An ANFIS-Based Modeling Comparison Study for Photovoltaic Power at Different Geographical Places in Mexico
| Autor: | Fernando Arellano-Valmaña, Jesús Fernando Hinojosa-Palafox, Yasuhiro Matsumoto, Hussain Alazki, Jose A. Ruz-Hernandez, Enrique J. Herrera-López, Alejandro García-Juárez, Nun Pitalúa-Díaz, Ricardo Perez-Enciso, Enrique Fernando Velázquez-Contreras |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
statistical method
Control and Optimization 020209 energy Energy Engineering and Power Technology ANFIS gradient descent photovoltaic system sustainable development 02 engineering and technology 010501 environmental sciences lcsh:Technology 01 natural sciences Wind speed Statistics Linear regression 0202 electrical engineering electronic engineering information engineering Daylight Electrical and Electronic Engineering Engineering (miscellaneous) 0105 earth and related environmental sciences Mathematics Adaptive neuro fuzzy inference system lcsh:T Renewable Energy Sustainability and the Environment Photovoltaic system Intelligent decision support system Gradient descent Energy (miscellaneous) Arithmetic mean |
| Zdroj: | Energies; Volume 12; Issue 14; Pages: 2662 Energies, Vol 12, Iss 14, p 2662 (2019) |
| ISSN: | 1996-1073 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |