VANET-Delay Minimization Routing with Mobility prediction for Artificial Neural Networks with ACO learning

  • Diwakar Bharadwaj et al.


Mobility prediction of the vehicles will address same challenge since will give a much best routing designing and it improve overall VANET the performance in term of continuous monitoring convenience. During this survey, centralized routing theme with the quality prediction (CRS-MP) planned for the VANET aided by the aSDN controller. Specifically, SDN controllerwill produce correct quality prediction through the Hybrid Artificial Neural Networks with Particle Swarm improvement Learning (HANN-ACO). during this work, performance of the pismire Colony improvement (ACO), a recently planned rule, has been tested on coaching on artificial neural networks. Then, supported the quality of  prediction, victorious transmissions likelihood and the average delay of the every vehicle request topology frequent changes calculable by wayside unit (RSUs) or bottom station (BS). Estimation is performed as supported a random urban- traffic model during which arrival of vehicle follows a less-homogeneous Poisson method (NHPP). SDN controller collects network data from RSUs and BS that square measure thought of because the switches. Supported the worldwide network data, the SDN  computesoptimum route ways for switch. Whereas supply vehicle and the destination vehicle square measure placed within coverage space of the identical switch, more route call are created by the RSUs or the BS severally to reduce the general conveyance service delay. Simulation results demonstratation that planned centralized route theme outperforms others in terms of the transmission delay, and also transmission performance of planned routing the me additional sturdy along with variable vehicle rate.

How to Cite
et al., D. B. (2019). VANET-Delay Minimization Routing with Mobility prediction for Artificial Neural Networks with ACO learning. International Journal of Control and Automation, 12(6), 169 - 178. Retrieved from