@INPROCEEDINGS{icin23:Collaborative,
AUTHOR="Doriana Monaco and Alessio Sacco and Enrico Alberti and Guido Marchetto and
Flavio Esposito",
TITLE="A Collaborative and Distributed {Learning-Based} Solution to Autonomously
Plan Computer Networks",
BOOKTITLE="2023 26th Conference on Innovation in Clouds, Internet and Networks and
Workshops (ICIN) (ICIN 2023)",
ADDRESS="Paris, France",
DAYS="5",
MONTH=mar,
YEAR=2023,
KEYWORDS="software-defined networking; distributed learning; reinforcement learning",
ABSTRACT="The high programmability provided by Software Defined Networking (SDN)
paradigm facilitated the integration of Machine Learning (ML) methods to
design a new family of network management schemes. Among them, we can cite
self-driving networks, where ML is used to analyze data and define
strategies that are then translated into network configurations by the SDN
controllers, making the networks autonomous and capable of auto-scaling
decisions based on the network's needs. Despite their attractiveness, the
centralized design of the majority of proposed solutions cannot keep up
with the increasing size of the network. To this end, this paper
investigates the use of a multi-agent reinforcement learning (MARL) model
for auto-scaling decisions in a SDN environment.
In particular, we study two possible alternatives for distributing
operations: a collaborative one, where controllers share the same
observations, and an individual one, where controllers make decisions
according to their own logic and share only some basic information, such as
the network topology. After an experimental campaign performed both on
Mininet and GENI, results showed that both approaches can guarantee high
throughput while minimizing the set of active resources."
}