Deep Learning-Based Dynamic Stable Cluster Head Selection in VANET

VANET is the spontaneous evolving creation of a wireless network, and clustering in these networks challenging task due to rapidly changing topology frequent disconnection networks. The cluster head (CH) stability plays prominent role robustness scalability network. stable CH ensures minimum intra- intercluster communication, thereby reducing overhead. These challenges lead authors search for selection method based on weighted amalgamation four metrics: befit factor, community neighborhood, eccentricity, trust. depends vehicle’s speed, distance, velocity, change acceleration. all are included factor. Also, accurate location vehicle model very vital. Thus, predicted with Kalman filter’s help used evaluate stability. results have shown better performance than existing state art dynamics communication links high speed inevitable. To comprehend this problem, graphing approach eccentricity neighborhood. link reliability calculated using eigengap heuristic. last metric trust; one concepts that has not been date as per literature. An adaptive spectrum sensing designed evaluating trust values specifically primary users. A deep recurrent learning commonly known long short-term memory (LSTM), trained probability detection various signals noise conditions. false rate drastically reduced usage LSTM. proposed scheme tested real map Chengdu, southwestern China’s Sichuan province, different vehicular mobilities. comparative study individual significant improvement during density. there considerable increase network energy, packet delay, delay ratio, throughput.