Bio-Inspired Optimisation Algorithm for Congestion Control in Computer Networking

Abstract

The development of internet technology gives consumers the chance to transfer packets across networks instantly. Such developments in internet technology are anticipated to ease congestion. Despite this, the majority of firms were bound by the expense of deploying cutting-edge technology or updating network infrastructure, necessitating efficient congestion management. Inherent distribution optimisation, which requires each source device on the network to continually adjust to its traffic load using the feedback information received or acknowledged from another source device, is unfortunately the problem with congestion management. This research addresses the issue of continually adjusting to a network traffic load by presenting a unique optimisation technique. This strategy is based on the features and hunting behaviour of foxes and rabbits on wild grass. A computer network congestion optimisation technique, named Fox Prey Optimisation, was created using a mathematical formulation of the fox predatory characteristics. The FPO algorithm is comparable to the Particle Swarm Optimisation (PSO), Ant Colony Optimisation (ACO), Artificial Bee Colony (ABC), and Firefly (FA) algorithmic methods that are inspired by nature. In utilising a set of standard benchmark functions, the algorithms were assessed, and the findings demonstrate, using the Levy N. 13 multimodal benchmark function, that FPO guaranteed a global minimum value of 2.0055, while PSO, ACO, and FA provided 5.6683, 3.1795e+03, and 10 respectively. ABC though did fairly well by registering 2.0, almost the same as FPO. As a consequence, FPO was able to adjust to the load of network traffic by adopting an ideal value of 2.0055. � 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.