Research On Location-based Vehicular Ad Hoc Network

Vehicular Ad Hoc Network (VANET) is applied for future Intelligent Transportation System(ITS) to improve road traffic safety and enrich vehicular multimedia applications. The locationinformation of the vehicle plays an important role in the VANET. In the paper, image processingand machine learning techniques are deployed to estimate the vehicle position which can be usedfor parameter selection of the Orthogonal Frequency Division Multiplexing (OFDM) transmission.From the vehicular communication perspective speaking, the architecture of the VANET can bedivided into Roadside-to-Vehicle Communications (RVC) and Inter-Vehicle Communications (IVC).The paper studies these two scenarios.Chapter2introduces the VANET and related position estimation technologies. Furthermore, therelated wireless communication technique is given, including vehicular wireless channel andOFDM transmission principle as well as Adaptive Modulation and Coding (AMC).Chapter3gives the realization of the vehicular position perception in VANET that we focus on.Based on the understanding of the related image processing and machine learning technologies, wefocus on the detection and the position estimation of the target vehicle which will be used for thesubsequent adaptive MCS selection.Chapter4studies the AMC under the IVC scenario and performs the simulation. The simulationresults show that the adaptive MCS based on the position estimation can obtain greater throughputcomparing with fixed MCS in the wireless fading channel and the OFDM physical layer modelunder the IVC scenario.Chapter5studies the AMC under the RVC scenario and performs the simulation.The simulationresults show the vehicular position information can be used for the MCS selection in the OFDMtransmission to achieve performance gain in the throughput.