International Journal of Science, Engineering and TechnologyAuthors: Rahul Sharma
Abstract: The integration of Artificial Intelligence (AI) and Machine Learning (ML) into cloud-based Disaster Recovery (DR) represents a paradigm shift from reactive to proactive system resilience. Traditional DR strategies often rely on manual intervention and static backup schedules, which struggle to meet the stringent Recovery Time Objectives (RTO) and Recovery Point Objectives (RPO) required by modern enterprise applications. AI-enhanced disaster recovery leverages predictive analytics to identify potential failures before they occur, automates the complex orchestration of failover processes, and optimizes resource allocation across distributed cloud environments. This review explores the architectural evolution of DR in the cloud, highlighting how intelligent algorithms enhance data integrity, reduce downtime, and enable self-healing infrastructures. By analyzing current methodologies and emerging trends, this article demonstrates that AI not only accelerates the recovery process but also provides a cost-effective, scalable framework for maintaining business continuity in an increasingly volatile digital landscape.
DOI: https://doi.org/10.5281/zenodo.19481954
