DServ‐LB: Dynamic server load balancing algorithm

Summary In recent years, web services have been largely accessed by the customer, and it increases the network traffic on the internet. To provide the services for the large number of customer, dynamic clustering concept has been implemented that provides the ability to add or remove the servers on demand. But managing and processing the large set of traffic are very complicated. Load balancing technic helps to resolve the problems of network traffic and give efficient network management. In this paper, we proposed a dynamic server load balancing algorithm (DServ‐LB) using OpenFlow switches in software‐defined networking. The OpenFlow switches support the dynamic programmability. Also, we used the sFlow protocol, which is used to monitor the servers resource information periodically and the controller. Based on the server resource availability, the controller installs forwarding rules in the OpenFlow switches. For implementation, we used Mininet for network emulation, POX controller, and Docker container as Mininet hosts. The result shows that the proposed DServ‐LB improves the overall network performance and efficiently utilizes the server resources if compared with existing load balancing algorithms. When the switch receives the new request at the data center (as shown in Figure 1), it replaces the least loaded server IP address in the destination IP address field that is mentioned in the flow table by the controller. The least loaded server is selected based on the server load parameters such as remaining memory, remaining CPU, and number of connections available. After replacing the IP address, the packet is forwarded to the particular web server.