Leveraging Software-Defined Networks for Load Balancing in Data Centre Networks using Linear Programming

Abstract

A rapid increase in the number of online applications has led to exponential growth in traffic. In data centers, it is hard to dynamically balance such huge amounts of traffic while keeping track of server data. A load-balancing strategy is an effective solution for distributing such huge amounts of traffic. The major contribution of this research work is to improve the performance of the network by designing a dynamic load balancing algorithm based on server data using SDN, reduction of controller overhead and optimizing energy consumption in a server pool. The problem is formulated using a Linear Programming mathematical model. In order to demonstrate the effectiveness and feasibility of the proposed technique, the experimental setup is deployed using real hardware components such as a Zodiac-Fx switch, Ryu controller and various web servers in the data center network. This proposed scheme is compared with round-robin and random load balancing mechanisms. The experimental results show that the performance is improved by 87.4% while saving 78% of the energy.