引用本文: | 薛自杰,卢昱妃,宁芊,黄霖宇,陈炳才.基于时空特征融合的网络流量预测模型[J].哈尔滨工业大学学报,2023,55(5):30.DOI:10.11918/202203059 |
| XUE Zijie,LU Yufei,NING Qian,HUANG Linyu,CHEN Bingcai.Network flow prediction based on spatialtemporal features fusion[J].Journal of Harbin Institute of Technology,2023,55(5):30.DOI:10.11918/202203059 |
|
摘要: |
随着网络规模的日益增大,实时准确的网络流量预测对流量调度、路由设计等工作至关重要。由于网络流量数据的非线性和不确定性,一些传统方法无法取得较好的预测精度。针对网络流量复杂的时空特征,本文提出一种基于时空特征融合的神经网络(ST-Fusion)进行流量预测。该模型采用编码器-解码器结构。首先,编码器具有时间和空间两个并行的特征通道,联合门限循环网络和自注意力机制提取流量的时序特征,采用图卷积神经网络提取流量的空间特征;然后,将编码器提取的时空特征使用双边门限机制进行特征融合;最后,将融合的结果输入到基于门限循环网络的解码器中依次生成预测结果。本文在3个公开的网络流量数据集(GEANT、ABILENE、CERNET)上进行实验,其评价指标选用MAE、RMSE、ACCURACY、VAR。实验结果表明ST-Fusion方法能够取得更好的预测效果。 |
关键词: 网络流量预测 特征融合 双边门限机制 图卷积神经网络 门限循环网络 自注意力机制 |
DOI:10.11918/202203059 |
分类号:TP399 |
文献标识码:A |
基金项目:四川省科技厅重点研发项目(2021YFQ0011);国家自然科学基金(61961040) |
|
Network flow prediction based on spatialtemporal features fusion |
XUE Zijie1,LU Yufei1,NING Qian1,HUANG Linyu1,CHEN Bingcai2
|
(1.College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China; 2.School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, Liaoning, China)
|
Abstract: |
With the increasing scale of network, the accurate and real-time prediction of network flow is essential for traffic scheduling and routing design. However, due to the nonlinearity and uncertainty of network flow data, some traditional methods fail to achieve good prediction accuracy. Considering the complex spatialtemporal features of network flow, a novel network flow prediction method based on spatialtemporal features fusion (ST-Fusion) was proposed, combined with encoderdecoder architecture. First, the encoder was designed with two parallel feature channels: temporal and spatial channels. The temporal features were extracted by integrating gated recurrent unit (GRU) and self-attention mechanism, and the graph convolutional network (GCN) was used to extract the spatial features. Then, the temporal and spatial features extracted by the encoder were fused by using the bilateral gated mechanism. Finally, the fused features were input into the GRU-based decoder to generate prediction results. Experiments were conducted on three public datasets (GEANT, ABILENE, and CERNET) using evaluation metrics including MAE, RMSE, ACCURACY, and VAR. Experimental results showed that the ST-Fusion method achieved better performance in network flow prediction. |
Key words: network flow prediction features fusion bilateral gated mechanism graph convolutional network (GCN) gated recurrent unit (GRU) self-attention mechanism |