English

Time-Series Foundation Models for ISP Traffic Forecasting

Networking and Internet Architecture 2026-02-18 v2

Abstract

Accurate network-traffic forecasting enables proactive capacity planning and anomaly detection in Internet Service Provider (ISP) networks. Recent advances in time-series foundation models (TSFMs) have demonstrated strong zero-shot and few-shot generalization across diverse domains, yet their effectiveness for computer networking remains unexplored. This paper presents a systematic evaluation of a TSFM, IBM's Tiny Time Mixer (TTM), on the CESNET-TimeSeries24 dataset, a 40-week real-world ISP telemetry corpus. We assess TTM under zero-shot and few-shot settings across multiple forecasting horizons (hours to days), aggregation hierarchies (institutions, subnets, IPs), and temporal resolutions (10-minute and hourly). Results show that TTM achieves consistent accuracy (RMSE 0.026-0.057) and stable R2R^2 scores across horizons and context lengths, outperforming or matching fully trained deep learning baselines such as GRU and LSTM. Inference latency remains under 0.05s per 100 points on a single MacBook Pro using CPU-only computation, confirming deployability without dedicated GPU or MPS acceleration. These findings highlight the potential of pretrained TSFMs to enable scalable, efficient, and training-free forecasting for modern network monitoring and management systems.

Keywords

Cite

@article{arxiv.2511.17529,
  title  = {Time-Series Foundation Models for ISP Traffic Forecasting},
  author = {Fan Liu and Behrooz Farkiani and Patrick Crowley},
  journal= {arXiv preprint arXiv:2511.17529},
  year   = {2026}
}

Comments

Accepted by the IEEE/IFIP Network Operations and Management Symposium (NOMS) 2026

R2 v1 2026-07-01T07:49:14.807Z