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

Table 7

Errors of different traditional models in June.

	Models	MAE (m/s)	MSE (m^2/s^2)	MAPE (%)	Running time (s)
Observation site 1	BPANN	0.4637	0.4260	10.48	0.8509
	ARIMA	0.4617	0.4215	10.06	37.0557
	AFSA-BPANN	0.4701	0.4267	10.91	104.7545
	WT-BPANN	0.4625	0.4278	10.05	1.4735
	WT-ARIMA	0.4663	0.4315	10.08	37.9540
	WAFSA-BPANN	0.3381	0.2066	8.14	145.9524
Observation site 2	BPANN	0.4446	0.3783	9.99	1.1537
	ARIMA	0.4442	0.3737	9.78	41.4958
	AFSA-BPANN	0.4443	0.3770	10.07	108.9195
	WT-BPANN	0.4450	0.3849	9.76	73.93
	WT-ARIMA	0.4462	0.3859	9.78	42.0491
	WAFSA-BPANN	0.3441	0.2084	8.27	143.1720
Observation site 3	BPANN	0.4716	0.3987	11.78	0.5463
	ARIMA	0.4671	0.3930	11.09	36.7596
	AFSA-BPANN	0.4720	0.3989	11.7	104.6663
	WT-BPANN	0.4700	0.4144	11.17	0.7220
	WT-ARIMA	0.4727	0.4198	11.08	41.9609
	WAFSA-BPANN	0.3353	0.2008	8.64	142.3210