The mobile ad hoc network, which allows cars to wirelessly connect to mobile devices as needed, served as a major source of inspiration for the development of the vehicle ad hoc network (VANET). The changing network topology and the automotive ad hoc network’s constant mobility pose several challenges. Reliable communication between cars and infrastructure depends on efficient routing systems. Numerous intelligent solution alternatives for enhancing traffic flow, safety, and convenience are now feasible due to recent advancements in computing technologies, intelligent transportation systems, and communications. Many industries are increasingly utilizing artificial intelligence (AI) due to its significant enhancement of traditional data-driven methods. This chapter presents an intelligent deep route learning technique for estimating highway traffic density. Using network simulator 2.3, we simulate the proposed work and do a comparison study using different performance measurement factors, such as coverage ratio, packet delivery ratio (PDR), and control overhead. We compared the proposed methods with existing methods and found that our suggested route increases the aggregate packet delivery ratio (PDR) by 23% over the current method. This is because it improves system overhead management and reduces latency, making data transfer more efficient. Overall, the simulation results demonstrate that IDRL routing is more complete than I-AREOR, AREOR, and ARIOR when it comes to routing over VANETs.
DLAR: Deep Learning-Based Adaptive Routing Strategies for Vehicular Ad-Hoc Networks (VANETs)
Studies Comp.Intelligence
2025-06-09
24 pages
Article/Chapter (Book)
Electronic Resource
English