Optimization of Link Failure Detection Models Integrating Link Importance Assessment and Community Division

Abstract

This study introduces an efficient link failure detection model to enhance network operation and service quality by addressing current methods' limitations like high resource use and narrow monitoring scope. The model integrates a dual-layer structure using link importance assessment and community partition algorithms, complemented by fault identification algorithms based on time series analysis and machine learning, such as autoregressive models and support vector machines. Tested in simulated environments, the model achieves up to 98% accuracy, with fault response times reduced to 20 seconds and recovery times to 40 seconds, showing particular effectiveness in critical and high-bandwidth scenarios.