This paper evaluates a Deep Q-Network (DQN_CC) based congestion control mechanism for multi-hop mobile wireless networks, extending its previous evaluation in static Wireless Smart Grid environments to scenarios characterized by node mobility and dynamic topologies. Unlike traditional Q-learning approaches that rely on discrete Q-tables and cope with large state spaces, DQN_CC employs deep reinforcement learning to generalize across states, enabling real-time regulation of packet transmissions based on observations of global and local packet delivery ratios (PDRs) without the need for pre-labeled datasets. Simulation campaigns with networks of different sizes and mobility patterns demonstrate that DQN_CC consistently improves key performance metrics, achieving higher PDR, lower end-to-end delays, and higher throughput compared to configurations without congestion control. While slightly moderating the overall throughput delivered to mitigate congestion, DQN_CC ensures that a higher proportion of packets meet latency constraints, highlighting its effectiveness in maintaining reliable and timely communication in challenging multi-hop mobile wireless scenarios.

Wireless propagation loss modeling has gained significant attention due to its critical importance in forthcoming dynamic wireless technologies. Stochastic and map-based propagation models require more information (elevation extension, statistical scattering characteristics) than required by empirical models (i.e., operating frequency, distance between transceivers, and height of the antennas), but such information is not always available. Thus, empirical models are still widely used to evaluate coverage, link budget, and received signal strength. The drawback of empirical models is inaccuracy in highly dynamic transmitter and receiver environments. To reduce the error caused by the use of a single environment, we divide a geographical terrain to employ a specific propagation model in each segment of the wireless link. We enhance a deep learning (DL) encoder-decoder architecture to extract semantic information from satellite imagery to divide an environment into three classes. Our DL architecture achieved a segmentation accuracy of 89.41%, 86.47%, and 87.37% in urban, suburban, and rural classes, respectively. Simulation results indicate that estimating propagation loss with our multi-environment model reduced the root mean square deviation (RMSD) with respect to two publicly available wireless tracing datasets, CU-WART and Portland MetroFi, by 3.79dB and 4.09dB, respectively.