Controller Placement in Software-Defined Multihop Wireless Networks: Optimal Solution and GA-based Approximation

In a multi-controller software-defined networking (SDN) architecture, solving the controller placement problem (CPP) has a direct effect on the generated control overhead in the network. We aim to minimize the control overhead exchanged in the network, especially in software-defined multihop wireless networks (SDMWN), i.e., a network that is built on multihop communications using a wireless medium. We solve this problem both optimally, using a nonlinear optimization model, and via a heuristic algorithm. The proposed heuristic approach is based on the genetic algorithm (GA). The objective of both the proposed optimization problem and the proposed GA algorithm is to find a given number of controllers, controller placements and assignments of controllers to devices while minimizing the generated control overhead in the network. Our results show the impact of different metrics, including the number of controllers, the arrival rate of new flows and the capacity limit of wireless links on the control overhead and the average number of controller-device and inter-controller hops. In addition, our results demonstrate that the GA-based heuristic approach can derive the same optimal solution for a small network with much less computational overhead, and can solve larger networks in a short period of time, making it feasible for non-trivial network sizes.