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

Table 8

Errors of different traditional models in August.

	Models	MAE (m/s)	MSE (m^2/s^2)	MAPE (%)	Running time (s)
Observation site 1	BPANN	0.4595	0.3856	7.95	1.0696
	ARIMA	0.4657	0.3989	8.05	39.0358
	AFSA-BPANN	0.4612	0.3840	7.98	102.2733
	WT-BPANN	0.4668	0.3956	8.05	1.0735
	WT-ARIMA	0.4787	0.4201	8.25	43.0450
	WAFSA-BPANN	0.3377	0.2055	5.94	147.2995
Observation site 2	BPANN	0.4189	0.3351	8.12	0.4442
	ARIMA	0.4189	0.3396	8.13	37.0051
	AFSA-BPANN	0.4139	0.3259	8	105.3182
	WT-BPANN	0.4239	0.3438	8.17	0.9281
	WT-ARIMA	0.4303	0.3563	8.3	37.1158
	WAFSA-BPANN	0.3043	0.1831	6.07	145.4899
Observation site 3	BPANN	0.4601	0.3883	8.26	2.2823
	ARIMA	0.4689	0.3981	8.48	37.7879
	AFSA-BPANN	0.4600	0.3850	8.32	102.6349
	WT-BPANN	0.4665	0.3928	8.39	2.0385
	WT-ARIMA	0.4727	0.4044	8.48	40.7267
	WAFSA-BPANN	0.3407	02140	6.35	142.8692