Artificial Neural Networks to Predict the Power Output of a PV Panel

Table 5

ANNs results for the Kyocera panel; bold identifies the ANNs with the best performance.

Topology	Error distribution [W]			Absolute error distribution [W]			Epochs	Time [s]
	Mean	Median	Stdev	Mean	Median	Stdev
Mlp_1	0.05	−0.5	8.1	5.3	3.0	6.2	15417	31
Mlp_2	−0.1	0.5	7.3	4.3	2.3	5.9	2854	5
Mlp_3	−1.9	−1.1	8.1	5.3	3.0	6.4	6354	12
Mlp_4	−0.9	−0.3	7.6	4.6	2.8	6.1	993	1
RNN_1	−0.6	−0.6	4.8	3.3	2.1	3.6	4976	102
RNN_2	9.8	7.1	11.2	11.2	8.2	9.8	533	10
RNN_3	0.7	1.4	8.6	5.7	3.2	6.5	555	11
Gamma_1	−1.0	0.4	8.9	5.8	3.2	6.8	126	2
Gamma_2	−3.0	−1.5	8.3	5.7	3.4	6.7	346	6