A Hybrid Quantum-Inspired Multi-Objective Optimization with Machine Learning (HQI-ML) Framework for Intelligent Network Routing

Abstract

The current communication networks are challenged by problems like congestion, packet loss, and routing inefficiency due to changing network traffic patterns. The existing routing techniques are mainly concentrated on single-objective optimization, which is not effective in handling network complexities. Therefore, to overcome the drawbacks of existing routing techniques, this study introduces a novel Hybrid Quantum-Inspired Multi-Objective Optimization with Machine Learning (HQI-ML) model for efficient routing in communication networks. The suggested model is based on the integration of machine learning techniques for network congestion prediction and quantum-inspired optimization for efficient routing decisions based on various parameters like network delay, bandwidth, packet delivery ratio, and energy consumption. The suggested model is capable of dynamically adapting to changing network conditions and improving the routing efficiency through quantum-inspired probabilistic search techniques. The performance of the proposed HQI-ML model is validated through experimental results, and the findings reveal that the suggested model is more efficient in comparison to existing routing techniques like Dijkstra, Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO).