Heuristic approaches for the reliable SDN controller placement problem

Software-defined networking (SDN) is one of the most used network architecture that divides the forwarding plane and control plane. The SDN centrally observes and regulates the network through a software control in the control plane, called as controller. Multiple controllers are needed to manage the software-defined WAN (SD-WAN) for handling the scalability and reliability issues of the network as one controller is not enough. Deploying numerous controllers efficiently to improve the performance of the network is known as controller placement problem (CPP). This paper proposes a Varna-based optimization (VBO) for a reliable CPP that minimizes the total average latency of SDN. To the best of our knowledge, the proposed work is a novel approach, which is compared with particle swarm optimization, teacher learning-based optimization, and Jaya algorithms to solve reliable CPP. The experimental results show that VBO gives better performance than teacher learning-based optimization (TLBO), PSO, and Jaya algorithms for the popular topologies that are publicly available.