An Attention-Based Model for Travel Energy Consumption of Electric Vehicle with Traffic Information

Table 1

Comparison of different models of travel energy consumption prediction.

	MAE	MSE	MAPE
RNN (att) + DNN	0.074682	0.163005	0.105525
RNN + DNN	0.078688	0.171749	0.111659
RNN + DNN (without vehicle data)	0.082078	0.179148	0.118443
DNN	0.131376	0.286749	0.173804

The bold values represent the algorithm with the least error; that is, the prediction effect of the algorithm is the best.