A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud

TL;DR

This paper introduces a meta reinforcement learning approach with workload prediction and neural processes to improve cloud autoscaling, achieving high accuracy and adaptability in dynamic environments, and is deployed at Alipay.

Contribution

It presents a novel end-to-end meta RL algorithm with workload prediction and neural processes for more accurate and adaptive cloud autoscaling.

Findings

Significant performance improvements over existing algorithms.

Successful deployment at Alipay for real-world cloud autoscaling.

Enhanced adaptability to workload fluctuations.

Abstract

Predictive autoscaling (autoscaling with workload forecasting) is an important mechanism that supports autonomous adjustment of computing resources in accordance with fluctuating workload demands in the Cloud. In recent works, Reinforcement Learning (RL) has been introduced as a promising approach to learn the resource management policies to guide the scaling actions under the dynamic and uncertain cloud environment. However, RL methods face the following challenges in steering predictive autoscaling, such as lack of accuracy in decision-making, inefficient sampling and significant variability in workload patterns that may cause policies to fail at test time. To this end, we propose an end-to-end predictive meta model-based RL algorithm, aiming to optimally allocate resource to maintain a stable CPU utilization level, which incorporates a specially-designed deep periodic workload prediction model as the input and embeds the Neural Process to guide the learning of the optimal scaling actions over numerous application services in the Cloud. Our algorithm not only ensures the predictability and accuracy of the scaling strategy, but also enables the scaling decisions to adapt to the changing workloads with high sample efficiency. Our method has achieved significant performance improvement compared to the existing algorithms and has been deployed online at Alipay, supporting the autoscaling of applications for the world-leading payment platform.