Abstract:
One of the world’s largest networks is VANETs. These networks offer infotainment, safety, driver assistance, and video on demand. VANETs have random topology and dynamic behavior that changes in urban contexts and highways.
However, spreading information is essential for multiple services. Thus, broadcasting is difficult and requires further study. In fact, artificial intelligence and learning-based computing appear to be the best options for VANETs’ dynamic behavior.
This project proposes a reinforcement learning-based hybrid relay selection technique for broadcasting. We first use an artificial neural network-based classification to select forwarding nodes, then use the Viterbi algorithm as a reinforcement tool to refine the first classification.
We use a grid map with different traffic densities to evaluate our contribution. After that, we compare the simulation results to other methods in the literature based on parameters like success rate, data loss, saved rebroadcasts, and delay.
We conclude that the proposed technique combining deep learning and reinforcement learning outperforms other recently proposed broadcasting schemes by increasing the success rate by 16%, the saved rebroadcasts by 20%, and the delay by 23%.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
