Time-Series Foundation Models for ISP Traffic Forecasting

TL;DR

This paper evaluates IBM's Tiny Time Mixer, a time-series foundation model, for ISP traffic forecasting, demonstrating its accuracy, efficiency, and potential for scalable network management without extensive training.

Contribution

It provides the first systematic assessment of a pretrained TSFM in real-world ISP traffic forecasting, showing competitive accuracy and low latency in zero-shot and few-shot settings.

Findings

TTM achieves RMSE 0.026-0.057 across horizons

Outperforms or matches deep learning baselines like GRU and LSTM

Inference latency under 0.05s per 100 points on CPU

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 $R^2$ 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.