Framework for Integrating Machine Learning Methods for Path-Aware Source Routing

Since the advent of software-defined networking (SDN), Traffic Engineering (TE) has been highlighted as one of the key applications that can be achieved through software-controlled protocols (e.g. PCEP and MPLS). Being one of the most complex challenges in networking, TE problems involve difficult decisions such as allocating flows, either via splitting them among multiple paths or by using a reservation system, to minimize congestion. However, creating an optimized solution is cumbersome and difficult as traffic patterns vary and change with network scale, capacity, and demand. AI methods can help alleviate this by finding optimized TE solutions for the best network performance. SDN-based TE tools such as Teal, Hecate and more, use classification techniques or deep reinforcement learning to find optimal network TE solutions that are demonstrated in simulation. Routing control conducted via source routing tools, e.g., PolKA, can help dynamically divert network flows. In this paper, we propose a novel framework that leverages Hecate to practically demonstrate TE on a real network, collaborating with PolKA, a source routing tool. With real-time traffic statistics, Hecate uses this data to compute optimal paths that are then communicated to PolKA to allocate flows. Several contributions are made to show a practical implementation of how this framework is tested using an emulated ecosystem mimicking a real P4 testbed scenario. This work proves valuable for truly engineered self-driving networks helping translate theory to practice.