A Deep-Reinforcement-Learning-based Dynamic Scheduling of Delay-Tolerant Requests in Elastic Optical Networks

We propose a deep reinforcement learning (DRL) framework for dynamic scheduling of delay-tolerant requests in the elastic optical networks, where the DRL agent automatically adjusts its scheduling strategy by interacting with the dynamic network environment. To the best of our knowledge, this is the first attempt to introduce DRL to schedule the delay-tolerant requests. The simulation results demonstrate that our proposed method outperforms the conventional heuristic methods.