27 August 2020 in IEEE Transactions on Control Systems Technology
Two hierarchical control schemes for regulating traffic in freeway networks via ramp metering are developed in this article. Both schemes are characterized by a multiclass nature and aim to jointly improve the total time spent by the vehicles and their pollutant emissions in the freeway network. Moreover, these schemes have been designed to be ``implementation-oriented,'' i.e., they are characterized by a low computation and communication effort of the controllers while providing high performance in case of bottlenecks that may be far downstream on-ramp merging areas. The reduction of the computation and communication load is achieved through an event-triggered logic implemented at the higher level of the hierarchical scheme, in which the lower level is represented by extended multiclass ALINEA controllers characterized by time-varying parameters. The two proposed schemes differ for the fact that one is a centralized scheme, whereas the second one is decentralized. The effectiveness of the two schemes is evaluated by simulation in a realistic setting, also through a comparison with an optimization-based approach.
10 October 2018 in IEEE Transactions on Intelligent Transportation Systems
The efficiency of freeway systems is often hindered by recurrent and non-recurrent congestion. The occurrence of these events is due not only to the high number of vehicles trying to use a shared infrastructure, but also by phenomena that temporarily deteriorate the capacity of the infrastructure itself. Among them, road accidents are considered as one of the primary causes of non-recurrent congestion. At the same time, several studies also identify traffic breakdowns as events leading to vehicle crashes. A specific goal of this research is to develop a global safety index that quantifies the expected number of crashes as a function of the current traffic state in the freeway system. Moreover, on the basis of this new index and the performance indicator generally adopted to evaluate the traffic delay, a coordinated ramp metering scheme is proposed jointly considering the reduction of travel times for the drivers and the improvement of safety in the freeway system. The control strategy is sought by defining a nonlinear optimal control problem with constrained control variables, solved by applying a specific gradient-based algorithm. The simulation analysis investigates the multi-objective nature of the problem assessing whether and to what extent the two components of the cost criterion are conflicting objectives.
14 June 2022 in European Journal of Control
17 June 2022 in IEEE Control Systems Letters
This work considers electric and autonomous buses which have to follow a given route, including fixed stops, in extra-urban roads with a given timetable. A charging infrastructure is present in each stop, allowing to charge the bus batteries. An optimal control scheme is proposed in this paper in order to regulate the optimal speed of buses along the route and the stopping/charging times at stops. The proposed control scheme, acting in real time according to a receding-horizon logic, consists of two modules: a traffic prediction model and an optimal control problem solver. The traffic model measures the traffic state in real time, provides the traffic state prediction in the considered road stretch and, in particular, communicates the predicted average speed in each road section to the second module. This latter computes the optimal behavior of buses by optimizing their expected final energy level, by maximizing their compliance with the timetable and by reducing oscillations in the speed profile. Simulation results based on a real case study show the effectiveness of the proposed control scheme.
31 January 2025 in IEEE Open Journal of Intelligent Transportation Systems
Effective traffic management and control are essential for mitigating congestion and minimizing environmental impacts on road transportation systems. In this paper, we propose a novel approach for traffic modeling that integrates physics-based dynamics with machine learning techniques. Our method leverages Gaussian Processes (GPs) and a multi-class second-order discrete traffic model known as METANET to develop a Physics-Regularized Machine Learning framework. Furthermore, the proposed approach includes for the first time multi-class on/off ramps within the modeling framework, enhancing the realism of the predictive model. We systematically evaluate the performance of the hybrid model across varying dataset sizes to determine optimal data requirements for accurate traffic predictions. Experimental results indicate the improved predictive performance of the proposed approach compared to traditional machine learning and physics-based models. Our findings underscore the potential of Physics-Regularized Machine Learning for enhancing traffic management and control strategies in real-world scenarios.