Abstract

Integrating machine learning (ML) into network management and orchestration has revolutionized edgebased networking paradigms, where real-time decision-making is critical. Traditional network management approaches often struggle with edge environments' dynamic and resource-constrained nature. By leveraging ML algorithms, networks at the edge can achieve enhanced efficiency, automation, and adaptability in areas such as traffic prediction, resource allocation, and anomaly detection (Wang et al., 2021). Supervised and unsupervised learning techniques facilitate proactive network optimization, reducing latency and improving quality of service (QoS) (Li & Zhang, 2020). Furthermore, reinforcement learning (RL) models enable autonomous network orchestration, allowing edge devices to adapt intelligently to fluctuating workloads and environmental conditions (Patel et al., 2019). However, challenges such as data privacy, computational overhead, and model interpretability remain key concerns in deploying ML-driven network orchestration at the edge (Chen et al., 2022). This paper explores state-of-the-art advancements, key challenges, and future research directions in ML-based edge network management, highlighting its potential to drive the next generation of intelligent, self-optimizing networks.