PV power forecasting using different Artificial Neural Networks strategies

Author

Sansa, Ines ; Missaoui, Sihem ; Boussada, Zina ; Bellaaj, Najiba Mrabet ; Ahmed, E.M. ; Orabi, Mohamed

Author_Institution

Lab. de Syst. Electr., Univ. de Tunis El Manar, Tunis, Tunisia

fYear

2014

fDate

25-27 March 2014

Firstpage

54

Lastpage

59

Abstract

The integration of photovoltaic (PV), intermittent and uncontrollable power, into the electrical grid has become one of the major challenges for power system operators. Therefore the PV power forecasting can be beneficial in system planning and balancing energies. In this paper the PV power forecasting of a real generator [1] is presented. Different Artificial Neural Networks (ANN) strategies are used to forecast the PV power from meteorological variables, the radiation and the temperature. Simulation results corresponding to each ANN strategy are presented, discussed and compared. The dynamic ANN chosen in this work is the Nonlinear Auto Regressive models with eXogenous input (NARX model). Its performances have proved in the different time frame PV power forecasting. The impact of season´s type on the efficiency of PV power forecasting is presented in the second part of this paper.

Keywords

load forecasting; neural nets; photovoltaic power systems; power engineering computing; power generation planning; power grids; ANN strategies; NARX model; PV power forecasting; artificial neural networks strategies; balancing energies; eXogenous input; electrical grid; nonlinear auto regressive models; photovoltaic power; power system operators; system planning; Artificial neural networks; Biological system modeling; Equations; Forecasting; Mathematical model; Predictive models; Weather forecasting; ANN; NARX model; PV power forecasting; model identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Green Energy, 2014 International Conference on

Conference_Location

Sfax

Print_ISBN

978-1-4799-3601-4

Type

conf

DOI

10.1109/ICGE.2014.6835397

Filename

6835397