The invention provides an SDN (Software Defined Network) traffic prediction model DI-GCN (Deep Informational-GCN) based on a graph neural network, and the method comprises the steps: firstly, fusing a graph convolution unit and a gating convolution unit, thereby effectively capturing the space-time correlation of an SDN network; secondly, a mutual information relation matrix is defined and constructed, and relation weight representation of the flow data is obtained, so that spatial structure feature information with more details is obtained; according to the method, a real data set # imgabs0 # is selected for 15 min, 30 min and 45 min prediction comparison, and experimental results show that the DI-GCN model not only ensures the capability of representing actual data, but also reduces prediction errors and obtains a better prediction effect.
本发明提出了一种基于图神经网络的SDN流量预测模型DI‑GCN(Deep Information‑GCN),首先将图卷积与门控卷积单元相融合,从而有效捕捉SDN网络的时空相关性;其次定义并构建互信息关系矩阵,获取流量数据的关系权重表示,从而得到更多细节的空间结构特征信息。本发明选择真实数据集#imgabs0#进行了15min、30min和45min的预测对比,实验结果表明,DI‑GCN模型不仅保证了表示实际数据的能力,而且缩小了预测误差以及取得了更好的预测效果。
SDN traffic prediction method based on graph neural network
一种基于图神经网络的SDN流量预测方法
2024-05-03
Patent
Electronic Resource
Chinese
IPC: | H04L TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION , Übertragung digitaler Information, z.B. Telegrafieverkehr / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Traffic flow prediction method based on graph neural network
European Patent Office | 2024
|Traffic Prediction Using Graph Neural Network
IEEE | 2023
|Traffic jam prediction method based on graph neural network
European Patent Office | 2024
|Airport traffic flow prediction method based on graph neural network
European Patent Office | 2023
|