AI-Driven Automation for Optimal Edge Cluster Network Management

Unlocking the potential of edge computing demands efficient network clustering management, this paper introduces a groundbreaking approach–Artificial intelligence (AI)-driven automation for Edge Cluster network systems and services. Indeed, the existing centralized structure of the edge cloud does not meet the supervision and regulation requirements of specific real-time services intended to be self-managed. Furthermore, the existing edge cloud is not compatible with next-generation network infrastructures because the existing ones rely on interdependence with centralized systems such as the Internet. This innovative solution leverages AI to automate and optimize the intricate dynamics of edge cluster networks and services. By seamlessly integrating AI technologies, this solution ensures real-time adaptability regarding autonomous network disconnection, resource optimization, heightened performance, and service re-clustering, setting the stage for a new era in edge computing. Hence, we assess our proposition using Recurrent Neural Networks (RNN) technology and a hierarchical clustering algorithm that we present in this manuscript to determine the optimal number of clusters based on the maximum distance between nodes within a cluster.