Enhancing Security and Performance in Live VM Migration: A Machine Learning-Driven Framework With Selective Encryption for Enhanced Security and Performance in Cloud Computing Environments

Abstract

Live virtual machine (LVM) migration is pivotal in cloud computing for its ability to seamlessly transfer virtual machines (VMs) between physical hosts, optimise resource utilisation, and enable uninterrupted service. However, concerns persist regarding safeguarding sensitive data during migration, particularly in critical sectors like healthcare, banking and military operations. Existing migration methods often compromise between performance and data security, prompting the need for a balanced solution. To address this, we propose a novel framework merging machine learning with selective encryption to fortify the pre-copy live migration process. Our approach intelligently predicts optimal migration times while selectively encrypting sensitive data, ensuring confidentiality and integrity without compromising performance. Rigorous experiments demonstrate its effectiveness, showcasing an average 51.82% reduction in downtime and an average 72.73% decrease in total migration time across diverse workloads. This integration of selective encryption not only bolsters security but also optimises migration metrics, presenting a robust solution for uninterrupted service delivery in critical cloud computing domains.