Advanced optimization techniques become necessary due to the fast-expanding broadband networks to deliver high-quality service. This research evaluates Artificial Intelligence (AI) methods to improve broadband service quality through definitions of essential Quality of Service (QoS) metrics and the creation of an AI-based optimization system. The research consists of examining three distinct machine learning models which include Support Vector Machines (SVM) along with Random Forests (RF) and K-Nearest Neighbors (KNN) for network performance optimization. The research introduces Q-learning-based reinforcement learning as an additional approach which optimizes broadband network management by implementing real-time resource adjustments and lowering operational inefficiencies. A combination of machine learning techniques with reinforcement learning within broadband networks produces remarkable improvements in latency and jitter and throughput and packet loss together with more reliable operations and adaptive managerial capabilities. This research uses extensive study and experimental simulations to develop important findings about intelligent broadband networks which leads to AI-based self-optimizing networks of the future. Future studies aim to integrate 5G technology and edge computing with AI systems as a means to improve both the intelligence level and scalable properties of broadband networks.
Shashishekhar Ramagundam (Thu,) studied this question.