AI-Driven Network Traffic Management and Predictions

Abstract

With the evolution of digital communication networks, needs for intelligent traffic management solutions to monitor and control the resource utilization and the performance of the network have been growing so rapidly. The study explores how Artificial Intelligence (AI) can be applied to predict and manage network traffic, using secondary data analysis of benchmark datasets and published literature. The study compares and contrasts the performances of various AI techniques, such as machine learning and deep learning models, for predicting network traffic, managing congestion, optimizing overheads and improving QOS. Results show that improved deep learning models, such as 'Transformer' and LSTM, offer a better prediction accuracy and can improve network performance greatly compared with traditional models. AI-based predictive analytics is essential for intelligent, adaptive, and autonomous communication networks to facilitate future digital infrastructures, the study concludes.