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.

The particular requirements and special features of vehicular ad hoc networks (VANETs) (e.g., special mobility patterns, short link lifetimes, rapid topology changes) involve challenges for the research community. One of these challenges is the development of new routing protocols specially designed for VANETs. In this paper, we present a novel game-theoretical approach of a multimetric geographical routing protocol for VANETs to forward video-reporting messages in smart cities. Game theory is considered a very interesting theoretical framework to analyze and optimize resource allocation problems in digital communication scenarios. Our contribution has shown to enhance the overall performance of VANETs in urban scenarios, in terms of percentage of packet losses, average end-to-end packet delay and peak signal to noise ratio (PSNR).

The design of different metrics in hop-by-hop routing protocols for vehicular ad hoc networks (VANETs) has been investigated with the clear objective to improve the performance of VANETs in terms of packet losses and average end-to-end delay. However, the best way of combining these metrics to compute a multiscore value for each candidate node to choose the best forwarding one, is an open issue yet. Based on a previous designed routing protocol called Multimedia Multimetric MapAware Routing Protocol (3MRP), a detailed analysis of the power mean function is done to determine which form of metrics combination will give the best results in terms of packet losses and average end-to-end delay. Extensive simulations have been conducted indicating that the geometric mean has obtained the lowest average percentage of packet losses.

Video content delivery for vehicular ad hoc networks (VANETs) is envisioned to be of high benefit for road safety, traffic management as well as for providing value-added vehicle services. In this paper, we evaluate five existing dissemination mechanisms in a realistic urban scenario. We also propose RCP+ as a renovated mechanism for adaptative video streaming over VANETs. RCP+ is a cross layer dissemination mechanism for video safety messages that specifically addresses urban scenarios with zero infrastructure support. Through simulations, we compare our proposal with other distributed dissemination mechanisms. The performance evaluation shows that our proposal mechanism is more suitable for video transmission in realistic urban scenarios. The results also indicate that a modified frame coding approach provides many opportunities for multimedia services.

Road safety has become a main issue for governments and car manufacturers in the last twenty years. The development of new vehicular technologies has favoured companies, researchers and institutions to focus their efforts on improving road safety. During the last decades, the evolution of wireless technologies has allowed researchers to design communication systems where vehicles participate in the communication networks. Thus, new types of networks, such as Vehicular Ad Hoc Networks (VANETs), have been created to facilitate communication between vehicles themselves and between vehicles and infrastructure. New concepts where vehicular networks play an important role have appeared the last years, such as smart cities and living labs [1]. Smart cities include intelligent traffic management in which data from the TIC (Traffic Information Centre) infrastructures could be reachable at any point. To test the possibilities of these future cities, living labs (cities in which new designed systems can be tested in real conditions) have been created all over Europe. The goal of our framework is to transmit information about the traffic conditions to help the driver (or the vehicle itself) take adequate decisions. In this work, the development of a warning system composed of Intelligent Traffic Lights (ITLs) that provides information to drivers about traffic density and weather conditions in the streets of a city is proposed and evaluated through simulations.

Vehicular communication for intelligent transportation systems will provide safety, comfort for passengers, and more efficient travels. This type of network has the advantage to warn drivers of any event occurred in the road ahead, such as traffic jam, accidents or bad weather. This way, the number of traffic accidents may decrease and many lives could be saved. Moreover, a better selection of non-congested roads will help to reduce pollution. Some other interesting services, such as downloading of multimedia services, would be possible and available through infrastructure along the roadside. Providing multimedia services over VANETs may require a QoS-aware routing protocol that often need to estimate available resources. In this paper, we study the performance, in realistic VANET urban scenarios, of an extension of AODV that includes the available bandwidth estimator ABE. AODV-ABE establishes forwarding paths that satisfy the bandwidth required by the applications. The results, obtained on the NCTUns simulator, show that AODV-ABE could be used in urban-VANETs where vehicles' speed is moderate.