Automatic Cloud Resource Scaling Algorithm based on Long Short-Term Memory Recurrent Neural Network

TL;DR

This paper introduces a dynamic auto-scaling algorithm for cloud resources using LSTM neural networks to predict demand, improving cost efficiency and SLA compliance over traditional threshold-based methods.

Contribution

It presents a novel LSTM-based prediction approach for cloud auto-scaling, addressing workload variability and outperforming existing algorithms.

Findings

Proposed algorithms outperform existing auto-scaling methods.

LSTM-based predictions improve resource provisioning accuracy.

Cost savings and SLA adherence are enhanced with the new approach.

Abstract

Scalability is an important characteristic of cloud computing. With scalability, cost is minimized by provisioning and releasing resources according to demand. Most of current Infrastructure as a Service (IaaS) providers deliver threshold-based auto-scaling techniques. However, setting up thresholds with right values that minimize cost and achieve Service Level Agreement is not an easy task, especially with variant and sudden workload changes. This paper has proposed dynamic threshold based auto-scaling algorithms that predict required resources using Long Short-Term Memory Recurrent Neural Network and auto-scale virtual resources based on predicted values. The proposed algorithms have been evaluated and compared with some of existing algorithms. Experimental results show that the proposed algorithms outperform other algorithms.