abstract

Research on congestion management and avoidance mechanisms is required since, as data use has been on the rise, current algorithms are struggling to keep up with demand and will need to be improved in the future. With respect to packet loss rates and buffer space requirements, blue is shown to be a much superior algorithm than red via the use of both controlled tests and simulations. The Blue algorithm targets packet loss and connection utilization to provide congestion management. In contrast to every other Active Queue Management technique, blue employs queue length to gauge network congestion. In order to decrease the dimensionality of the neural network structure, the input characteristics of the Bus System are selected using an angular distance-based clustering algorithm. Both online and offline modes of congestion management may make use of the suggested approaches.