A Deep Recurrent-Reinforcement Learning Method for Intelligent AutoScaling of Serverless Functions

TL;DR

This paper proposes a deep recurrent reinforcement learning approach for autoscaling serverless functions, demonstrating improved performance over traditional threshold-based methods in dynamic cloud environments.

Contribution

It introduces a LSTM-enhanced PPO algorithm for function autoscaling, addressing partial observability and outperforming existing threshold-based autoscaling strategies.

Findings

Recurrent RL agents effectively model environment dynamics.

LSTM-based autoscaling improves throughput by 18%.

It increases function execution by 13% and scales 8.4% more instances.

Abstract

FaaS introduces a lightweight, function-based cloud execution model that finds its relevance in a range of applications like IoT-edge data processing and anomaly detection. While cloud service providers offer a near-infinite function elasticity, these applications often experience fluctuating workloads and stricter performance constraints. A typical CSP strategy is to empirically determine and adjust desired function instances or resources, known as autoscaling, based on monitoring-based thresholds such as CPU or memory, to cope with demand and performance. However, threshold configuration either requires expert knowledge, historical data or a complete view of the environment, making autoscaling a performance bottleneck that lacks an adaptable solution. RL algorithms are proven to be beneficial in analysing complex cloud environments and result in an adaptable policy that maximizes the expected objectives. Most realistic cloud environments usually involve operational interference and have limited visibility, making them partially observable. A general solution to tackle observability in highly dynamic settings is to integrate Recurrent units with model-free RL algorithms and model a decision process as a POMDP. Therefore, in this paper, we investigate model-free Recurrent RL agents for function autoscaling and compare them against the model-free PPO algorithm. We explore the integration of a LSTM network with the state-of-the-art PPO algorithm to find that under our experimental and evaluation settings, recurrent policies were able to capture the environment parameters and show promising results for function autoscaling. We further compare a PPO-based autoscaling agent with commercially used threshold-based function autoscaling and posit that a LSTM-based autoscaling agent is able to improve throughput by 18%, function execution by 13% and account for 8.4% more function instances.