Ultra-fast Optical Network Throughput Prediction using Graph Neural Networks

One of the key performance metrics for optical networks is the maximum achievable throughput. Determining it however, is an NP-hard optimisation problem, often solved via computationally expensive integer linear programming (ILP) formulations. Heuristics, in conjunction with sequential loading, are scalable but non-exact. There is, thus, a need for ultra-fast performance evaluation of optical networks. For the first time, we propose message passing neural networks (MPNN), to learn the relationship between the structure and the maximum achievable throughput of optical networks. We demonstrate that MPNNs can accurately predict the maximum achievable throughput while reducing the computational time by 5-orders of magnitude compared to the ILP.