Time-Series Foundation Models for ISP Traffic Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Fan, Farkiani, Behrooz, Crowley, Patrick
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912910206304256
author Liu, Fan
Farkiani, Behrooz
Crowley, Patrick
author_facet Liu, Fan
Farkiani, Behrooz
Crowley, Patrick
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17529
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Time-Series Foundation Models for ISP Traffic Forecasting
Liu, Fan
Farkiani, Behrooz
Crowley, Patrick
Networking and Internet Architecture
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.
title Time-Series Foundation Models for ISP Traffic Forecasting
topic Networking and Internet Architecture
url https://arxiv.org/abs/2511.17529