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.

Machine learning (ML) techniques have demonstrated considerable effectiveness when integrated into routing protocols to enhance the performance of Smart Grid Networks. However, their performance across diverse real-world scenarios remains a topic of exploration. In this study, we evaluate the performance and transferability of four ML models—Long Short-Term Memory (LSTM), Feedforward Neural Network (FF), Decision Trees, and Naive Bayes—across three distinct scenarios: Barcelona, Montreal, and Rome. Through rigorous experimentation and analysis, we analyze the varying efficacy of these models in different scenarios. Our results demonstrate that LSTM outperforms other models in the Montreal and Rome scenarios, highlighting its effectiveness in predicting the optimal forwarding node for packet transmission. In contrast, Ensemble of Bagged Decision Trees emerge as the optimal model for the Barcelona scenario, exhibiting strong performance in selecting the most suitable forwarding node for packet transmission. However, the transferability of these models to scenarios where they were not trained is notably limited, as evidenced by their decreased performance on datasets from other scenarios. This observation underscores the importance of considering the data characteristics when selecting ML models for real-world applications. Furthermore, we identify that the distribution of nodes within datasets significantly influences model performance, highlighting its critical role in determining model efficacy. These insights contribute to a deeper understanding of the challenges inherent in transferring ML models between real-world scenarios, providing valuable guidance for practitioners and researchers alike in optimizing ML applications in Smart Grid Networks.

In this paper, we propose different strategies to efficiently deploy RSUs in a city with the ultimate goal of having an 802.11p-based infrastructure to deliver Internet services. Unlike most existing works, (i) our strategies' only prior information is the average density of vehicles in the studied area, and (ii) they rely on the forecast of a performance model of 802.11p to assist and guide their choices regarding the location of RSUs. With the help of two simulators, namely SUMO and ns-3, we investigate the behavior of each strategy in three scenarios inspired by the street map of real-life major cities. Our findings are twofold: (i) we demonstrate that any efficient RSUs deployment is tightly tied to the specifics of the considered city (namely, the arrangement of streets and the spatial density of vehicles); (ii) the best strategy is not to position RSUs where the traffic density is at its highest, nor at the street junctions where the traffic density is often at its highest but instead where they will be able to deliver the target QoS to a maximum number of vehicles.

The application areas of multi-hop wireless networks are expected to experience sustained growth in the next years. This growth will be further supported by the current possibility of providing low-cost communication capabilities to any device. One of the main issues to consider with this type of networks is congestion control, that is, avoiding an excessive volume of data traffic that could lead to a loss of performance. In this work, a distributed congestion control mechanism is proposed for generic multi-hop networks. Different categories of data traffic are taken into account, each of them with different quality of service requirements. The mechanism is based on machine learning techniques, specifically, the CatBoost algorithm that uses gradient boosting on decision trees. The obtained decision trees are used to predict whether the packets to be transmitted over the network will reach their destination on time or not. This prediction will be made based on the network load state, which will be quantified by means of two parameters: the utilization factor of the different transmission channels, and the occupancy of the buffers of the network nodes. To make the values of these parameters available to all nodes in the network, an appropriate dissemination protocol has also been designed. Besides, a method to assign different transmission priorities to each traffic category, based on the estimation of the network resources required at any time, has also been included. The complete system has been implemented and evaluated through simulations, which show the correct functionality and the improvements obtained in terms of packet delivery ratio, network transit time, and traffic differentiation.

Mobile Ad-hoc Networks (MANETs) exhibit a limited wireless transmission range due to the interference present in the channel and the packets lost due to transmission errors. Diversity reception is a common technique in many radio communication systems, fixed or mobile, which improves signal reception quality. Although Maximum Ratio Combining (MRC) is a well-known diversity technique, its implementation for the ns-3 network simulator has not been published in the open technical literature given its complexity. In this sense, the main contribution of this work is an inexpensive implementation of MRC diversity reception in the ns-3 network simulator. To this end, we have used a single Nakagami-m fading channel to model the resulting received signal after using MRC to the copies of the transmitted signal. The proposed implementation is then evaluated in the context of two classic scenarios. The first one is a static linear chain topology network, and the second one is a MANET scenario. The performance evaluation confirms the correct implementation of our proposal and shows significant improvements in terms of network transit time and packet delivery ratio.