AI-DRIVEN BROADBAND NETWORK PERFORMANCE PREDICTION USING GREY WOLF OPTIMIZATION-OPTIMIZED NEURAL NETWORKS

Abstract

Predicting broadband network performance is a critical task for optimizing bandwidth allocation, ensuring smooth data transmission, and improving overall user experience. Traditional prediction models often struggle to adapt to the dynamic nature of network environments, leading to inaccurate predictions. This paper introduces an AI-driven framework for broadband network performance prediction, utilizing a Grey Wolf Optimization (GWO) algorithm to optimize a neural network model. By treating network traffic as a time series, we apply advanced AI techniques to predict future traffic patterns. The hybrid GWO-optimized neural network fine-tunes the model's hyperparameters, significantly improving its predictive accuracy and adaptability. Extensive simulations reveal that our approach outperforms conventional machine learning methods, offering enhanced accuracy, efficiency, and the ability to adapt to continuously changing network conditions.