Global solar irradiance is one of the main significant factors for designing and considering the volume of any solar station beside of it is usage in agricultural and building issue. Due of lack a precise information about the irradiance in Iraq metr
DOI:
https://doi.org/10.21271/ZJPAS.33.5.5Keywords:
Renewable energy, Solar system, Artificial neural network, Prediction.Abstract
Global solar irradiance is one of the main significant factors for designing and considering the volume of any solar station beside of it is usage in agricultural and building issue. Due of lack a precise information about the irradiance in Iraq metrological organization and seismology, this study is aimed to adopt the historical global data, build numerical analysis via using artificial neural network and predicting hourly irradiance. The test is applied over three locations Erbil, Bagdad, and Basra for being references to their closest locations. A foreword neural network (FNN) is the learning algorithm that is used in this study with relying on seven input variables consisting of Temperature, Precipitation, Humidity, Wind speed, Wind direction Sunshine duration and Date. After normalizing and standardizing data, an iteration method is used for determining the optimum number of neuron(s) in a hidden layer. It yields a least Root Mean square error (RMSE) between 2.5 to 3. The computed correlation coefficients are between 0.94 -0.96 for the mentioned locations.
References
Adel, M. (2008). Artificial Intelligence technique for modelling and forecasting of solar radiation data: a review. Int. J. Artificial Intelligence and Soft Computing.
Adel, M., & Alessandro, M. P. (2010). A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste. ELSEVIER.
Adel, M., & Soteris, A. K. (2008). Artificial intelligence techniques for photovoltaic applications: A review. ELSEVIER.
Alzahrani, A., Kimball, J., & Dagli, C. (2014). Predicting Solar Irradiance Using Time Series Neural Networks. ELSEVIER.
Chiteka, K., & Enweremadu, C. (2016). Prediction of global horizontal solar irradiance in Zimbabwe using artificial neural networks. ELSEVIER.
David, E., Gerrit, H., & R.W., M. (1994). Development of a neural network model to predict daily solar radiation. ELSEVIER.
Jinchuan, K., & Xinzhe, L. (2008). Empirical Analysis of Optimal Hidden Neurons in Neural Network Modeling for Stock Prediction. IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application.
Kais, J. A.-J., Munya, F. A.-Z., & Zahraa, S. M. (2012). Estimation of clear sky hourly global solar radiation in Iraq. INTERNATIONAL JOURNAL OF ENERGY AND ENVIRONMENT.
Kevin, L. P., & Paul, E. K. (2005). Artificial neural networks : an introduction. The Society of Photo-Optical Instrumentation Engineers.
meteoblue. (2006). Retrieved from https://www.meteoblue.com/en/weather/week/basra_iraq_99532
Michael, N. (2011). Artificial Intelligence: A Guide to Intelligent Systems. Pearson Education Canada.
Mubiru, J., & Banda, E. (2007). Estimation of monthly average daily global solar irradiation. elsevier.
Negnevitsky, M. (2002). Artificail intelligence a guide of intelligent system. Pearson.
S., R., & M., M. (2009). Estimation of Diffuse Fraction of Global Solar Radiation Using Artificial Neural Networks. Taylor & Francis Group, LLC.
Toolbox, S. M. (2019). MATLAB. Retrieved from Mathworks Inc.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2021 Zana Saleem Mohammed1, Gzing Adil Mohammed
This work is licensed under a Creative Commons Attribution 4.0 International License.
