his dataset supports the experimental evaluation of an edge-native architecture for hybrid fiber-coaxial (HFC) networks, where transport-layer (L2–L4) processing is relocated from centralized vCMTS to access-level MEC nodes using the VPP HostStack. While this work focuses on L2–L4 softwarization and transport relocation, application-layer (L5) processing remains out of scope and is identified as a future research direction.
The dataset covers three test scenarios:
The advancement and ubiquity of digital networks have fundamentally transformed numerous spheres of human activity. At the heart of this phenomenon lies the Transmission Control Protocol (TCP) model, whose influence is particularly notable in the exponential growth of the Internet due to its potential ability to transmit flexibly through an advanced Congestion Control (CC). Seeking an even more efficient CC mechanism, this work proposes the construction of Deep Learning Neural Networks (MLP, LSTM, and CNN) for classifying network congestion levels.
