Resource Optimization and Forecasting of Mobile Ad-hoc Network using Particle Swarm Optimization along with Ensemble ML Modeling in 6G

In the evolution towards 6G networks, Mobile ad-hoc networks (MANETs) emerge as vital components, offering adaptability in dynamic environments. However, efficient resource management remains a challenge. This study delves into resource optimization and forecasting techniques within 6G MANETs, particularly focusing on bandwidth and congestion parameters. We utilize innovative machine learning models, including Artificial Neural Networks (ANN), Particle Swarm Optimization (PSO), and ensemble methods, to enhance resource utilization effectively. Moreover, we employ Recurrent Neural Networks (RNN) and Adaptive Neuro-Fuzzy Inference Systems (AN-FIS) to forecast temporal variations in network conditions. Leveraging historical network data, our models generate accurate and precise forecasts. By integrating optimization and forecasting techniques, this research contributes to enhancing network scalability and performance, thus directly aligning with the objectives of UN Sustainable Development Goal 9: Industry, Innovation, and Infrastructure.