Mathematical Problems in Engineering / 2015 / Article / Tab 6

Research Article

A New Hybrid Model Based on an Intelligent Optimization Algorithm and a Data Denoising Method to Make Wind Speed Predication

Table 6

Errors of different traditional models in February.

ModelsMAE (m/s) MSE (m2/s2)MAPE (%)Running time (s)

Observation site 1BPANN0.39110.30416.682.8502
ARIMA0.40880.3208747.2708
AFSA-BPANN0.39280.30696.71105.3652
WT-BPANN0.37700.27356.585.1081
WT-ARIMA0.38190.28216.5340.7528
WAFSA-BPANN0.30400.16225.4156.3590

Observation site 2BPANN0.42190.33049.52.0659
ARIMA0.44150.35269.9435.5574
AFSA-BPANN0.43070.33899.78106.2827
WT-BPANN0.40870.304592.4668
WT-ARIMA0.41300.31099.0342.0537
WAFSA-BPANN0.31340.16747.44148.8582

Observation site 3BPANN0.39750.28458.270.5424
ARIMA0.40980.30218.4342.4113
AFSA-BPANN0.39490.27938.24105.7024
WT-BPANN0.38330.26548.050.7321
WT-ARIMA0.38490.26947.9240.7567
WAFSA-BPANN0.30550.16016.87146.8292