Leveraging SDN for scalable and sustainable fat tree networks: a multi-objective performance and energy efficiency evaluation of an 8-pod fat tree data center

Modern data centers increasingly rely on Software-Defined Networking (SDN) to address challenges related to scalability, performance, and efficient resource management. This research investigates the scalability and performance optimization of fat-tree topology within SDN environments, focusing on the impact of a sleep mode technique on network efficiency and energy consumption. Using the Mininet emulator, an 8-pod fat-tree network is simulated and compared against traditional routing methods like Equal-Cost Multi-Path (ECMP) and Dijkstra’s algorithm. The findings show that the sleep mode technique improves bandwidth utilization and throughput by reducing energy consumption during low-traffic periods without significantly affecting data flow. In contrast, Dijkstra’s algorithm exhibited reduced throughput due to inefficient path management, while ECMP did not fully optimize load balancing or energy efficiency. The sleep mode approach efficiently redistributes traffic across active switches, preventing congestion and outperforming both Dijkstra and ECMP in terms of average load. The results demonstrate that implementing sleep mode in fat-tree SDN networks enhances both network performance and energy efficiency, offering a practical solution for large-scale data center operations. These findings provide valuable insights for optimizing SDN-based traffic management in modern network infrastructures.