ML-enabled flow admission control policy for proactive QoS assurance in programmable RINA networks

In this paper, we investigate the deployment and performance benefits of a machine learning (ML)-enabled flow admission control policy for programmable networks following the clean slate Recursive InterNetwork Architecture (RINA) design principles. The proposed flow admission control policy is based on RouteNet, a cutting-edge Graph Neural Network (GNN) able to accurately predict per-path packet loss, delay and jitter metrics. Upon arrival of a new flow request, RouteNet can accurately estimate the Quality of Service (QoS) metrics experienced by all active traffic flows if the new incoming one is established in the network. In this way, incoming flow requests are accepted only when the QoS levels of all traffic flows are satisfied appropriately. Throughout the paper, we illustrate our envisioned ML-enabled QoS-aware RINA network scenario, while also disclosing initial proof-of-concept experimental results using the publicly available IRATI RINA prototype.