A New WRR Algorithm for an Efficient Load Balancing System in IoT Networks under SDN

Abstract

The Internet of Things (IoT) connects various smart objects and manages a vast network using diverse technologies, which present numerous challenges. Software-defined networking (SDN) is a system that addresses the challenges of traditional networks and ensures the centralized configuration of network entities to manage network integrity. Furthermore, the uneven distribution of IoT network load results in the depletion of IoT device resources. To address this issue, traffic must be distributed equally, requiring efficient load balancing to be ensured. This requires the development of an efficient architecture for IoT networks. The main goal of this paper is to propose a novel architecture that leverages the potential of SDN, the clustering technique, and a new weighted round-robin (N-WRR) protocol. The objective of this architecture is to achieve load balancing, which is a crucial aspect in the development of IoT networks as it ensures the network’s efficiency. Furthermore, to prevent network congestion and ensure efficient data flow by redistributing traffic from overloaded paths to less burdened ones. The simulation results demonstrate that our N-WRR algorithm achieves highly efficient load balancing compared to the simple weighted round-robin (WRR), and without the application of any load balancing method. Furthermore, our proposed approach enhances throughput, data transfer, and bandwidth availability. This results in an increase in processed requests.