@INPROCEEDINGS{Routing-with-ART,
AUTHOR="Antonino Angi and Alessio Sacco and Flavio Esposito and Guido Marchetto",
TITLE="Routing with {ART:} Adaptive Routing for {P4} Switches With {In-Network}
Decision Trees",
BOOKTITLE="2024 IEEE Global Communications Conference: Next-Generation Networking and
Internet (Globecom 2024 NGNI)",
ADDRESS="Cape Town, South Africa",
PAGES="5.93",
DAYS=7,
MONTH=dec,
YEAR=2024,
ABSTRACT={Recent advances in Machine Learning (ML) brought several advantages also
within computer network management. For programmable data planes, however,
it is more challenging to benefit from these advantages, given the
complexity of ML models and their limited resource capabilities. In this
paper, we propose ART, an attempt to simplify ML-based solutions for
routing, so that they can ``fit{"}, i.e., be executed, on P4 switches. To
provide such model simplification, ART relies on efficient knowledge
distillation techniques, converting, in particular, Deep Reinforcement
Learning (DRL) models into simpler a Decision Tree (DT). Our evaluation
results validate the accuracy of the extracted model and the application of
the model logic directly into switches with little impact, paving the way
for a more reactive data plane programmability via machine learning
integration.}
}