ACO-RTCov: An Ant Colony Optimization Framework for Real-Time Covariance Detection in 6G-Enabled IoT Networks

With the rapid development of 6G-enabled Internet of Things (IoT) networks, there is a dire need for fast, reliable data analysis methods that can handle large volumes of dynamic, decentralized data. Considering this, this study proposes a novel framework based on Ant Colony Optimization (ACO) for real-Time covariance detection in 6G-enabled IoT systems. Inspired by how ants find the best paths using pheromone trails, our proposed model treats sensor features as nodes in a graph and uses artificial ants to explore them by identifying important relationships between data streams. Integrated into a layered 6G IoT architecture with edge computing, the framework efficiently processes data and adapts to changing conditions by dynamically updating pheromone trails. Extensive evaluations using both real-world (IoTID20) and synthetically generated datasets demonstrate that our proposed ACO-based approach achieves an accuracy of 96.2% and outperforms Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Simulated Annealing (SA) by 6.8%, 4.4%, and 7.7%, respectively. These results highlight the model's superior ability to detect real-Time covariance patterns in dynamic 6G-IoT environments. In addition to the above, our proposed ACO meets the low-latency requirements of next-generation IoT applications.