Mehmood Khawaja Tahir, Atiq Shahid, Hussain Muhammad Majid
Department of Electrical Engineering, Khwaja Fareed University of Engineering & Information Technology, Rahim Yar Khan 64200, Pakistan.
School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh EH14 4AS, UK.
Sensors (Basel). 2023 Nov 22;23(23):9324. doi: 10.3390/s23239324.
In the modern era, with the emergence of the Internet of Things (IoT), big data applications, cloud computing, and the ever-increasing demand for high-speed internet with the aid of upgraded telecom network resources, users now require virtualization of the network for smart handling of modern-day challenges to obtain better services (in terms of security, reliability, scalability, etc.). These requirements can be fulfilled by using software-defined networking (SDN). This research article emphasizes one of the major aspects of the practical implementation of SDN to enhance the QoS of a virtual network through the load management of network servers. In an SDN-based network, several servers are available to fulfill users' hypertext transfer protocol (HTTP) requests to ensure dynamic routing under the influence of the SDN controller. However, if the number of requests is directed to a specific server, the controller is bound to follow the user-programmed instructions, and the load on that server is increased, which results in (a) an increase in end-to-end user delay, (b) a decrease in the data transfer rate, and (c) a decrease in the available bandwidth of the targeted server. All of the above-mentioned factors will result in the degradation of network QoS. With the implementation of the proposed algorithm, dynamic active sensing server load management (DASLM), on the SDN controller, the load on the server is shared based on QoS control parameters (throughput, response time, round trip time, etc.). The overall delay is reduced, and the bandwidth utilization along with throughput is also increased.
在现代，随着物联网（IoT）、大数据应用、云计算的出现，以及借助升级后的电信网络资源对高速互联网的需求不断增加，用户现在需要对网络进行虚拟化，以便智能应对现代挑战，从而获得更好的服务（在安全性、可靠性、可扩展性等方面）。这些需求可以通过使用软件定义网络（SDN）来满足。本文着重探讨了SDN实际应用的一个主要方面，即通过网络服务器的负载管理来提高虚拟网络的服务质量（QoS）。在基于SDN的网络中，有多个服务器可用于满足用户的超文本传输协议（HTTP）请求，以确保在SDN控制器的影响下进行动态路由。然而，如果大量请求指向特定服务器，控制器必然会遵循用户编程的指令，该服务器的负载就会增加，这会导致：（a）端到端用户延迟增加；（b）数据传输速率降低；（c）目标服务器的可用带宽减少。上述所有因素都会导致网络QoS下降。通过在SDN控制器上实施所提出的动态主动感知服务器负载管理（DASLM）算法，服务器负载会根据QoS控制参数（吞吐量、响应时间、往返时间等）进行共享。整体延迟降低，带宽利用率和吞吐量也会提高。
