Search

In alignment with climate change, the European Union endeavors to accelerate the electrification progress of the public transit system. In particular, Copenhagen in Denmark and Oslo in Norway develop a blueprint to have 100% public transit electrification by 2030 and 2028, respectively. In this study, the lifecycle approach is applied to explore the role of electric buses in the electrification progress of the public transport system in different European countries. To better model the energy/fuel consumption, we integrate the theoretical model of human thermal comfortable temperature into our proposed framework. We take into account the effects of weather, the daily operation characteristics, and the energy mix of different European counties, and evaluate the lifecycle environmental and economic performance of electric buses. The result shows that the public transportation system with both hybrid and electric buses can be good compensation between financial and environmental needs instead of using electric buses to replace all the conventional buses. Moreover, the operational plan of the public transportation system mixed with electric and hybrid buses may be adjusted according to the seasonal temperature variation so as to maximize the environmental benefits. Considering the different economic and environmental scenarios of energy sources, some EU countries would be able to reduce or remove the incentives for electric buses.

In this paper, a data-driven two-lane traffic flow model based on cellular automata is proposed. Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) are used to learn the characteristics of car following behavior and lane changing behavior, respectively, from real operation data of vehicles. Under optimal network parameters, the mean absolute errors of the LSTM network for training and testing data are only 0.001 and 0.006, respectively; while the prediction accuracy of the SVM classifier for both data reaches higher than 0.99. Moreover, forward rules and lane changing rules which are more consistent with actual situation are designed. The simulation results show that: (1) the new model can reflect the first-order phase transition from free flow to synchronized flow; (2) the frequency of unsuccessful lane changing is near zero in low-density traffic areas, but increases sharply in high-density regions; and (3) the lane changing duration and unsuccessful lane changing frequency display similar trends as traffic densities increase.