Towards Designing an Energy Aware Data Replication Strategy for Cloud Systems Using Reinforcement Learning

TL;DR

This paper proposes a reinforcement learning-based data replication strategy for cloud systems that dynamically adapts to workload changes, aiming to optimize quality of service, profit, and environmental impact.

Contribution

It introduces a novel reinforcement learning approach for data replication that automatically learns system behavior and adapts without manual threshold tuning.

Findings

Demonstrates improved QoS through adaptive replication

Balances profit and environmental impact effectively

Provides a detailed RL model for cloud data management

Abstract

The rapid growth of global data volumes has created a demand for scalable distributed systems that can maintain a high quality of service. Data replication is a widely used technique that provides fault tolerance, improved performance and higher availability. Traditional implementations often rely on threshold-based activation mechanisms, which can vary depending on workload changes and system architecture. System administrators typically bear the responsibility of adjusting these thresholds. To address this challenge, reinforcement learning can be used to dynamically adapt to workload changes and different architectures. In this paper, we propose a novel data replication strategy for cloud systems that employs reinforcement learning to automatically learn system characteristics and adapt to workload changes. The strategy's aim is to provide satisfactory Quality of Service while optimizing a trade-off between provider profit and environmental impact. We present the architecture behind our solution and describe the reinforcement learning model by defining the states, actions and rewards.