An artificial neural network to assess the impact of neighbouring photovoltaic systems in power forecasting in Utrecht, the Netherlands

RENEWABLE ENERGY

卷:85

Article

Vaz, A. G. R.^1,2  Elsinga, B.²  van Sark, W. G. J. H. M.²  Brito, M. C.³ 

[1] Univ Lisbon, Fac Ciencias, Dept Geog Engn, P-1749016 Lisbon, Portugal

[2] Univ Utrecht, Copernicus Inst Sustainable Dev, Energy & Resources, NL-3584 CS Utrecht, Netherlands

[3] Univ Lisbon, Fac Ciencias, Inst Dom Lutz, P-1749016 Lisbon, Portugal

关键词: Photovoltaics;    Artificial neural network;    NARX model;    Time series;    Forecasting;   

DOI  :  10.1016/j.renene.2015.06.061

来源: Elsevier

【 摘 要 】

In order to perform predictions of a photovoltaic (PV) system power production, a neural network architecture system using the Nonlinear Autoregressive with exogenous inputs (NARX) model is implemented using not only local meteorological data but also measurements of neighbouring PV systems as inputs. Input configurations are compared to assess the effects of the different inputs. The added value of the information of the neighbouring PV systems has demonstrated to further improve the accuracy of predictions for both winter and summer seasons. Additionally, forecasts up to 1 month are tested and compared with a persistence model. Normalized root mean square errors (nRMSE) ranged between 9% and 25%, with the NARX model clearly outperforming the persistence model for forecast horizons greater than 15 min. (C) 2015 Elsevier Ltd. All rights reserved.

【 授权许可】

Free