Review Paper on Routing and Networks Using Hybrid AI

In recent years, the engineering and physical sciences have been more interested in traffic dynamics. In order to increase the transportation efficiency of a scale-free network, we propose a routing strategy by building a cost function based on the ratio of degree to closeness centrality. In this brief, we concentrate on the traffic capacity that can be measured by the critical point of phase transition from free flow to congestion. Simulations are used to examine the average route length, traffic load, and maximum node betweenness. To further analyze the traffic distribution, load variance, load mean, and load decrease rate are added. Our approach outperforms the efficient routing (ER) technique by achieving a notable increase in traffic capacity and more equitable load distribution.