Paper Contents
Abstract
Self-healing networks represent a transformative approach to maintaining network reliability and performance amidst faults or attacks, with minimal energy overhead as a critical design goal. This paper explores AI-based anomaly detection techniques that enable real-time identification and correction of network issues, balancing Quality of Service (QoS) and sustainability requirements. By integrating advanced machine learning models, including hybrid deep learning architectures, these networks dynamically adapt to faults while minimizing energy consumption through optimized resource management. The proposed framework ensures network resilience, prolongs device lifetime, and supports eco-friendly network operations with demonstrable improvements in packet delivery and energy efficiency. Experimental evaluations validate the effectiveness of AI-driven self-healing in reducing downtime and maintaining service quality under constrained energy budgets.
Copyright
Copyright © 2025 Dr. Kismat Chhillar. This is an open access article distributed under the Creative Commons Attribution License.
