Application of Chaos and Neural Network in Power Load Forecasting

Table 1

Comparison of the forecasting results and errors by the different methods.

Time (h)	Real load (MW)	This paper’s method		Standard BP network method
		Results (MW)	Error (%)	Results (MW)	Error (%)
0	6416.69	6482.81	1.03	6554.61	2.15
1	6111.52	6185.50	1.21	6329.72	3.57
2	6044.52	6098.35	0.89	6206.50	2.68
3	5998.76	6041.46	0.71	6031.26	0.54
4	5813.06	5833.42	0.35	6073.57	4.48
5	5945.27	5852.57	−1.56	5823.41	−2.05
6	6195.15	6163.60	−0.51	6075.02	−1.94
7	6863.36	7001.31	2.01	6956.71	1.36
8	7232.71	7347.72	1.59	7457.66	3.11
9	7781.65	7879.76	1.26	7949.74	2.16
10	7847.12	7910.78	0.81	7974.20	1.62
11	8000.54	8154.24	1.92	8151.80	1.89
12	7756.46	7882.10	1.62	7614.51	−1.83
13	7154.43	7055.72	−1.38	6967.08	−2.62
14	7340.18	7263.15	−1.05	7077.44	−3.58
15	7467.57	7588.56	1.62	7344.41	−1.65
16	7513.92	7577.81	0.85	7586.82	0.97
17	7856.26	7963.15	1.36	7955.23	1.26
18	7862.16	7871.63	0.12	7831.54	−0.39
19	7891.19	7914.19	0.29	7776.06	−1.46
20	8487.14	8406.51	−0.95	8617.81	1.54
21	8180.10	8220.22	0.49	8362.52	2.23
22	7476.11	7570.30	1.26	7682.50	2.76
23	6416.69	6347.42	−1.08	6632.33	3.36
RSM	//	//	1.080	//	2.133