Performance Optimization of Software-Defined Industrial Internet-of-Things (SD-IIoT)

Abstract

Software-Defined Networking (SDN) offers a centralized network management approach that can effectively address the complex and varied traffic demands characteristic of Industrial Internet of Things (IIoT) environments by decoupling the control plane from the data plane. The centralized control architecture of SDN necessitates the performance optimization of controllers to manage diverse traffic efficiently within IIoT applications. This paper explores the criteria for selecting controllers in SDN-enabled IIoT (SD-IIoT) environments, utilizing the Less Complex Analytic Network Process (LC-ANP) to establish their prioritization. A ranking system for SD-IIoT controllers is formulated using LC-ANP, and experimental validation of this method underscores its effectiveness in optimizing controller performance. The proposed approach enhances the overall efficiency of SDN-enabled IIoT networks, as evidenced by experimental evaluations measuring delay, throughput, packet loss ratio (PLR), and jitter across five different topologies with varying nodes and edges. The experiments indicate an overall increase in the average throughput, and a decrease in delay, jitter, and PLR. The results also show that the suggested strategy and proposed controller surpass the benchmark controller in complex network topologies. These results confirm the method's capacity to significantly improve network performance in SD-IIoT applications.