Comparative Analysis of Deep Learning Models for Real-World ISP Network Traffic Forecasting

Josef Koumar, Timotej Smoleň, Kamil Jeřábek, Tomáš Čejka
3/20/2025
cs.LGcs.AIcs.NI

No official code found. Best implementation: koumajos/isp-forecasting-benchmark (2 stars, last commit 2025-11-11).

Abstract

Accurate network traffic forecasting is essential for Internet Service Providers (ISP) to optimize resources, enhance user experience, and mitigate anomalies. This study evaluates state-of-the-art deep learning models on CESNET-TimeSeries24, a recently published, comprehensive real-world network traffic dataset from the ISP network CESNET3 spanning multivariate time series over 40 weeks. Our findings highlight the balance between prediction accuracy and computational efficiency across different levels of network granularity. Additionally, this work establishes a reproducible methodology that facilitates direct comparison of existing approaches, explores their strengths and weaknesses, and provides a benchmark for future studies using this dataset.

View on arXivView PDF

Code Implementations(1)

koumajos/isp-forecasting-benchmarkCommunity100%
20Shell, PythonFeb 14, 202511 months ago

Similar Papers

Improving Internet Traffic Matrix Prediction via Time Series Clustering

85% match2025

Deep Learning Network-Temporal Models For Traffic Prediction

85% match2026

How does the Performance of the Data-driven Traffic Flow Forecasting Models deteriorate with Increasing Forecasting Horizon? An Extensive Approach Considering Statistical, Machine Learning and Deep Learning Models

83% match2025

Joint Graph Convolution and Sequential Modeling for Scalable Network Traffic Estimation

82% match2025

Causally-Aware Spatio-Temporal Multi-Graph Convolution Network for Accurate and Reliable Traffic Prediction

82% match1 repo22024

Deep Learning Approaches for Network Traffic Classification in the Internet of Things (IoT): A Survey

82% match2024

Cite this paper

@article{koumar2025comparative,
  title  = {Comparative Analysis of Deep Learning Models for Real-World ISP Network Traffic Forecasting},
  author = {Josef Koumar and Timotej Smoleň and Kamil Jeřábek and Tomáš Čejka},
  year   = {2025},
  eprint = {2503.17410},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.17410v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2503.17410.svg)](https://codeofpaper.com/paper/2503.17410)

Discussion