| Título: | An Improved Prediction Approach on Solar Irradiance of Photovoltaic Power Station |
| Autores: |
Dong, Haiying; School of Automation & Electrical Engineering, Lanzhou Jiao Tong University Yang, Lei; School of Automation & Electrical Engineering, Lanzhou Jiao Tong University Zhang, Shengrui; School of Automation & Electrical Engineering, Lanzhou Jiao Tong University Li, Yuan; School of Automation & Electrical Engineering, Lanzhou Jiao Tong University |
| Fecha: | 2013-09-26 |
| Publicador: | TELKOMNIKA: Indonesian journal of electrical engineering |
| Fuente: |
 |
| Tipo: |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
| Tema: |
Electrical; Artificial intelligence; Computer simulation photovoltaic power station; solar irradiance; prediction; wavelet decomposition; extreme learning machine (ELM) |
| Descripción: | Abstract Solar irradiance is the main factor which influences the photovoltaic output power. In order to predict the photovoltaic output power accurately, the prediction accuracy of irradiance should be improved. In terms of unsatisfactory prediction accuracy of irradiance of traditional photovoltaic power station, this paper presents an approach to predict solar irradiance of photovoltaic power station based on wavelet decomposition and extreme learning machine. In this method, the historical solar irradiance data is divided through the wavelet decomposition of three layers. Then the prediction models of irradiance are built based on the extreme learning machine. Finally, the solar irradiance is predicted with 15 minutes’ resolution one day ahead. With the decomposed components and the relative meteorological data as the input and the irradiance forecast data after wavelet reconstruction as the output. The simulation result coming from the actual measured data of a photovoltaic power station in Gansu province indicates that the proposed model is of higher accuracy in comparison with the traditional ones. |
| Idioma: | Inglés |