The Role of AI in Real-Time Decision-Making for Communication Networks: A Study on Self-Optimization and Latency Reduction

Abstract

The rapid advancement of communication networks, including wireless, cellular, and IoT technologies, has led to an increased demand for high-speed data transmission and low-latency performance. Traditional network management systems struggle to meet these dynamic requirements, especially with latency-sensitive applications such as autonomous vehicles, real-time streaming, and telemedicine. This study investigates the role of Artificial Intelligence (AI) in enhancing real-time decision-making within communication networks, focusing on self-optimization and latency reduction. By leveraging machine learning (ML), deep learning (DL), and reinforcement learning (RL), AI-driven systems can dynamically adjust network parameters, predict traffic patterns, and allocate resources autonomously. The research highlights the application of AI frameworks, including Software-Defined Networking (SDN) and edge computing, in reducing latency and optimizing network performance. The findings underscore AI's transformative potential to autonomously manage network configurations, stabilize latency, and ensure efficient resource allocation, paving the way for scalable, high-performance communication networks suitable for next-generation applications.