Optimizing WDM Network Restoration with Deep Reinforcement Learning and Graph Neural Networks Integration

Network survivability is a major and critical con-cern in the design and operation of Wavelength Division Multi-plexing (WDM) networks. The vulnerability of these networks to various external (e.g. natural disaster, human accidents) or internal (e.g. equipment aging, power failure) disruptions necessitates effective mechanisms for quick service restoration. To efficiently restore the affected services has been a major research problem for many years. Several solutions such as pre-computed restoration paths or using heuristic algorithms have been proposed. These approaches have limitations in terms of adaptability to unforeseen network topologies and prolonged outages. In this paper, we introduce an approach to improve resilience in WDM networks by integrating Deep Reinforcement Learning (DRL) with Graph Neural Networks (GNN). Our proposed DRL+GNN-based solution leverages the capabilities of DRL in decision-making and the inherent ability of GNNs to generalize over graphs of varying sizes and structures. By considering the current and future state of the network, our solution intelligently selects pre-computed restoration paths that is viable. The results demonstrate the superior performance of our DRL+GNN agent in comparison to existing algorithms across a wide range of failure scenarios and network loading.