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

Table 9

Errors of different traditional models in October.

	Models	MAE (m/s)	MSE (m^2/s^2)	MAPE (%)	Running time (s)
Observation site 1	BPANN	0.3824	0.2768	7.2	0.5651
	ARIMA	0.3827	0.2766	7.18	32.6927
	AFSA-BPANN	0.3827	0.2752	7.22	110.4872
	WT-BPANN	0.3898	0.2954	7.25	0.6419
	WT-ARIMA	0.3930	0.3019	7.27	35.1270
	WAFSA-BPANN	0.2963	0.1503	5.79	151.7133
Observation site 2	BPANN	0.4141	0.3206	8.05	0.8032
	ARIMA	0.4122	0.3257	7.89	33.0404
	AFSA-BPANN	0.4157	0.3238	8.11	109.5214
	WT-BPANN	0.4274	0.3511	8.11	0.8312
	WT-ARIMA	0.4301	0.3526	8.16	35.2028
	WAFSA-BPANN	0.3164	0.1983	6.34	147.8061
Observation site 3	BPANN	0.4156	0.3245	8.75	0.5211
	ARIMA	0.4148	0.3242	8.85	35.9502
	AFSA-BPANN	0.4085	0.3132	8.78	105.3837
	WT-BPANN	0.4167	0.3288	8.9	0.5227
	WT-ARIMA	0.4297	0.3504	9.15	36.1737
	WAFSA-BPANN	0.3356	0.2173	7.45	142.9675