M$^{2}$STL: Multi-Range Multi-Level Spatial-Temporal Learning Model for Network Traffic Prediction

Network traffic prediction is crucial for network management, resource allocation, congestion control, and network anomaly detection. However, existing studies on network traffic prediction often fail to fully utilize the complex spatial-temporal dependencies present in network traffic data. This paper introduces a deep learning-based network traffic prediction model, named Multi-range Multi-level Spatial-Temporal Learning (M$^{2}$STL), specifically designed to learn the complex spatial-temporal characteristics inherent in a dynamic network environment. Within M$^{2}$STL, we devised three Spatial-Temporal Aggregation (STA) modules, each designed to learn from three different ranges of spatial-temporal features: recent, daily, and weekly. In particular, we propose three primary techniques within the STA modules to extract these spatial-temporal features: 1) A Dilated Conv Net based on 1D-dilated convolutions is proposed to learn long correlations in the temporal dimension with a small number of parameters. 2) A Mix-hop GCN Net, based on graph convolutions, is proposed to effectively extract spatial features. 3) Instead of providing the Mix-hop GCN Net with a pre-fixed adjacency matrix, a Graph Learning Net is proposed to learn multiple adjacency matrices, progressing from the shallower level to the deeper level. Extensive experiments have been conducted on two real-world network traffic datasets, Abilene and GÉANT. The results demonstrate that our method outperforms the other seven baselines across different prediction intervals. The Normalized Mean Absolute Error (NMAE) is 28.4% lower than the best baseline algorithm when the prediction interval is 36 on the GÉANT dataset.

I. Introduction

With rapid developments in science and technology, the Internet is affecting all aspects of people's lives, bringing great convenience and joy. However, the rapid increase in user demand and network scale has posed many challenges to the current network infrastructure. As network traffic can reflect the overall health of network operation, it becomes one of the important indicators of a network. If network traffic can be accurately predicted in advance, network operators can allocate resources reasonably [1], [2] and improve network operating efficiency [3], [4]. Moreover, accurate network traffic prediction can also help detect potential network threats and anomalies in time [5], [6], as well as provide detailed guidance for network operation and maintenance [7], [8]. Network traffic prediction can be regarded as a typical spatial-temporal prediction problem, the key to which is to effectively extract the complex temporal and spatial features in the network traffic data.