Abstract
Energy consumption in vehicle driving is greatly influenced by traffic scenarios, and the intelligent traffic system (ITS) has a key role in solving the real-time optimal control of hybrid vehicles. To this end, a new energy management control strategy based on vehicle-to-everything (V2X) communication for vehicle speed prediction was proposed to dynamically adjust the engine and motor power output according to the traffic conditions. This study is based on intelligent network connectivity technology to obtain forward traffic state data and use a deep learning algorithm to model vehicle speed prediction using the traffic state data. The energy economy function was modeled using the MATLAB/Sinumlink platform and validated with a plug-in hybrid vehicle model simulation. The results indicate that the proposed strategy improves the vehicle energy economy by 13.02% and reduces CO2 emissions by 16.04% under real vehicle driving conditions, compared with the conventional logic threshold-based control strategy.
Highlights
A speed prediction model based on a deep learning network was designed to improve
A speed prediction model based on a deep learning network was designed to imthe accuracy of vehicle speed prediction
Combined with VISSIM to build a scethe speed prediction is performed by simulating the speed and traffic information of the nario, the speed prediction is performed by simulating the speed and traffic information vehicle in front of the target vehicle through V2V and V2I communication technologies of the vehicle in front of the target vehicle through V2V and V2I communication technolunder the conditions of intelligent network connection to ensure the real-time accuracy of ogies under the conditions of intelligent network connection to ensure the real-time accuthe energy management strategy
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. To develop an optimal energy management strategy, the predicted vehicle speed is used to calculate the future vehicle energy demand, which is used to adjust the vehicle’s power distribution in real time to obtain a suitable fuel economy and alleviate the congestion and auto emissions in urban areas [2,3]. The strategies abovementioned studies focusedfor onfixed developing energy management management based on speedhave prediction operating conditions using strategies based onand speed prediction for fixed operating using GPS information. State of charge (SOC) values, a control strategy based on a on a combination ofcurrent logic threshold and instantaneous optimization is used to dynamicombination logic threshold instantaneous optimization is usedenergy to dynamically cally allocateofthe demand torqueand to create a hybrid vehicle with optimal economy. Allocate the demand torque to create a hybrid vehicle with optimal energy economy
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
