The coordinated scheduling of electric vehicle (EV) charging is a critical challenge for smart cities, particularly in high-density infrastructure such as Mobility Hubs (MHs). This paper evaluates and compares two prominent approaches to the EV Charging Scheduling Problem (CSP): Mixed-Integer Linear Programming (MILP) and Reinforcement Learning (RL). We formulate a shared problem framework and apply both strategies under two structured scenarios: a small-scale deterministic benchmark and a medium-scale, realistic deployment with higher heterogeneity. Results show that MILP achieves optimal cost and state of charge SoC compliance in tractable cases but struggles with scalability. RL, based on Proximal Policy Optimization (PPO), achieves near-optimal performance while scaling to 100 EVs with minimal computation time. Despite occasional SoC deviations, the RL agent exhibits robust and adaptive behavior under dynamic conditions. This study offers actionable insights for selecting and deploying EV scheduling strategies in real-world urban environments.

Traffic congestion in urban areas has intensified due to the rapid growth of vehicles, inadequate infrastructure planning, and unsynchronized traffic signals. This study presents an adaptive traffic signal control strategy called Gap-Fuzzy, which combines the Mamdani fuzzy logic controller with a gapout detection mechanism. The system dynamically adjusts the duration of the green light based on real-time traffic data, including queue length and arrival rate. Furthermore, the green phase is terminated early if prolonged gaps in vehicle flow are detected. We evaluated the proposed Gap-Fuzzy system using the SUMO microscopic traffic simulator. The results indicate that it reduced vehicle waiting times by up to 70% and CO2emissions by 25% compared to fixed-time control. In addition, it outperformed the SUMO actuated controller under low, medium, and high traffic conditions while maintaining comparable performance under very high demand. These findings highlight the effectiveness of integrating fuzzy logic with gap-out detection to enhance traffic flow and minimize environmental impact.

We are witnessing a profound shift in societal and political attitudes, driven by the visible consequences of climate change in urban environments. Urban planners, public transport providers, and traffic managers are urgently reimagining cities to promote sustainable mobility and expand green spaces for pedestrians, bicycles, and scooters. To design more sustainable cities, urban planners require realistic simulation tools to optimize mobility, identify location for car chargers, convert streets to pedestrian zones, and evaluate the impact of alternative configurations. However, realistic traffic profiles are essential to produce meaningful simulation results. Addressing this need, we propose a traffic generator based on deep reinforcement learning integrated with the SUMO simulator. This tool learns to generate an instantaneous number of vehicles throughout the day, aligning closely with the target profiles observed at the traffic monitoring stations. Our approach generates accurate 24-hour traffic patterns for any city using minimal statistical data, achieving higher accuracy compared to existing alternatives. In particular, our proposal demonstrates a highly accurate 24-hour traffic adjustment, with the generated traffic deviating only by about 5% from the real target traffic. This performance significantly exceeds that of current SUMO tools like RouteSampler, which struggle to accurately follow the total daily traffic curve, especially during peak hours when severe traffic congestion occurs.

This study presents a privacy-sensitive traffic signal control system based on Deep Q-Networks (DQN) aimed at reducing carbon emissions in urban dense scenarios by minimizing vehicle waiting time at road intersections. The system utilizes data from the city infrastructure (non-sensitive data) while addressing privacy concerns. We validate the model's effectiveness using a testing framework that includes various reward function models, training scenarios, and traffic conditions. Preliminary results indicate that during peak hours, the system can reduce vehicle waiting times at intersections by up to 50%. This work serves as a reference for developing intelligent and sustainable transportation systems.

The Third Generation Partnership Project (3GPP) has recently announced its Release 16, which introduces advanced functionalities to support the cellular vehicle to everything (C-V2X) technology. C-V2X allows direct communication between vehicles through the sidelink operation. This appears as an option to DSRC technologies; both are key wireless technologies that play a vital role in implementing and deploying advanced driving applications. This paper presents a thorough review of the available open-source frameworks intended for the performance evaluation of C-V2X protocols and V2X applications. For this, we consider validated OMNeT++-based simulation libraries and frameworks: SimuLTE, OpenCV2X, Artery-C, 5G-Sim-V2I/N, and Simu5G. We focus on the different frameworks' support regarding advanced V2X communications on 5G mobile networks.

Simulations are the first approach used by the research community to evaluate mobile ad hoc networks. Particularly, vehicular ad hoc networks (VANETs) are a singular type of mobile ad hoc networks that raise technical challenges, for instance, in the context of vehicular mobility models. When assessing VANETs, realistic vehicular models are essential to produce meaningful evaluation results. In this context, realistic vehicles' mobility includes re-routing capabilities that allow vehicles to re-compute their routes in front of specific traffic conditions (e.g., traffic jams). In this paper, we provide a thorough analysis of the influence of enabling re-routing properties on (i) the mobility of the vehicle and (ii) on the connections of the vehicular network. For this, we use the road traffic simulator SUMO to generate vehicular traces, and then we will analyze the connectivity of the vehicular network employing well-known graph metrics. Our results provide insights about the behavior of the vehicle's mobility and the nodes' connectivity.