Journals
Publish with us
Publishing partnerships
About us
Blog
International Journal of Photoenergy
Journal overview
For authors
For reviewers
For editors
Table of Contents
Special Issues
International Journal of Photoenergy
/
2017
/
Article
/
Tab 3
/
Research Article
Learning Processes to Predict the Hourly Global, Direct, and Diffuse Solar Irradiance from Daily Global Radiation with Artificial Neural Networks
Table 3
Best performance of learning processes for different FFNN configurations.
Model
Input matrix
Hidden neurons
R
RMSE (kWh/m
2
)
1
SD, HA,
G
D
,
K
t
15
0.980
0.0707
2
SD,
G
D
,
K
t
10
0.846
0.1224
3
S
f
, HA,
G
D
,
K
t
15
0.953
0.0707
4
S
f,
HA,
K
t
12
0.892
0.1140
5
SD, HA,
K
t
10
0.920
0.0836
6
SD, HA,
G
D
10
0.891
0.1090
7
δ
, SD, HA,
G
D
,
K
t
20
0.984
0.0390
8
δ
, SD, HA,
G
D
,
K
t
,
W
ss
10
0.950
0.0707