Characterization and modeling of a grid-connected photovoltaic system using a Recurrent Neural Network
Authors:
- 1 July 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1761-1766
Abstract
Photovoltaic (PV) system modeling is used throughout the photovoltaic industry for the prediction of PV system output under a given set of weather conditions. PV system modeling has a wide range of uses including: prepurchase comparisons of PV system components, system health monitoring, and payback (return on investment) times. In order to adequately model a PV system, the system must be characterized to establish the relationship between given weather inputs (e.g., irradiance, spectrum, temperature) and desired system outputs (e.g., AC power, module temperature). Traditional approaches to system characterization involve characterizing and modeling each component in a PV system and forming a system model by successively using component models. This paper lays the groundwork for using a Recurrent Neural Network (RNN) to characterize and model an entire PV system without the need to characterize or model the individual system components. Input/output relationships are “learned” by the RNN using measured system performance data and correlated weather data. Thus, this method for characterizing and modeling PV systems is useful for existing PV system installations with several weeks of correlated system performance and weather data.Keywords
This publication has 8 references indexed in Scilit:
- Performance prediction of 20kWp grid-connected photovoltaic plant at Trieste (Italy) using artificial neural networkEnergy Conversion and Management, 2010
- Estimation of the energy of a PV generator using artificial neural networkRenewable Energy, 2009
- Performance evaluation of solar photovoltaic arrays including shadow effects using neural network2009
- Characterisation of Si-crystalline PV modules by artificial neural networksRenewable Energy, 2009
- Empirical study of a hybrid algorithm based on Clonal Selection and Small Population Based PSO2008
- Comparison of PV system performance-model predictions with measured PV system performance2008 33rd IEEE Photovolatic Specialists Conference, 2008
- Improvement and validation of a model for photovoltaic array performanceSolar Energy, 2006
- Artificial neural networks in renewable energy systems applications: a reviewRenewable and Sustainable Energy Reviews, 2001