Optimal Content Distribution and Multi-resource Allocation in Software Defined Virtual CDNs

A software defined virtual content delivery network (SDvCDN) is a virtual cache network deployed fully in software over a programmable cloud network infrastructure that can be elastically consumed and optimized using global information about network conditions and service requirements. We formulate the joint content-resource allocation problem for the design of SDvCDNs, as a minimum cost mixed-cast flow problem with resource activation decisions. Our solution optimizes the placement and routing of content objects along with the allocation of the required virtual storage, compute, and transport resources, capturing activation and operational costs, content popularity, unicast and multicast delivery, as well as capacity and latency constraints. Numerical experiments confirm the benefit of elastically optimizing the SDvCDNs configuration, compared to the dedicated provisioning of traditional CDNs.