Traffic management in vehicular adhoc networks using hybrid deep neural networks and mobile agents

<p>The traffic congestion in vehicular adhoc networks (VANETs) is a vital problem due to its dynamic increase loads. VANETs undergo inefficient routing capability increasing demands. This has led the need for intelligent transport system (ITS) assist enabling suitable loads between vehicles and road side units (RSU). Most conventional systems offer distributed solution manage but fail regulate real-time flows. In this paper, control offered by combining deep neural network (DNN) with mobile agents (MA). An experimental analysis carried out test efficacy of DNN-MA against machine learning algorithm VANETs. DNN-Mal validated under various metrics like latency, percentage delivery ratio, packet error rate, throughput. The results show that proposed method offers reduced energy consumption latency.</p>