Comparative Analysis of Deep Learning Models for Real-World ISP Network Traffic Forecasting
This work provides a benchmark for ISP network traffic forecasting, but it is incremental as it focuses on comparing existing methods on a new dataset.
This study tackled the problem of network traffic forecasting for ISPs by evaluating deep learning models on the CESNET-TimeSeries24 dataset, finding a balance between prediction accuracy and computational efficiency across different network granularities.
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.