A Genetic-based Discrete Metaheuristic Algorithm for Controller Placement in Software-Defined Network

Software-Defined Networking (SDN) concept involves separating the control plane from the data plane. The network control is determined by an entity called the controller located on the control plane. Determining the optimal number and placement of controllers on the control plane is known as the Controller Placement Problem (CPP). This article addresses the resolution of CPP using Unsupervised Kmeans (U-kmeans) and Horse Herd Optimized Algorithm (HOA). The U-kmeans algorithm clusters switches and determines the number of controllers. Since the CPP problem is discrete, the HOA algorithm uses genetic operators, called Modified HOA (MHOA). The next step of this article involves finding the optimal location for each controller within its cluster using MHOA. To improve the convergence rate, MHOA utilizes an Elite Opposition-based Learning (EOBL) strategy. The effectiveness and scalability of the proposed algorithm are evaluated through simulation tests on various networks. The results show that the proposed method outperforms other state-of-the-art algorithms regarding metrics such as end-to-end delay, load imbalance, and energy consumption. In particular, the proposed method reduces load imbalance by 9.66%, end-to-end delay by 19.65%, and average energy consumption by 8.43%.