One of the most important goals of vehicular ad hoc networks (VANETs) in smart cities is the efficient management of accidents, specially to prevent them. Our research lies on a promising smart service, which soon might be available in our cities. After the occurrence of an accident, a vehicle could make a light and short video of the situation and send it through the VANET till reaching an access point in the infrastructure of the city to alert the emergencies service (e.g., 911 or 112). With a video message, the level of seriousness of the accident could be better interpreted by the authorities (i.e., health care unit, police, ambulance drivers) than with a simple text message. In this way, vehicles could participate in reporting a situation in the city using the ad hoc network so it would be possible to have a quick reaction of the emergency units and even prevent further accidents. The deployment of an efficient routing protocol to manage video-reporting messages in VANETs has important benefits by enabling a fast warning of the incident, which potentially might save lives. To contribute with this goal, we propose a multimedia multimetric map-aware routing protocol to provide video-reporting messages over VANETs in smart cities. Furthermore, a realistic scenario is created by using real maps with SUMO including buildings that may interfere the signal between sender and receiver. Also, we use our REVsim tool that allows vehicles to avoid choosing vehicles behind buildings to be chosen as next forwarding nodes. Simulations show the benefits of our proposal, taking into account the mobility of the nodes and the presence of interfering buildings.

In recent years, the general interest in routing for vehicular ad hoc networks (VANETs) has increased notably. Many proposals have been presented to improve the behavior of the routing decisions in these very changeable networks. In this paper, we propose a new routing protocol for VANETs that uses four different metrics. which are the distance to destination, the vehicles’ density, the vehicles’ trajectory and the available bandwidth, making use of the information retrieved by the sensors of the vehicle, in order to make forwarding decisions, minimizing packet losses and packet delay. Through simulation, we compare our proposal to other protocols, such as AODV (Ad hoc On-Demand Distance Vector), GPSR (Greedy Perimeter Stateless Routing), I-GPSR (Improvement GPSR) and to our previous proposal, GBSR-B (Greedy Buffer Stateless Routing Building-aware). Besides, we present a performance evaluation of the individual importance of each metric to make forwarding decisions. Experimental results show that our proposed forwarding decision outperforms existing solutions in terms of packet delivery.

This research explores the potential of Machine Learning (ML) to enhance wireless communication networks, specifically in the context of Wireless Smart Grid Networks (WSGNs). We integrated ML into the well-established Routing Protocol for Low-Power and Lossy Networks (RPL), resulting in an advanced version called ML-RPL. This novel protocol utilizes CatBoost, a Gradient Boosted Decision Trees (GBDT) algorithm, to optimize routing decisions. The ML model, trained on a dataset of routing metrics, predicts the probability of successfully reaching a destination node. Each node in the network uses the model to choose the route with the highest probability of effectively delivering packets. Our performance evaluation, carried out in a realistic scenario and under various traffic loads, reveals that ML-RPL significantly improves the packet delivery ratio and minimizes end-to-end delay, making it a promising solution for more efficient and responsive WSGNs.

Road safety applications envisaged for Vehicular Ad Hoc Networks (VANETs) depend largely on the dissemination of warning messages to deliver information to concerned vehicles. The intended applications, as well as some inherent VANET characteristics, make data dissemination an essential service and a challenging task in this kind of networks. This work lays out a decentralized stochastic solution for the data dissemination problem through two game-theoretical mechanisms. Given the non-stationarity induced by a highly dynamic topology, diverse network densities, and intermittent connectivity, a solution for the formulated game requires an adaptive procedure able to exploit the environment changes. Extensive simulations reveal that our proposal excels in terms of number of transmissions, lower end-to-end delay and reduced overhead while maintaining high delivery ratio, compared to other proposals.