Gateway Selection in 5G/Wi-Fi Architecture: A Fire Emergency Case Study

Public safety and first-responder networks require technologies that outperform current emergency networks. 5G and Wi-Fi architectures seem to be promising solutions for those environments. However, seamless integration of these wireless networks needs to be well investigated to benefit from the advan-tages of both networks and to fulfill the firefighter requirements. For this purpose, we propose a gateway selection algorithm for firefighter interventions. Proximal Policy Optimization, a well-known reinforcement learning strategy, is used to define and train the agent. Simulation results demonstrate that the proposed framework outperforms the Host Network Association scheme defined in the Optimized Link State Routing Protocol in terms of network throughput and packet drop rate.