Abstract
Proposed herein are techniques to address limitations in classical Ant Colony Optimization (ACO) routing protocols that rely on static, hand-crafted probabilistic rules and lack contextual awareness. Traditional ACO-based routing reacts slowly to rapid topology changes or fluctuating link quality, and pheromone evaporation alone cannot ensure fast convergence in highly dynamic or congested environments. To overcome these limitations, techniques herein replace conventional control packets with intelligent software-based AI agents that employ learning-based decision models. These AI agents evaluate link quality, predict route reliability, and optimize exploration behavior in real time by integrating machine-learning-based decision-making with adaptive ACO behavior. The techniques enable context-aware routing decisions, faster convergence, and improved Quality of Service (QoS) compliance. By combining learned value functions with pheromone values, the disclosed AI-Enhanced ACO routing protocol provides a hybrid routing mechanism capable of handling mobility, congestion, and multi-metric optimization, leading to faster convergence, improved path stability, and smarter multipath routing in dynamic wireless and mesh networking environments.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
M M, Niranjan and P Bhavanasi, Srihari, "AN AI-ENHANCED ANT COLONY OPTIMIZATION BASED ROUTING PROTOCOL", Technical Disclosure Commons, (February 26, 2026)
https://www.tdcommons.org/dpubs_series/9399