In the age of digital transformation, network applications are placing unprecedented demands on network infrastructure. Traditional network management solutions are simply not up to the task, struggling to keep pace with the evolving needs of modern applications such as augmented and virtual reality, holographic telepresence, etc.
MAGNNETO, an innovative Machine Learning framework for autonomous network optimization, is designed to address the main operational challenges of modern networked systems. Our proposed framework integrates a Graph Neural Network architecture into a Multi-Agent Reinforcement Learning setting, enabling fully decentralized optimization that capitalizes on the inherent distributed nature of networked environments.
MAGNNETO is adaptable and versatile, offering the potential to handle a wide range of network optimization challenges. It has already been successfully implemented in two highly impactful scenarios: Traffic Engineering optimization and Congestion Control in Datacenters. In both cases, MAGNNETO has achieved similar performance to state-of-the-art approaches, offering significant improvements in execution cost while being totally compliant with current and legacy equipment.
In this talk, we will explore the MAGNNETO framework in detail, discussing its innovative design, key features, and multifaceted applications. In addition to this, we will also introduce a promising research line to enhance the framework by integrating Topological Deep Learning techniques, envisioning a novel approach that goes beyond the traditional graph domain.
Join us as we embark on a pioneering journey to redefine the landscape of distributed network optimization and management with MAGNNETO.
