TAP-DBA: A Traffic-Aware Predictive Bandwidth Allocation Framework for Multi-Gigabit WANs

The rapid growth of network traffic and the emergence of multi-gigabit wide area networks (WANs) have necessitated the development of advanced bandwidth allocation mechanisms to ensure optimal Quality of Service (QoS). This paper proposes a Traffic-Aware Predictive Dynamic Bandwidth Allocation (TAP-DBA) algorithm designed to address the challenge of real-time adaptability in multi-gigabit networks. TAP-DBA integrates Traffic Classification and Predictive Bandwidth Allocation to optimize QoS for diverse traffic types, including real-time, bulk, and best-effort traffic. The algorithm leverages Deep Packet Inspection (DPI) and Machine Learning (ML)-based predictive analytics to dynamically allocate bandwidth while ensuring low latency, efficient utilisation, and fairness. Simulation results demonstrate the effectiveness of TAP-DBA in reducing latency for critical traffic, maximising throughput, and maintaining equitable bandwidth distribution. The proposed framework is scalable, secure, and compatible with existing network protocols, making it a promising solution for next-generation WANs.