TY - JOUR
T1 - An ANFIS-Based Modeling Comparison Study for Photovoltaic Power at Different Geographical Places in Mexico
AU - Pitalúa-Díaz, Nun
AU - Arellano-Valmaña, Fernando
AU - Ruz-Hernandez, Jose A.
AU - Matsumoto, Yasuhiro
AU - Alazki, Hussain
AU - Herrera-López, Enrique J.
AU - Hinojosa-Palafox, Jesús Fernando
AU - García-Juárez, A.
AU - Pérez-Enciso, Ricardo Arturo
AU - Velázquez-Contreras, Enrique Fernando
N1 - Publisher Copyright:
© 2019 by the authors.
PY - 2019/7/11
Y1 - 2019/7/11
N2 - In this manuscript, distinct approaches were used in order to obtain the best electrical power estimation from photovoltaic systems located at different selected places in Mexico. Multiple Linear Regression (MLR) and Gradient Descent Optimization (GDO) were applied as statistical methods and they were compared against an Adaptive Neuro-Fuzzy Inference System (ANFIS) as an intelligent technique. The data gathered involved solar radiation, outside temperature, wind speed, daylight hour and photovoltaic power; collected from on-site real-time measurements at Mexico City and Hermosillo City, Sonora State. According to our results, all three methods achieved satisfactory performances, since low values were obtained for the convergence error. The GDO improved the MLR results, minimizing the overall error percentage value from 7.2% to 6.9% for Sonora and from 2.0% to 1.9% for Mexico City; nonetheless, ANFIS overcomes both statistical methods, achieving a 5.8% error percentage value for Sonora and 1.6% for Mexico City. The results demonstrated an improvement by applying intelligent systems against statistical techniques achieving a lesser mean average error.
AB - In this manuscript, distinct approaches were used in order to obtain the best electrical power estimation from photovoltaic systems located at different selected places in Mexico. Multiple Linear Regression (MLR) and Gradient Descent Optimization (GDO) were applied as statistical methods and they were compared against an Adaptive Neuro-Fuzzy Inference System (ANFIS) as an intelligent technique. The data gathered involved solar radiation, outside temperature, wind speed, daylight hour and photovoltaic power; collected from on-site real-time measurements at Mexico City and Hermosillo City, Sonora State. According to our results, all three methods achieved satisfactory performances, since low values were obtained for the convergence error. The GDO improved the MLR results, minimizing the overall error percentage value from 7.2% to 6.9% for Sonora and from 2.0% to 1.9% for Mexico City; nonetheless, ANFIS overcomes both statistical methods, achieving a 5.8% error percentage value for Sonora and 1.6% for Mexico City. The results demonstrated an improvement by applying intelligent systems against statistical techniques achieving a lesser mean average error.
KW - ANFIS
KW - Gradient descent
KW - Photovoltaic system
KW - Statistical method
KW - Sustainable development
UR - https://doi.org/10.3390/en12142662
U2 - 10.3390/en12142662
DO - 10.3390/en12142662
M3 - Artículo
VL - 12
JO - Energies
JF - Energies
IS - 14
M1 - 2662
ER -