Fremer: Lightweight and Effective Frequency Transformer for Workload Forecasting in Cloud Services

TL;DR

Fremer is a novel frequency domain Transformer model that significantly improves workload forecasting accuracy and efficiency in cloud services, enabling better auto-scaling and resource management.

Contribution

It introduces Fremer, a lightweight frequency Transformer that outperforms existing models in accuracy and efficiency for cloud workload forecasting, with open-source datasets and real-world validation.

Findings

Fremer achieves 5.5% lower MSE than SOTA models.

Fremer reduces computational costs and parameters.

Auto-scaling with Fremer improves latency by 18.78%.

Abstract

Workload forecasting is pivotal in cloud service applications, such as auto-scaling and scheduling, with profound implications for operational efficiency. Although Transformer-based forecasting models have demonstrated remarkable success in general tasks, their computational efficiency often falls short of the stringent requirements in large-scale cloud environments. Given that most workload series exhibit complicated periodic patterns, addressing these challenges in the frequency domain offers substantial advantages. To this end, we propose Fremer, an efficient and effective deep forecasting model. Fremer fulfills three critical requirements: it demonstrates superior efficiency, outperforming most Transformer-based forecasting models; it achieves exceptional accuracy, surpassing all state-of-the-art (SOTA) models in workload forecasting; and it exhibits robust performance for multi-period series. Furthermore, we collect and open-source four high-quality, open-source workload datasets derived from ByteDance's cloud services, encompassing workload data from thousands of computing instances. Extensive experiments on both our proprietary datasets and public benchmarks demonstrate that Fremer consistently outperforms baseline models, achieving average improvements of 5.5% in MSE, 4.7% in MAE, and 8.6% in SMAPE over SOTA models, while simultaneously reducing parameter scale and computational costs. Additionally, in a proactive auto-scaling test based on Kubernetes, Fremer improves average latency by 18.78% and reduces resource consumption by 2.35%, underscoring its practical efficacy in real-world applications.