Network congestion prediction

Efficient congestion prediction plays a vital role in improving the performance, reliability, and scalability of modern computer networks. This work introduces a dataset comprising 12 carefully selected features that capture critical aspects of network behavior relevant to congestion analysis. The features reflect traffic characteristics, packet-level dynamics, and queue metrics that collectively represent both temporal and spatial conditions of the network. The dataset has been structured to support machine learning and deep learning applications, enabling the training and evaluation of predictive models that can proactively identify congestion patterns before they impact quality of service. By providing a comprehensive and feature-rich dataset, this work facilitates the development of AI-driven congestion prediction frameworks, with applications in Software-Defined Networking (SDN), healthcare communication systems, and next-generation intelligent networks.