Optimizing Emergency Video Delivery in Connected Vehicular Networks Using a Genetic Approach

Abstract

Real-time streaming of multimedia content in vehicular networks presents various challenges, including rapidly changing network topology, lack of global vision, and fluctuating traffic conditions. To address these challenges, this paper proposes a genetic algorithm-based method to optimize emergency video streaming in Vehicular Fog Computing (VFC) environments. This approach enables adapting video transmission during road incidents without requiring prior network knowledge, while optimizing resource utilization and reducing latency. Routing reliability and efficiency are ensured through TCP for intra-frame and UDP for inter-frame transmissions. Experimental results show that the proposed streaming mechanism significantly outperforms traditional GA-based routing, with notable improvements such as reduced End-to-End Delay (E2ED) and increased throughput. Additionally, gains were observed in path discovery time, load management and processing time.