SDN-based Optimal Traffic Engineering for Cellular Networks with Service Chaining

Abstract

In this paper, we propose using software-defined networking technologies for optimal traffic engineering in cellular networks with service chaining. We study the case in which virtual machines are used to support network services and each flow requires multiple network services. To minimize the maximum load of virtual machines and guarantee that the sum rate of admitted flows is large enough, we formulate an optimization problem that is inherently different from the minimum cost flow problem. We transform the optimization problem to a linear programming problem, which can be solved in polynomial time. We also use numerical results to justify the usage of the proposed approach.