Transmission power adaptive congestion control algorithm based on Bayesian network

In vehicular ad hoc network (VANET), the interaction of vehicle state is realized by sending periodic beacon. When the number of vehicles in the network increases, a large number of nodes send beacon periodically, resulting in channel overload and congestion. Aiming at this issue, this paper designed an algorithm based on Bayesian network to adjust transmission power. Firstly, the algorithm evaluates the current channel load based on the channel busy ratio measured by the vehicle itself. Secondly, the parameter is used to predict the channel load at the next moment through Bayesian network learning. Finally, the transmission power is adaptively adjusted based on the prediction result to avoid the network congestion. The simulation experiment shows that the algorithm can effectively reduce the transmission delay, collision rate and improve packet delivery rate.