In Wireless Network, the vehicular ad-hoc network (VANET) has become a fast-growing emerging research topic. The great advent of developments in VANET has paved the way for the growth of Intelligent Transportation System (ITS) applications. It has provided essential information to the vehicles in the network, and it prevents and reduces traffic congestion during vehicles exchanging information in the network. The traffic congestion prediction plays a significant role in minimizing accidents in networks and improving traffic management for users.
When vehicles exchange information, some delays occur due to traffic that leads to congestion and energy consumption and emission of pollution disputable in traffic management for smart cities. Traditional deep learning-based traffic congestion prediction models exploit the dynamic behavior of the vehicles in the network that degrades the rendition of deep learning models in predicting the traffic congestion on the road or network. A hybrid deep learning model negotiates the dynamic behavior of the vehicle and predicts the congestion in traffic effectively on networks. Thus, a hybrid deep learning model enhances the ability to predict traffic congestion on the roads.