Research Article
A Simple Method of Residential Electricity Load Forecasting by Improved Bayesian Neural Networks
Table 9
Comparison models with the basic IBNN with 16 inputs.
| | Model No. | Inputs vectors describe (number of input vectors) | Inputs selection |
| | 1 | BNN_16 (16) | | | 2 | No historical Load (8) | | | 3 | Less T (14) | | | 4 | Less RH (14) | | | 5 | No T (13) | | | 6 | No RH (13) | | | 7 | No time (15) | | | 8 | No day-type (15) | | | 9 | Only Load (8) | | | 10 | Only T and Load (9) | | | 11 | Time, T and Load (10) | | | 12 | day-type, T and Load (10) | | | 13 | T, RH and Load (10) | |
|
|
T-Temperature RH-Relative Humidity.
|
