Online Ensemble Transformer for Accurate Cloud Workload Forecasting in Predictive Auto-Scaling

TL;DR

This paper introduces E3Former, an online ensemble transformer model that significantly improves workload forecasting accuracy for cloud auto-scaling, enabling efficient resource management with minimal computational overhead.

Contribution

The paper presents a novel online ensemble transformer model that enhances workload forecasting accuracy and robustness in cloud auto-scaling, with real-world deployment demonstrating substantial resource savings.

Findings

Reduces forecast error by an average of 10% in online tasks.

Deployed in ByteDance's IHPA platform supporting over 600,000 CPU cores.

Achieves over 40% resource utilization reduction while maintaining service quality.

Abstract

In the swiftly evolving domain of cloud computing, the advent of serverless systems underscores the crucial need for predictive auto-scaling systems. This necessity arises to ensure optimal resource allocation and maintain operational efficiency in inherently volatile environments. At the core of a predictive auto-scaling system is the workload forecasting model. Existing forecasting models struggle to quickly adapt to the dynamics in online workload streams and have difficulty capturing the complex periodicity brought by fine-grained, high-frequency forecasting tasks. Addressing this, we propose a novel online ensemble model, E3Former, for online workload forecasting in large-scale predictive auto-scaling. Our model synergizes the predictive capabilities of multiple subnetworks to surmount the limitations of single-model approaches, thus ensuring superior accuracy and robustness. Remarkably, it accomplishes this with a minimal increase in computational overhead, adhering to the lean operational ethos of serverless systems. Through extensive experimentation on real-world workload datasets, we establish the efficacy of our ensemble model. In online forecasting tasks, the proposed method reduces forecast error by an average of 10%, and its effectiveness is further demonstrated through a predictive auto-scaling test in the real-life online system. Currently, our method has been deployed within ByteDance's Intelligent Horizontal Pod Auto-scaling (IHPA) platform, which supports the stable operation of over 30 applications, such as Douyin E-Comerce, TouTiao, and Volcano Engine. The predictive auto-scaling capacity reaching over 600,000 CPU cores. On the basis of essentially ensuring service quality, the predictive auto-scaling system can reduce resource utilization by over 40%.