Bridging the High-Frequency Data Gap: A Millisecond-Resolution Network Dataset for Advancing Time Series Foundation Models

TL;DR

This paper introduces a high-resolution millisecond-scale dataset from 5G wireless networks to improve time series foundation models, highlighting the need for high-frequency data in model pre-training and evaluation.

Contribution

The paper presents a novel millisecond-resolution dataset from wireless networks and benchmarks models, revealing current models' limitations on high-frequency data.

Findings

Most TSFMs perform poorly on high-frequency data in zero-shot and fine-tuned settings.

The dataset expands the scope of TSFMs to include wireless network data.

Benchmark results highlight the need for models to incorporate high-frequency data during training.

Abstract

Time series foundation models (TSFMs) require diverse, real-world datasets to adapt across varying domains and temporal frequencies. However, current large-scale datasets predominantly focus on low-frequency time series with sampling intervals, i.e., time resolution, in the range of seconds to years, hindering their ability to capture the nuances of high-frequency time series data. To address this limitation, we introduce a novel dataset that captures millisecond-resolution wireless and traffic conditions from an operational 5G wireless deployment, expanding the scope of TSFMs to incorporate high-frequency data for pre-training. Further, the dataset introduces a new domain, wireless networks, thus complementing existing more general domains like energy and finance. The dataset also provides use cases for short-term forecasting, with prediction horizons spanning from 1 millisecond (1 step) to 96 milliseconds (96 steps). By benchmarking traditional machine learning models and TSFMs on predictive tasks using this dataset, we demonstrate that most TSFM model configurations perform poorly on this new data distribution in both zero-shot and fine-tuned settings. Our work underscores the importance of incorporating high-frequency datasets during pre-training and forecasting to enhance architectures, fine-tuning strategies, generalization, and robustness of TSFMs in real-world applications.