Ann-based model with adaptive observation system for estimation solar irradiance and illuminance on horizontal surface

Article Sidebar

PDF
Published: Dec 20, 2018
Keywords:
All skies condition Expert system Artificial Neural Network

Main Article Content

S. Hongkong
Intelligent Artificial and Innovation ResearchUnit, Mechanical engineering, Faculty of industrial and technology, Rajamangala University of Technology Isan Sakonnakhon Campus, Sakonnakhon 47160, Thailand

Abstract

Continuous prediction of solar energy for designing has important. This article presented an estimation solar irradiance and illuminance on a horizontal surface by using artificial neural network (ANN) with the adaptive observation system (AOS). The AOS was detection system of inputs available for predicting, which consist of sky ratio and solar altitude angle. The sky ratio (SR) was using electronic circuit for detection. The solar altitude angle (α) calculate from sun position at latitude and longitude of a location with solar time. The 2-inputs (SR, α) and 4-outputs (Eeg, Eed, Evg, Evd) of solar irradiance and illuminance had been trained in ANN model. The feed-forward neural network with the back-propagation (BP) training algorithm was used train the model with 10 neurons, one hidden layer. The result shown comparison between estimation and measured by use MBD, RMSD and R2. The AOS is a novel technique for predicting and can be predicted solar quality whit out expensive instrument.

Article Details

How to Cite
Hongkong, S. (2018). Ann-based model with adaptive observation system for estimation solar irradiance and illuminance on horizontal surface. Journal of Research and Applications in Mechanical Engineering, 6(2), 82–94. Retrieved from https://ph01.tci-thaijo.org/index.php/jrame/article/view/141598
Issue
Vol. 6 No. 2 (2018)
Section
RESEARCH ARTICLES

by-nc-sa

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

References

[1] Angström, A. On the computation of global radiation from records of sunshine. Arkiv Geof., Vol. 2, 1956, pp. 471-479.

[2] Behrang, M.A., Assareh, E., Ghanbarzadeh, A. and Noghrehabadi, A.R. The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data. Solar Energy, Vol. 84(8), 2010, pp. 1468-1480.

[3] Voyant, C., Muselli, M., Paoli, C. and Nivet, M.L. Optimization of an artificial neural network dedicated to the multivariate forecasting of daily global radiation. Energy, Vol. 36(1), 2011, pp. 348-359.

[4] Janjai, S. and Plaon, P. Estimation of sky luminance in the tropics using artificial neural networks: Modeling and performance comparison with the CIE model. Applied Energy, Vol. 88(3), 2011, pp. 840-847.

[5] Koca, A., Oztop, H.F., Varol, Y. and Koca, G.O. Estimation of solar radiation using artificial neural networks with different input parameters for Mediterranean region of Anatolia in Turkey. Expert Systems with Applications, Vol. 38(7), 2011, pp. 8756-8762.

[6] Hasni, A., Sehli, A., Draoui, B., Bassou, A. and Amieur B. Estimating global solar radiation using artificial neural network and climate data in the south-western region of Algeria. Energy Procedia, Vol. 18, 2012, pp. 531-537.

[7] Notton , G., Paoli, C., Vasileva, S., Nivet, M.L., Canaletti, J.L. and Cristofari, C. Estimation of hourly global solar irradiation on tilted planes from horizontal one using artificial neural networks. Energy, Vol. 39(1), 2012, pp. 166-179.

[8] Benghanem, M., Mellit, A. and Al amri, S.N. ANN-based modelling and estimation of daily global solar radiation data: A case study. Energy Conversion and Management, Vol. 50(7), 2009, pp. 1644-1655.

[9] Shafiqur, R. and Mohamed, M. Artificial neural network estimation of global solar radiation using air temperature and relative humidity. Energy Policy, Vol. 36(2), 2008, pp. 571-576.

[10] Kumar, S. and Kaur, T. Development of ANN based model for solar potential assessment using various meteorological parameters. Energy Procedia, Vol. 90, 2016, pp. 587-592.

[11] Sivaneasan, B., Yu, C.Y. and Goh, K.P. Solar forecasting using ANN with Fuzzy Logic pre-processing. Energy procedia, Vol. 143, 2017, pp. 727-732.

[12] Siva Krishna Rao K, D.V., Premalatha, M. and Naveen, C. Analysis of different combinations of meteorological parameters in predicting the horizontal global solar radiation with ANN approach: A case study. Renewable and Sustainable Energy Reviews, Vol. 91, 2018, pp. 248-258.

[13] Commission International de I’Eclairage. Spatial distribution of daylight-CIE standard overcast sky and clear sky, Publication CIE S003/E-1996, 1996, CIE Central Bureau, Vienna.

[14] Benali, L., Notton, G., Fouilloy, A., Voyant, C. and Dizene, R. Solar radiation forecasting using artificial neural network and random forest methods: Application to normal beam, horizontal diffuse and global components. Renewable Energy, Vol. 132, 2019. pp. 871-884.

[15] Neelamegam, P. and Amirtham, V.A. Prediction of solar radiation for solar systems by using ANN models with different back propagation algorithms. Journal of Applied Research and Technology, Vol. 14, 2016, pp. 206-214.

[16] Ramli Rahim, B. and Rosady, M. Classification of daylight and radiation data into three sky conditions by sky ratio and sunshine duration. Energy and Buildings, Vol. 36, 2004, pp. 660-666.

[17] Pattanasethanon, S., Lertsatitthana-korn, C., Atthajariyakul, S. and Soponronnarit, S. All sky modeling daylight availability and illuminance/irradiance on horizontal plane for Mahasarakham, Thailand. Energy Conversion and Management, Vol. 48, 2007, pp. 1601-1614.

[18] Kittler, R. and Darula, S. Determination of time and sun position system. Solar Energy, Vol. 93, 2013, pp. 72-79.