HTNet: Dynamic WLAN Performance Prediction using Heterogenous Temporal GNN
HTNet: Dynamic WLAN Performance Prediction using Heterogenous Temporal GNN
复制标题
DOI：
10.1109/infocom53939.2023.10229047
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Hongkuan Zhou;R. Kannan;A. Swami;V. Prasanna
中科院分区：
文献类型：
--
作者：
Hongkuan Zhou;R. Kannan;A. Swami;V. Prasanna
预测WLAN部署的吞吐量是一个经典的问题，它是在健壮和高性能WLAN系统的设计中发生的。但是，由于越来越复杂的通信协议以及密度和密度WLAN部署的设备之间的干扰增加，传统方法要么具有实质性的运行时或巨大的预测错误，因此不能在下游任务中应用。最近，图形神经网络已被证明是强大的图形分析模型，并且已广泛应用于各种网络问题，例如链接调度和电源分配。在这项工作中，我们提出了HTNET，这是一种专门的异质时间图神经网络，从动态WLAN部署中提取功能。分析WLAN部署图的唯一图形结构，我们表明HTNET可以在每个快照上实现最大表达能力。基于强大的消息传递方案，与其他基于GNN的方法相比，HTNET需要更少的图层，这些方法需要减少支持数据和运行时。为了评估HTNET的性能，我们准备了六种不同的设置，其中有五千多个密集的动态WLAN部署，这些设置涵盖了广泛的现实情况。 HTNET在所有六个设置上达到了最低的预测误差，比最新方法的平均提高了25.3％。
Predicting the throughput of WLAN deployments is a classic problem that occurs in the design of robust and high performance WLAN systems. However, due to the increasingly complex communication protocols and the increase in interference between devices in denser and denser WLAN deployments, traditional methods either have substantial runtime or enormous prediction error and hence cannot be applied in downstream tasks. Recently, Graph Neural Networks have been proven to be powerful graph analytic models and have been broadly applied to various networking problems such as link scheduling and power allocation. In this work, we propose HTNet, a specialized Heterogeneous Temporal Graph Neural Network that extracts features from dynamic WLAN deployments. Analyzing the unique graph structure of WLAN deployment graphs, we show that HTNet achieves the maximum expressive power on each snapshot. Based on a powerful message passing scheme, HTNet requires fewer number of layers compared with other GNN-based methods which entails less supporting data and runtime. To evaluate the performance of HTNet, we prepare six different setups with more than five thousands dense dynamic WLAN deployments that cover a wide range of real-world scenarios. HTNet achieves the lowest prediction error on all six setups with an average improvement of 25.3% over the state-of-the-art methods.