arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.09797cs.NIcs.LG
收藏

M3Net: 一种基于图神经网络的多指标专家混合网络数字孪生

M3Net: A Multi-Metric Mixture of Experts Network Digital Twin with Graph Neural Networks

Carnegie Mellon University(卡内基梅隆大学)

Blessed Guda, Carlee Joe-Wong

AI总结:

M3Net通过图神经网络实现多指标专家混合网络,提升网络性能预测的准确性和可扩展性。

摘要:

5G/6G网络技术的兴起有望实现自动驾驶和虚拟现实等应用,导致连接设备数量大幅增加,从而复杂化网络管理。更糟糕的是,这些应用对延迟、可靠性等指标有严格但异质的性能要求。因此,许多近期工作都集中在开发预测网络性能的能力上。然而,传统的网络建模方法,如离散事件模拟器和仿真,往往难以在准确性和可扩展性之间取得平衡。通过机器学习增强的网络数字孪生(NDT)通过创建物理网络的虚拟副本,实现了实时模拟和分析。然而,最先进的模型仍无法实现完整的NDT,因为它们通常只关注单一性能指标或模拟网络数据。我们引入了M3Net,一种多指标专家混合(MoE)NDT,利用图神经网络架构,从扩展的网络状态数据集中估计多种性能指标,以适应多种场景。我们证明,M3Net通过将MAPE(平均绝对百分比误差)从20.06%降低到17.39%,显著提高了流延迟预测的准确性,同时在抖动和丢包方面分别达到了66.47%和78.7%的准确率。

英文摘要:

The rise of 5G/6G network technologies promises to enable applications like autonomous vehicles and virtual reality, resulting in a significant increase in connected devices and necessarily complicating network management. Even worse, these applications often have strict, yet heterogeneous, performance requirements across metrics like latency and reliability. Much recent work has thus focused on developing the ability to predict network performance. However, traditional methods for network modeling, like discrete event simulators and emulation, often fail to balance accuracy and scalability. Network Digital Twins (NDTs), augmented by machine learning, present a viable solution by creating virtual replicas of physical networks for real- time simulation and analysis. State-of-the-art models, however, fall short of full-fledged NDTs, as they often focus only on a single performance metric or simulated network data. We introduce M3Net, a Multi-Metric Mixture-of-experts (MoE) NDT that uses a graph neural network architecture to estimate multiple performance metrics from an expanded set of network state data in a range of scenarios. We show that M3Net significantly enhances the accuracy of flow delay predictions by reducing the MAPE (Mean Absolute Percentage Error) from 20.06% to 17.39%, while also achieving 66.47% and 78.7% accuracy on jitter and packets dropped for each flow

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。

↑