AI-assisted resource advertising and pricing to realize distributed tenant-driven virtual network slicing in inter-DC optical networks

We propose a novel artificial intelligence (AI) assisted framework to realize virtual network (VNT) slicing in an inter-datacenter optical network (IDCON), where the infrastructure provider (InP) performs resource advertising and pricing based on deep reinforcement learning (DRL) and grants the virtual network embedding (VNE) schemes calculated distributedly by the tenants. Simulation results confirm that compared with the traditional centralized VNT slicing framework, our proposal can not only make the InP more profitable but also relieve its computation complexity effectively.