The status of energy consumption and air pollution in China is serious. It is important to analyze and predict the different fuel consumption of various types of vehicles under different influence factors. In order to...The status of energy consumption and air pollution in China is serious. It is important to analyze and predict the different fuel consumption of various types of vehicles under different influence factors. In order to fully describe the relationship between fuel consumption and the impact factors, massive amounts of floating vehicle data were used.The fuel consumption pattern and congestion pattern based on large samples of historical floating vehicle data were explored, drivers＇ information and vehicles＇ parameters from different group classification were probed, and the average velocity and average fuel consumption in the temporal dimension and spatial dimension were analyzed respectively.The fuel consumption forecasting model was established by using a Back Propagation Neural Network. Part of the sample set was used to train the forecasting model and the remaining part of the sample set was used as input to the forecasting model.展开更多
基金supported by the project "Research on the Traffic Environment Carrying Capacity and Feedback Gating Based Dynamic Traffic Control in Urban Network" which is funded by the China Postdoctoral Science Foundation (No. 2013M540102)supported by the Open Foundation of smart-city research center of Hangzhou Dianzi University, smart-city research center of Zhejiang Province
文摘The status of energy consumption and air pollution in China is serious. It is important to analyze and predict the different fuel consumption of various types of vehicles under different influence factors. In order to fully describe the relationship between fuel consumption and the impact factors, massive amounts of floating vehicle data were used.The fuel consumption pattern and congestion pattern based on large samples of historical floating vehicle data were explored, drivers＇ information and vehicles＇ parameters from different group classification were probed, and the average velocity and average fuel consumption in the temporal dimension and spatial dimension were analyzed respectively.The fuel consumption forecasting model was established by using a Back Propagation Neural Network. Part of the sample set was used to train the forecasting model and the remaining part of the sample set was used as input to the forecasting model.
