Estimation of Hourly Solar Radiations on Horizontal Surface from Daily Average Solar Radiations Using Artificial Neural Network

Adi Kurniawan, Eiji Shintaku


Hourly solar radiation information is necessary to increase the effectiveness of photovoltaic (PV) energy systems. However, compared with daily average solar radiation, the measurement of hourly solar radiation is much less available. In this study, a multilayer perceptron artificial neural network based on daily average solar radiation is proposed to estimate the amount of hourly solar radiation. The proposed method also relies on the location of the PV system, the hour when the estimate is needed, and the month when the estimate is needed. Two separate networks were built to estimate hourly direct solar radiation and hourly diffuse solar radiation, the summation of which is the estimated value of global hourly solar radiation. The networks were trained using three years of data from 2016 to 2018 from five locations around Japan. The data were taken from the website of the Japan Meteorological Agency (JMA). The number of hidden neurons for each network was determined by comparing the regression value obtained during the training process. The proposed method was validated by comparing the estimated value with the actual measured solar radiation value for each month in 2019 for the same five locations used for training the networks. The reliability of the proposed method was confirmed with the minimum R2 of 0.951 for the estimation of hourly direct solar radiation and 0.983 for hourly diffuse solar radiation. Further improvement in the accuracy of estimating the daily peak radiation value is considered to improve the total accuracy of the estimation model in the future.


Diffuse solar radiation; direct solar radiation; global solar radiation; multilayer perceptron; renewable energy; solar energy forecasting.

Full Text:



G. Weissman, R. Sargent, and B. Fanshaw, “Renewables on the Rise 2018,†Environment America Research & Policy Center, 2017.

A. Kurniawan and E. Shintaku, “Control of photovoltaic system connected to DC bus in all-electric ship,†in The 2nd International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation, 2018, pp. 110–115. doi: 10.1109/ICAMIMIA.2017.8387568.

M. R. Arsalan, S. Sarwito, and E. S. Koenhardono, “Planning an on-grid solar energy generation system for the Dwimatama pier at Tanjung Emas port,†IOP Conf Ser Earth Environ Sci, vol. 1081, no. 1, p. 012019, Sep. 2022, doi: 10.1088/1755-1315/1081/1/012019.

E. Koenhardono, D. Putri, and I. Kusuma, “Application of Hybrid Power Generation System on a Tanker Ship to Support the Development of Eco Ship Technology,†IOP Conf Ser Earth Environ Sci, vol. 1081, no. 1, p. 012053, Sep. 2022, doi: 10.1088/1755-1315/1081/1/012053.

E. Setyo Koenhardono et al., “Development of ecotourism floating restaurant in Surabaya City,†in MATEC Web of Conferences, Jul. 2018, vol. 177. doi: 10.1051/matecconf/201817701010.

I. R. Kusuma, Semin, M. B. Zaman, and E. S. Koenhardono, “Load Flow Simulation of Radial Shipboard Network Structure with Direct Current Distribution Systems,†in IOP Conference Series: Earth and Environmental Science, Feb. 2022, vol. 972, no. 1. doi: 10.1088/1755-1315/972/1/012038.

A. Kurniawan, E. S. Koenhardono, A. A. Masroeri, S. Sarwito, and A. Santoso, “Optimizing Solar-Powered Tourist Boat with Converter-Based Maximum Power Point Tracker,†International Journal of Applied Engineering Research, vol. 11, no. 23, pp. 11142–11144, 2016.

A. Kurniawan and E. Shintaku, “A Neural Network-Based Rapid Maximum Power Point Tracking Method for Photovoltaic Systems in Partial Shading Conditions,†Applied Solar Energy, vol. 56, no. 3, pp. 157–167, 2020, doi: 10.3103/S0003701X20030068.

A. Calcabrini, H. Ziar, O. Isabella, and M. Zeman, “A simplified skyline-based method for estimating the annual solar energy potential in urban environments,†Nat Energy, vol. 4, no. 3, pp. 206–215, 2019, doi: 10.1038/s41560-018-0318-6.

C. Yao, M. Chen, and Y.-Y. Hong, “Novel Adaptive Multi-Clustering Algorithm-Based Optimal ESS Sizing in Ship Power System Considering Uncertainty,†IEEE Transactions on Power Systems, vol. 33, no. 1, pp. 307–316, 2017, doi: 10.1109/tpwrs.2017.2695339.

M. Marzouq, H. el Fadili, Z. Lakhliai, and K. Zenkouar, “A review of solar radiation prediction using artificial neural networks,†in International Conference on Wireless Technologies, Embedded and Intelligent Systems, 2017. doi: 10.1109/WITS.2017.7934658.

A. N. Azmi, N. Bin Salim, and A. B. Khamis, “Analysis of an energy storage sizing for grid-connected photovoltaic system,†Indonesian Journal of Electrical Engineering and Computer Science, vol. 16, no. 1, pp. 17–24, 2019, doi: 10.11591/ijeecs.v16.i1.pp17-24.

D. Yanti, “The use of solar cell in ground water irrigation to support agricultural cultivation in rainfed field,†Int J Adv Sci Eng Inf Technol, vol. 6, no. 1, pp. 112–115, 2016, doi: 10.18517/ijaseit.6.1.677.

A. Kurniawan and E. Shintaku, “Determining the optimal inclination and orientation angles of solar panels installed on ship,†International Journal of Renewable Energy Research, vol. 10, no. 1, pp. 45–53, 2020.

B. Setiawan, M. Hery Purnomo, and M. Ashari, “A High Precision Angle Compensation Controller For Dish Solar Tracker installed on a Moving Large Ship,†2013.

A. Kurniawan and E. Shintaku, “Estimation of the Monthly Global , Direct , and Diffuse Solar Radiation in Japan Using Artificial Neural Network,†Int J Mach Learn Comput, vol. 10, no. 1, 2020.

J. Zeng and W. Qiao, “Short-term solar power prediction using a support vector machine,†Renew Energy, vol. 52, pp. 118–127, 2013, doi: 10.1016/j.renene.2012.10.009.

P. F. Jiménez-Pérez and L. Mora-López, “Modeling and forecasting hourly global solar radiation using clustering and classification techniques,†Solar Energy, vol. 135, pp. 682–691, 2016, doi: 10.1016/j.solener.2016.06.039.

E. Paulescu and R. Blaga, “Regression models for hourly diffuse solar radiation,†Solar Energy, vol. 125, pp. 111–124, 2016, doi: 10.1016/j.solener.2015.11.044.

D. H. W. Li, W. Chen, S. Li, and S. Lou, “Estimation of hourly global solar radiation using Multivariate Adaptive Regression Spline (MARS) – A case study of Hong Kong,†Energy, vol. 186, p. 115857, 2019, doi: 10.1016/

M. H. Hakemzadeh, A. Shavalipour, K. Sopian, and S. H. Zaidi, “An investigation of modelling diffuse solar radiation under tropical climatic conditions,†International Journal of Renewable Energy Research, vol. 10, no. 1, pp. 499–511, 2020.

B. Mohammadi and Z. Aghashariatmadari, “Estimation of solar radiation using neighboring stations through hybrid support vector regression boosted by Krill Herd algorithm,†Arabian Journal of Geosciences, vol. 13, no. 10, pp. 1–16, 2020, doi: 10.1007/s12517-020-05355-1.

N. Abdelhafidi, N. E. I. Bachari, and Z. Abdelhafidi, “Estimation of solar radiation using stepwise multiple linear regression with principal component analysis in Algeria,†Meteorology and Atmospheric Physics, 2020, doi: 10.1007/s00703-020-00739-0.

D. Munandar, “Multilayer perceptron (MLP) and autoregressive integrated moving average (ARIMA) models in multivariate input time series data: Solar irradiance forecasting,†Int J Adv Sci Eng Inf Technol, vol. 9, no. 1, pp. 220–228, 2019, doi: 10.18517/ijaseit.9.1.6426.

A. Khosravi, R. N. N. Koury, L. Machado, and J. J. G. Pabon, “Prediction of hourly solar radiation in Abu Musa Island using machine learning algorithms,†J Clean Prod, vol. 176, pp. 63–75, 2018, doi: 10.1016/j.jclepro.2017.12.065.

G. Notton, C. Voyant, A. Fouilloy, J. L. Duchaud, and M. L. Nivet, “Some applications of ANN to solar radiation estimation and forecasting for energy applications,†Applied Sciences (Switzerland), vol. 9, no. 1, 2019, doi: 10.3390/app9010209.

F. O. Hocaoglu and F. Serttas, “A novel hybrid (Mycielski-Markov) model for hourly solar radiation forecasting,†Renew Energy, vol. 108, pp. 635–643, 2017, doi: 10.1016/j.renene.2016.08.058.

A. Kurniawan and E. Shintaku, “Two-step artificial neural network to estimate the solar radiation at Java Island,†International Journal of Electrical and Computer Engineering, vol. 11, no. 4, 2021, doi: 10.11591/ijece.v9i4.ppxx-xx.

A. Kurniawan and A. Harumwidiah, “An evaluation of the artificial neural network based on the estimation of daily average global solar radiation in the city of Surabaya,†Indonesian Journal of Electrical Engineering and Computer Science, vol. 22, no. 3, pp. 1245–1250, Jun. 2021, doi: 10.11591/ijeecs.v22.i3.pp1245-1250.

S. A. M. Maleki, H. Hizam, and C. Gomes, “Estimation of hourly, daily and monthly global solar radiation on inclined surfaces: Models re-visited,†Energies (Basel), vol. 10, no. 1, 2017, doi: 10.3390/en10010134.



  • There are currently no refbacks.

Published by INSIGHT - Indonesian Society for Knowledge and Human Development