Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domain

TL;DR

This paper introduces large-scale time series datasets from the CloudOps domain to facilitate pre-training and scaling studies, demonstrating significant error reduction with a promising architecture and setting a foundation for future research.

Contribution

It provides the first large-scale CloudOps time series datasets and benchmarks, enabling research into pre-training and scaling of time series models.

Findings

Pre-trained models improve forecasting accuracy.

Scaling both data and models enhances performance.

Achieved 27% error reduction on the largest dataset.

Abstract

Time series has been left behind in the era of pre-training and transfer learning. While research in the fields of natural language processing and computer vision are enjoying progressively larger datasets to train massive models, the most popular time series datasets consist of only tens of thousands of time steps, limiting our ability to study the effectiveness of pre-training and scaling. Recent studies have also cast doubt on the need for expressive models and scale. To alleviate these issues, we introduce three large-scale time series forecasting datasets from the cloud operations (CloudOps) domain, the largest having billions of observations, enabling further study into pre-training and scaling of time series models. We build the empirical groundwork for studying pre-training and scaling of time series models and pave the way for future research by identifying a promising candidate architecture. We show that it is a strong zero-shot baseline and benefits from further scaling, both in model and dataset size. Accompanying these datasets and results is a suite of comprehensive benchmark results comparing classical and deep learning baselines to our pre-trained method - achieving a 27% reduction in error on the largest dataset. Code and datasets can be found https://github.com/SalesforceAIResearch/pretrain-time-series-cloudops.