OQPMSAV: Opportunistic Quality of Services Provisioning for Multimedia Services using Artificial Neural Network

Abstract

Vehicular ad hoc network is used to provide services related to traffic safety and user requirements. In VANET, applications are designed for users from various domains automobile company, road safety authority, advertisement industries, personal entertainment. Applications developer requires efficient utilization of available networking resources. VANET is witnessed of continuous support form researchers, developer, government authorities and vehicles manufactures. In VANET, vehicles are designed to move at high speed which causes more frequent disruption for data communication. Frequent loss of wireless communication link and outdated routes are common phenomenon. Applications in VANET are classified into safety and non-safety messages. In this research work, we have focused on multimedia applications requirements and reliable delivery of multimedia messages in VANET. An adaptive mechanism is proposed to provide QoS provisioning for multimedia applications. Artificial neural network is used to estimate requirements for applications andenhancevehicular network wireless communication efficiency. OQPMSAV is designed to provide reliable multimedia services delivery in high vehicular mobility and frequent disruption in wireless links. Vehicles in Network Simulation (Veins) simulation tool and Simulation of Urban Mobility (SUMO) are used for simulation experiments. Simulation experiments are performed for analyzing OQPMSAV for successful delivery of multimedia messages in different scenarios. Simulation results show that OQPMSAV provides reliable and timely delivery of multimedia services in terms of successful packet delivery ratios.

Keywords:Vehicular ad hoc Networks (VANETs);IEEE 802.11p;Quality of Service; Artificial Neural Network; OMNeT++; Veins; SUMO

Cite this Article
UpendraDwivedi, Akhilesh R. Upadhyay. Opportunistic Quality of Services Provisioning for Multimedia Services using Artificial Neural Network. Journal of Communication Engineering & Systems. 2018; 8(1): 25–38p.