Towards using Reinforcement Learning for Scaling and Data Replication in Cloud Systems

TL;DR

This paper explores the potential of reinforcement learning to automate data replication and scaling in cloud systems, aiming to reduce manual threshold setting and improve responsiveness.

Contribution

It provides a comprehensive survey of reinforcement learning approaches applied to data replication and scaling in cloud environments.

Findings

RL can automate threshold setting for data replication

RL-based strategies adapt better to workload changes

Survey highlights current RL methods in cloud scaling

Abstract

Given its intuitive nature, many Cloud providers opt for threshold-based data replication to enable automatic resource scaling. However, setting thresholds effectively needs human intervention to calibrate thresholds for each metric and requires a deep knowledge of current workload trends, which can be challenging to achieve. Reinforcement learning is used in many areas related to the Cloud Computing, and it is a promising field to get automatic data replication strategies. In this work, we survey data replication strategies and data scaling based on reinforcement learning (RL).