Joint Graph Convolution and Sequential Modeling for Scalable Network Traffic Estimation

TL;DR

This paper presents a novel spatiotemporal deep learning model combining Graph Convolutional Networks and Gated Recurrent Units to accurately forecast network traffic in complex topologies, validated on real-world data.

Contribution

It introduces an integrated GCN-GRU model that effectively captures spatial and temporal dependencies for scalable network traffic prediction, outperforming existing methods.

Findings

Achieves superior accuracy on the Abilene dataset

Demonstrates robustness and stability in traffic forecasting

Shows the importance of model components through ablation studies

Abstract

This study focuses on the challenge of predicting network traffic within complex topological environments. It introduces a spatiotemporal modeling approach that integrates Graph Convolutional Networks (GCN) with Gated Recurrent Units (GRU). The GCN component captures spatial dependencies among network nodes, while the GRU component models the temporal evolution of traffic data. This combination allows for precise forecasting of future traffic patterns. The effectiveness of the proposed model is validated through comprehensive experiments on the real-world Abilene network traffic dataset. The model is benchmarked against several popular deep learning methods. Furthermore, a set of ablation experiments is conducted to examine the influence of various components on performance, including changes in the number of graph convolution layers, different temporal modeling strategies, and methods for constructing the adjacency matrix. Results indicate that the proposed approach achieves superior performance across multiple metrics, demonstrating robust stability and strong generalization capabilities in complex network traffic forecasting scenarios.