Lightpath requests processing in flexible packet switching optical networks using reinforcement learning

We present a self-adaptive framework to process lightpath requests on a packet switching optical network. Our framework takes care of issues regarding lightpath setting up, resource reservation and load balancing. The framework is composed of a dimensioning phase that adds up new resources to an initial topology and a learning phase that provides routing intelligence to efficiently use the dimensioned resources. The proposed framework is tested on a realistic topology achieving a probability of packet loss of 1×10^-4.