Dynamic Load Balancing Algorithm in SDN-based Data Center Networks
Gudu Bekama Haile, Jianxun Zhang · Zenodo (CERN European Organization for Nuclear Research) · 2021
Current networking architectures have many drawbacks that must be overcome to meet modern IT requirements. To overcome these limitations; Software Defined Networking (SDN) is taking place as the new networking approach. One of the major issues is that they use static switches that cause poor utilization of the network resources. Another issue is the slow response and delays are the main problems in current networking trend. This research proposes an implementation of a dynamic load balancing algorithm for SDN based three tier Data Center network to overcome these issues. A test has been implemented using Floodlight controller as SDN controller and Mininet software to emulate the network. Python programming language is used to define a network topology and to write the load balancing algorithm program. Finally, iPerf is used to test network performance. The network was tested before and after running the load balancing algorithm. The testing focused on Quality of Service (QoS) parameters such as throughput, bandwidth, and response time. The algorithm increased throughput with at least 50% at distribution level and with 33% at core level which also result in faster response time as well.