Temperature Prediction of Photovoltaic Panels Based on Support Vector Machine with Pigeon-Inspired Optimization

Table 3

Comparison of prediction accuracy for the temperature of PV panels.

Method	MAPE (%)	Accuracy improvement (%)	Training time (s)
SVM	0.4172	—	—
DE-SVM	0.3130	28.08	—
PSO-SVM	0.3138	27.91	128.595743
PIO-SVM	0.3121	28.51	116.0571
OPIO-SVM	0.3104	28.59	103.87497
DFPIO-SVM	0.2883	28.97	94.505892