Evaluating Solar Prediction Methods to Improve PV Micro-grid Effectiveness Using Nonlinear Autoregressive Exogenous Neural Network (NARX NN)
- 14 Downloads
In recent years, insufficient access to energy and environmental challenges caused the push for clean and sustainable means of power generation. The integration of renewable energy resources into the electricity grid is known to reduce Greenhouse Gas (GHG) emissions and environmental pollution. Solar power has the enormous benefit of availability and can often be accessed cost effectively. However, there is a recurring problem of intermittency and variability in most solar power generation systems. The variability and intermittent nature of solar power sources introduce significant challenges in the planning and scheduling of smart grids. Solar power prediction can mitigate this variability and improve the integration of solar power resources into smart grids. This paper presents an Artificial Neural Network (ANN) model for solar power prediction, and assesses how several weather input variables from Leeds, UK, affect the prediction accuracy. Following this, the Nonlinear Autoregressive Exogenous Neural Network (NARX NN) model performance is compared with Nonlinear Autoregressive Neural Network (NAR NN) model using a time series modelling approach. The result shows that NARX NN model outperformed NAR NN model for the studied geographical location.
KeywordsNonlinear autoregressive NARX NN and NAR NN Models Prediction Performance comparison
- Chen, X., Du, Y., Xiao, W., & Lu, S., 2017. Power ramp-rate control based on power forecasting for PV grid-tied systems with minimum energy storage. IEEE Conference 2017.Google Scholar
- GlobalData. (2017). Global PV capacity is expected to reach 969GW by 2025. Power Technology.Google Scholar
- Gurney, K. (1997). An introduction to neural networks. ROUTLEDGE, UCL Press Limited 11 New Fetter Lane London EC4P 4EE, UCL Press Limited is an imprint of the Taylor & Francis Group, Record Number: 163. https://www.inf.ed.ac.uk/teaching/courses/nlu/assets/reading/Gurney_et_al.pdf.
- Haykin, S. (2005). Neural Network: A Comprehensive Foundation, Pearson Education (Singapore) Pte. Ltd., Indian Branch, 482 F. I. E. Patparganj Delhi 110092, India, Pearson Prentice Hall.Google Scholar
- IEA. (2015). Energy from the desert: Very large scale PV power plants for shifting to renewable energy future. International Energy Agency Photovoltaic Power Systems Program.Google Scholar
- IEA. (2018). Electricity generation from renewables by source World 1990–2016. International Energy Agency. Key World Energy Statistics 2018Google Scholar
- IRENA. (2017). Renewable energy: A key climate solution. International Renewable Energy Agency.Google Scholar
- IRENA. (2019). Innovation landscape for a renewable-powered future: Solutions to integrate variable renewables. International Renewable Energy Agency, Abu Dhabi.Google Scholar
- Kalogirou. (2000). Applications of artificial neural-networks for energy systems. Applied Energy, 67(1–2), 17–35.Google Scholar
- Mitchell, T. M. (1997). Machine learning, McGraw-Hill Science/Engineering/Math. Retrieved from https://www.cs.ubbcluj.ro/~gabis/ml/ml-books/McGrawHill%20-%20Machine%20Learning%20-Tom%20Mitchell.pdf.
- Mohammed, L. B., Hamdan, M. A., & Abdelhafez, E. A. (2013). Hourly solar radiation prediction based on Nonlinear Autoregressive Exogenous (Narx) neural network. Jordan Journal of Mechanical and Industrial Engineering, 7, 11–18.Google Scholar
- Nagelkerke, N. J. D. (1991). A note on a general definition of the coefficient of determination. Retrieved from http://www.cesarzamudio.com/uploads/1/7/9/1/17916581/nagelkerke_n.j.d._1991_-_a_note_on_a_general_definition_of_the_coefficient_of_determination.pdf. Biometrika trust http://links.jstor.org/sici?sici=0006-3444%28199109%2978%3A3%3C691%3AANOAGD%3E2.0.CO%3B2-V.
- Nuchhi, S. S., Sali, R. B., & Ankaliki, S. G. (2013). Effect of reactive power compensation on voltage profile. International Journal of Engineering Research and Technology, 2(6), 2627.Google Scholar
- Pelland, S., Galanis, G., & Kallos, G. (2011). Solar and photovoltaic forecasting through post- processing of the Global Environmental Multiscale numerical weather prediction model. Progress in Photovoltaics: Research and Applications, 21(3). https://doi.org/10.1002/pip.1180
- Siegelman & Sontag. (1992). On the computational power of neural nets. In Proceedings of the fifth annual workshop on Computational learning theory. ACM conference Proceedings, 440–449.Google Scholar
- Tanti, T. (2018). The key trends that will shape renewable energy in 2018 and beyond. World Economic Forum.Google Scholar
- Vernier. (2001). What are mean squared error and root mean squared error? Beaverton, OR: Vernier Software & Technology. Retrieved from https://www.vernier.com/til/1014/.Google Scholar
- WEO. (2019). World Energy Outlook 2017: A world in transformation. IEA.Google Scholar