Adaptive Hybrid Genetic-Ant Colony Optimization for Dynamic Self-Healing and Network Performance Optimization in 5G/6G Networks

Abstract

The rapid growth of 5G/6G networks requires resilient solutions to optimize network performance while ensuring adaptability against failures. This paper introduces a novel Adaptive Hybrid Genetic-Ant Colony Optimization (GA-ACO) framework, designed for dynamic self-healing and multi-objective performance optimization in next-generation mobile networks. The developed method combines the global optimization competencies of a Genetic Algorithm (GA) with the local rerouting performance of Ant Colony Optimization (ACO), developing a dynamic switching mechanism. When no faults are detected, GA optimizes critical objectives such as latency minimization, bandwidth utilization, and energy efficiency. After identifying network faults, such as base station failures, ACO quickly reroutes impacted devices to preserve fault tolerance and minimize downtime. Main network metrics, including latency, bandwidth utilization, energy efficiency, and fault tolerance, are optimized at the same time utilizing a weighted-sum fitness function. The model adjusts dynamically to changing network situations, making it perfectly appropriate for real-time applications in 5G/6G networks, such as smart cities and mission-critical communications. Simulation results show the efficiency of the GA-ACO hybrid, demonstrating improved network efficiency and rapid recovery during failures. This innovative adaptive approach guarantees a more effective, efficient, and sustainable mobile communication network, competent of facing the complex needs of future 5G/6G technologies.