Development of a Representative EV Urban Driving Cycle Based on a k-Means and SVM Hybrid Clustering Algorithm
Table 9
Comparison of the Xi’an EV urban driving cycle and test data.
Characteristic parameters
Test data
Driving cycle
RE
MRE
RMSE
Average speed (km/h)
20.01
20.74
3.65%
4.03%
1.32%
Maximum speed (km/h)
68.22
63.86
6.39%
Average acceleration (m/s2)
0.76
0.78
2.63%
Average deceleration (m/s2)
0.78
0.77
1.28%
Standard deviation of acceleration (m/s2)
0.84
0.79
5.95%
Proportion of acceleration(%)
34.5
32.9
4.64%
Proportion of deceleration(%)
32.1
31.9
0.62%
Proportion of uniform speed(%)
15.9
17.3
8.81%
Proportion of idling(%)
17.5
17.9
2.29%
Note: RE is the relative error of the assessment parameters of the candidate driving cycles and the overall test data; MRE is the mean relative error of all assessment parameters; and RMSE is the root mean square error of the SAPD.