An efficient online auction for resource leasing in cloud radio access networks

This work studies the emerging C-RAN market in a 5G wireless network where mobile operators lease computation and communication resources from the tower company to serve wireless users. We propose an online C-RAN auction where each mobile operator bids for three types of resources in a future time window: wireless spectrum at base stations (BSs), front-haul link capacities, and mobile BS instances at the mobile cloud. We target an online C-RAN auction that executes in polynomial time, elicits truthful bids from mobile operators, and maximizes the social welfare of the C-RAN eco-system with both spectrum cost at BSs and server cost at the mobile cloud considered. We consider two business models of the tower company, and show how the marriage of i) a new Fenchel dual approach to convex optimization with ii) the posted pricing framework for online auction design can help achieve the three goals simultaneously, and evaluate the efficiency of our online C-RAN auction through both theoretical analysis and empirical studies.