Which Deep Learner? A Systematic Evaluation of Advanced Deep Forecasting Models Accuracy and Efficiency for Network Traffic Prediction

TL;DR

This paper systematically evaluates twelve advanced deep learning models, including transformers and traditional approaches, for network traffic prediction, analyzing their accuracy, efficiency, and robustness across diverse datasets and conditions.

Contribution

It provides a comprehensive comparison of various deep forecasting models for network traffic, highlighting effective architectures and deployment strategies.

Findings

Transformer-based models show strong accuracy in complex traffic patterns.

Traditional models remain competitive in resource-constrained environments.

Certain architectures balance accuracy and efficiency effectively.

Abstract

Network traffic prediction is essential for automating modern network management. It is a difficult time series forecasting (TSF) problem that has been addressed by Deep Learning (DL) models due to their ability to capture complex patterns. Advances in forecasting, from sophisticated transformer architectures to simple linear models, have improved performance across diverse prediction tasks. However, given the variability of network traffic across network environments and traffic series timescales, it is essential to identify effective deployment choices and modeling directions for network traffic prediction. This study systematically identify and evaluates twelve advanced TSF models -- including transformer-based and traditional DL approaches, each with unique advantages for network traffic prediction -- against three statistical baselines on four real traffic datasets, across multiple time scales and horizons, assessing performance, robustness to anomalies, data gaps, external factors, data efficiency, and resource efficiency in terms of time, memory, and energy. Results highlight performance regimes, efficiency thresholds, and promising architectures that balance accuracy and efficiency, demonstrating robustness to traffic challenges and suggesting new directions beyond traditional RNNs.