The application and performance optimization of multi-controller-based load balancing algorithm in computer networks

This paper addresses the critical issue of network congestion caused by the increase in network traffic in contemporary society. The computer networks serve as the foundation for information exchange and online services, and their efficiency is essential. Traditional load-balancing algorithms face challenges in handling dynamic workloads, leading to inefficient resource utilization and extended response time. To address this problem, a novel method called Genetic-Bird Swarm Optimization (GBSO) is introduced, focusing on multi-controller-based load balancing. This method involves problem modeling, analysis, and selection processes, including the selection of switches and target controllers within the network segment. The results showed that the throughput of the proposed GBSO method was about 3800, and the load index after load balancing was 0.6, indicating that the workload distribution was balanced. The accuracy of the proposed GBSO algorithm was 92.15 %, the precision was 89 %, the recall rate was 88 %, and the F1 score was 85 %, all of which were higher than the existing Naive Bayes algorithm. This study emphasizes the importance of load balancing in optimizing computer network performance. The new algorithm proposed in this article provides a reliable solution for uniform network traffic distribution, reducing the limitations of existing methods.