AI-Enabled Disaster Recovery for Cloud Infrastructure: Proactive Failure Detection and Recovery Strategies
- Version
- Download 21
- File Size 453.62 KB
- Download
AI-Enabled Disaster Recovery for Cloud Infrastructure: Proactive Failure Detection and Recovery Strategies
Naga Surya Teja Thallam
thallamteja21@gmail.com
Abstract
Cloud computing is becoming the back bone of modern digital infrastructures, in which case it is more important that the cloud services are resilient and available. In cloud environments, such as hardware fault, cyber attack or natural disaster, failures albeit rare do occur. Conventional disaster recovery (DR) solutions are based on reactive and such remedies increase downtime and cost inefficiency. In this paper, we present an innovative AI enabled disaster recovery framework that combines proactive failure detection and auto recovery strategies to improve the resilience of cloud infrastructure. We use machine learning (ML) and deep learning (DL) to create predictive models capable of determining if there is likely to be a failure or not before it happens. Anomaly detection, predictive analytics and self healing mechanism are utilized in the proposed system so as to minimize the downtime and resource usage in case of disaster situations. And we introduce some mathematical reliability model that we use to quantify the effectiveness of AI driven recovery strategies. Performance evaluations show that AI based approaches are much more superior than traditional DR techniques in response time, accuracy of failure prediction and its recovery efficiency. AI based DR can revolutionize cloud resilience by making it autonomous, efficient and reliable as evidenced by the aforementioned findings.
Keywords
Cloud Infrastructure, Disaster Recovery, Artificial Intelligence, Proactive Failure Detection, Machine Learning, Predictive Analytics, Self-Healing Systems, Anomaly Detection, Resilience, High Availability