Vehicular networks support intelligent transportation system (ITS) to improve drivers' safety and traffic efficiency on the road by exchanging traffic-related information between vehicles and also between vehicles and infrastructure. Routing protocols that are designed for vehicular networks should be flexible and able to adapt to the inherent dynamic network characteristics of these kind of networks. Therefore, there is a need to have effective vehicular communications, not only to make mobility more efficient but also to reduce collateral issues such as pollution and health problems. Nowadays, the use of machine learning (ML) algorithms in wireless networks are on the rise, including vehicle networks that can benefit from possible data-driven predictions. This work aims to contribute to the design of a smart ML-based routing protocol for vehicular ad hoc networks (VANETs) used to report traffic-related messages in urban environments. We propose a new ML-based forwarding algorithm to be used by the current vehicle holding a given packet to predict which vehicle within its transmission range is the best next-hop to forward that packet towards its destination. Our algorithm is based on a neural network designed from a dataset that contains data records that are captured during simulated urban scenarios. Simulation results show how our ML-based proposal improves the performance of our multimetric routing protocol for VANETs in urban scenarios in terms of packet delivery probability. The performance evaluation of MPANN shows packet losses lower than 20% (and average packet delays below 0.04 ms) for different vehicles' densities, in completely new scenarios but of similar complexity than the Barcelona scenario used to train the model. Even for much more complex scenarios (with narrow curvy streets), our proposal is able to reduce the packet losses in 20% with respect to the multimetric routing protocol as well as the average packet delays in 0.04 ms.

Usually, simulations are the first approach to evaluate wireless and mobile networks due to the difficulties involved in deploying real test scenarios. Working with simulations, testing, and validating the target network model often requires a large number of simulation runs. Consequently, there are a significant amount of outcomes to be analyzed to finally plot results. One of the most extensively used simulators for wireless and mobile networks is OMNeT++. This simulation environment provides useful tools to automate the execution of simulation campaigns, yet single-scenario simulations are also supported where the assignation of resources (i.e., CPUs) has to be declared manually. However, conducting a large number of simulations is still cumbersome and can be improved to make it easier, faster, and more comfortable to analyze. In this work, we propose a large-scale simulations framework called simulations manager for OMNeT++ (SMO). SMO allows OMNeT++ users to quickly and easily execute large-scale network simulations, hiding the tedious process of conducting big simulation campaigns. Our framework automates simulations executions, resources assignment, and post-simulation data analysis through the use of Python’s wide established statistical analysis tools. Besides, our tool is flexible and easy to adapt to many different network scenarios. Our framework is accompanied by a command-line environment allowing a fast and easy manipulation that allows users to significantly reduce the total processing time to carry out large sets of simulations about 25% of the original time. Our code and its documentation are publicly available at GitHub and on our website.