演进,从而形成“子网的网络”。然而,由于无线子网的动态移动性,子网内和子网间的数据传输不可避免地会相互干扰,这给无线资源管理带来了很大的挑战。此外,大多数现有的方法需要子网络之间的瞬时信道增益,这通常是很难收集。为了解决这些问题,在本文中,我们提出了一种新的有效的智能无线电资源管理方法,使用多智能体深度强化学习(MARL),它只需要接收功率的总和,命名为接收信号强度指标(RSSI),在每个信道上,而不是信道增益。然而,直接从RSSI中分离个体干扰几乎是不可能的事情。为此,我们进一步提出了一种新的MARL架构,命名为GA-Net,它集成了一个硬注意力层来模拟基于RSSI的子网络间关系的重要性分布,并排除不相关的子网络的影响,并采用一个多头注意力层的图注意力网络来精确的功能,并计算它们的权重,将影响个人的吞吐量。实验结果表明,我们提出的框架显着优于传统的方法和基于MARL的方法在各个方面。

英文摘要:

The 6G network enables a subnetwork-wide evolution, resulting in a "network of subnetworks". However, due to the dynamic mobility of wireless subnetworks, the data transmission of intra-subnetwork and inter-subnetwork will inevitably interfere with each other, which poses a great challenge to radio resource management. Moreover, most of the existing approaches require the instantaneous channel gain between subnetworks, which are usually difficult to be collected. To tackle these issues, in this paper we propose a novel effective intelligent radio resource management method using multi-agent deep reinforcement learning (MARL), which only needs the sum of received power, named received signal strength indicator (RSSI), on each channel instead of channel gains. However, to directly separate individual interference from RSSI is an almost impossible thing. To this end, we further propose a novel MARL architecture, named GA-Net, which integrates a hard attention layer to model the importance distribution of inter-subnetwork relationships based on RSSI and exclude the impact of unrelated subnetworks, and employs a graph attention network with a multi-head attention layer to exact the features and calculate their weights that will impact individual throughput. Experimental results prove that our proposed framework significantly outperforms both traditional and MARL-based methods in various aspects.

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。

↑