Comparison of Three Short Term Photovoltaic System Power Generation Forecasting Methods

Abstract:

An accurate forecasting method for solar power generation of the photovoltaic (PV) system is urgent needed under the relevant issues associated with the high penetration of solar power in the electricity system. This paper presents a comparison of three forecasting approaches on short term solar power generation of PV system. Three forecasting methods, namely, persistence method, back propagation neural network method, and radial basis function (RBF) neural network method, are investigated. To demonstrate the performance of three methods, the methods are tested on the practical information of solar power generation of a PV system. The performance is evaluated based on two indexes, namely, maximum absolute percent error and mean absolute percent error.

• Periodical: Applied Mechanics and Materials (Volumes 479-480)
• Pages: 585-589
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.479-480.585
• Online since: December 2013
• Authors: Wen Yeau Chang
• Keywords: Back Propagation (BP) Neural Network, Persistence Method, Photovoltaic (PV) System, Radial Basis Function Neural Network, Solar Power Generation Forecasting

References

[1] J. Bing, O. Bartholomy and P. Krishnani, in: Validation of Solar PV Power Forecasting Methods for High Penetration Grid Integration, Proceedings of the 2012 IEEE Power and Energy Society General Meeting, (2012) July 22-26, San Diego, USA.

DOI: 10.1109/pesgm.2012.6345562

[2] W.Y. Chang: Advanced Materials Research, Vol. 684 (2013), p.671.

[3] Y. Huang, J. Lu, C. Liu, X. Xu, W.S. Wang and X. Zhou, in: Comparative Study of Power Forecasting Methods for PV Stations, Proceedings of the 2010 International Conference on Power System Technology, (2010) October 24-28, Hangzhou, China.

DOI: 10.1109/powercon.2010.5666688

[4] P. Bacher, H. Madsen and H.A. Nielsen: Solar Energy Vol. 83 (2009), p.1772.

[5] H.T.C. Pedro and C.F.M. Coimbra: Solar Energy Vol. 86 (2012), p. (2017).

[6] C. Chen, S. Duan, T. Cai and B. Liu: Solar Energy Vol. 85 (2011), p.2856.

[7] Y.Z. Li, R. Luan and J.C. Niu, in: Forecast of Power Generation for Grid-Connected Photovoltaic System Based on Grey Model and Markov Chain, Proceedings of the 3rd IEEE Conference on Industrial Electronics and Applications, (2008).

DOI: 10.1109/iciea.2008.4582816

[8] L. Chen and X. Lai, in: Comparison between ARIMA and ANN models used in short-term wind speed forecasting, Proceedings of the 2011 Asia-Pacific Power and Energy Engineering Conference, (2011) March 25-28, Wuhan, China.

DOI: 10.1109/appeec.2011.5748446

[9] W.Y. Chang: International Journal of Digital Content Technology and Its Application Vol. 7 (2013), p.502.

[10] G. Li and J. Shi: Applied Energy Vol. 87 (2010), p.2313.

[11] W.Y. Chang: Journal of Applied Mathematics Vol. 2013 (2013), Article ID 971389.