HyperPath-SVM: A novel adaptive support vector machine with temporal graph kernels for network path selection
Abstract
Modern network infrastructure faces unprecedented challenges in intelligent path selection due to exponential traffic growth and dynamic conditions. Current approaches suffer from either inflexibility (traditional protocols) or computational overheads (neural networks). This study presents HyperPath-SVM, a novel enhanced Support Vector Machine framework that addresses these limitations through three key innovations: Dynamic Discriminative Weight Evolution (DDWE), which enables continuous weight adaptation through closed-form mathematical updates; Temporal Graph Convolution Kernel (TGCK), which incorporates network topology dynamics into kernel computations; and quantum-inspired optimisation, which is implemented on classical hardware using principles from quantum annealing for faster convergence. Our evaluation of 127 million routing decisions collected over 8 months from real network datasets demonstrates exceptional performance: 96.5% path selection accuracy, 1.8ms inference time, and 98MB memory footprint. The framework maintains 94% accuracy during single-link and cascading network failures while providing complete interpretability for operational deployment. Production simulations indicate 31% latency reduction and 28% throughput improvement over the traditional protocols. This work establishes enhanced SVMs as superior alternatives to neural networks for real-time network intelligence, combining computational efficiency with adaptive learning capabilities.