Owing to its essential contribution to the production of environmentally sustainable energy sources, the issue of renewables has captured the world's attention. Solar energy is one of the sources used to produce renewable energy. Solar irradiation estimation is a critical component for renewable energy systems such as photovoltaic (PV) systems to be built. It may also help reduce energy costs and provide high energy quality in distributed solar photovoltaic generation electricity grids.
Thus, this study aims to forecast one-step and multi-step solar irradiation ahead. The effect of weather conditions plays a significant role in helping to predict solar irradiation. Besides, much of the analysis focuses on minimizing the Mean Absolute Percentage Error. Yet, depending on the prediction model's reliability based on the error calculation and a closer look deep down into the data, there was still a weakness.
This research's results are suggested scenarios to find a system based on the short-term horizon for forecasting solar irradiance. As the error target is below 8 percent, the error for solar irradiance prediction is generally correct. The granularity of the prediction data affects the probability of error values being obtained by prediction. The classification used was based on the month in this report. The average of each month's prediction MAPE was 5.8%.
Proposing a pragmatic way in doing error analysis by comparing several error approaches and data volatility to deepen the analysis. Moving average proven could improve prediction accuracy because it may help capture the dramatic change of the data. In future research, more factors should be considered to capture hidden behavior.

REFERENCES

[1] "Renewables 2019." International Energy Agency. https://www.iea.org/reports/renewables-2019/power (accessed November 30, 2020).
[2] "Taiwan to boost renewable energy to 20% by 2025, introduce trillion-dollar investment." Taiwan News. https://www.taiwannews.com.tw/en/news/3880997 (accessed December 1, 2020).
[3] "Global Energy Outlook: ," in "Energy Transition or Energy Addition?," Resources for the Future, 2020. [Online]. Available: www.eef.org/geo
[4] "Renewables 2020 Global Status Report," REN 21, 2020. [Online]. Available: ren21.net/gsr-2020/
[5] Z. X. Fei Wang, Zhao Zhena, Yu Lie, Kangping Lia, Liqiang Zhaof, Miadreza Shafie-khahh, João P.S. Catalãoi, "A minutely solar irradiance forecasting method based on real-time sky image-irradiance mapping model," Energy Conversion and Management, vol. 220, 2020.
[6] S. K.-K. Sobrina Sobria, Nasrudin Abd. Rahima, "Solar photovoltaic generation forecasting methods: A review," Energy Conversion and Management, vol. 156, pp. 459-497, 2018.
[7] L. N. Amanpreet Kaur, Hugo T.C. Pedro, Carlos F.M. Coimbra, "Benefits of solar forecasting for energy imbalance markets," Renewable Energy, vol. 86, p. 819e830, 2016.
[8] M. N. Muhammad Qamar Raza, Chandima Ekanayake, "On recent advances in PV output power forecast," Solar Energy, vol. 136, pp. 125–144, 2016.
[9] J. Z. Can Wan, Yonghua Song, Zhao Xu, Jin Lin, Zechun Hu, "Photovoltaic and Solar Power Forecasting for Smart Grid Energy Management," JOURNAL OF POWER AND ENERGY SYSTEMS, vol. 1, pp. 38-45, 2015.
[10] M. H. R. Nasrin, N. A. Rahim, "Effect of high irradiation on photovoltaic power and energy," International Journal of Energy Research, 2017.
[11] "30 Innovative Solutions Show Path to Renewable-Powered Future." International Renewable Energy Agency (IRENA). https://www.irena.org/newsroom/articles/2020/Jul/30-Innovative-Solutions-Show-Path-to-Renewable-Powered-Future (accessed December 15, 2020).
[12] "Solar is now the most popular form of new electricity generation worldwide." The Conversation. https://theconversation.com/solar-is-now-the-most-popular-form-of-new-electricity-generation-worldwide-81678 (accessed December 15, 2020).
[13] R. R.-I. Abdul Muhaimin Ismail, Muhammad Asifb, Abu Bakar Munir, Firdaus Muhammad-Sukki "Progress of solar photovoltaic in ASEAN countries: A review," Renewable and Sustainable Energy Reviews, vol. 48, pp. 399–412, 2015.
[14] "RENEWABLES 2016 GLOBAL STATUS REPORT," Renewable Energy Policy Network for the 21st Century (REN21), 2016.
[15] I. E. A. I. PVPS, "TRENDS 2016 IN PHOTOVOLTAIC APPLICATIONS," 2016.
[16] S. F. Giorgio Graditi, Giovanna Adinolfi, Giuseppe Marco Tina, Cristina Ventura, "Energy yield estimation of thin-film photovoltaic plants by using physical approach and artificial neural networks," Solar Energy, vol. 130, pp. 232–243, 2016.
[17] I. M. Manoja Kumar Behera, Niranjan Nayak "Solar photovoltaic power forecasting using optimized modified extreme learning machine technique," Engineering Science and Technology, an International Journal, vol. 21, pp. 428–438, 2018.
[18] N. M. Rakibuzzaman Shah, R.C. Bansal, V.K. Ramachandaramurthy "A review of key power system stability challenges forlarge-scale PV integration," Renewable and Sustainable Energy Reviews, vol. 41, pp. 1423–1436, 2015.
[19] N. A. R. Sam Koohi-Kamalі, H. Mokhlis, V.V. Tyagi, "Photovoltaic electricity generator dynamic modeling methods for smart grid applications: A review," Renewable and Sustainable Energy Reviews, vol. 57, pp. 131–172, 2016.
[20] K. V. Vidyanandan, "An Overview of Factors Affecting the Performance of Solar PV Systems," Power Management Institute, NTPC Ltd., NOIDA, India., 2017. [Online]. Available: https://www.researchgate.net/publication/319165448
[21] J.-F. C. Na Dong, Ai-Guo Wu, Zhong-Ke Gao, "A novel convolutional neural network framework based solar irradiance prediction method," Electrical Power and Energy Systems, vol. 114, p. 105411, 2020.
[22] Y. N. Xiangyun Qing, "Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM," Energy, vol. 148, pp. 461-468, 2018.
[23] G. E. Vahid Nourani, Jazuli Abdullahi, and Ala Tahsin, "Multi-region Modeling of Daily Global Solar Radiation with Artificial Intelligence Ensemble," Natural Resources Research, vol. 28, pp. 1218-1237, 2019.
[24] K. A. Yoshito Hirata, "Improving time series prediction of solar irradiance after sunrise: Comparison among three methods for time series prediction," Solar Energy, vol. 149, pp. 294-301, 2017.
[25] R. C. D. Sujan Ghimirea, Nawin Raja, Jianchun Mib, "Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms," Applied Energy, vol. 253, 2019.
[26] M. O. Badr Benamrou , Imane Allaouzi , Mohamed Ben Ahmed, "A Proposed Model to Forecast Hourly Global Solar Irradiation Based on Satellite Derived Data, Deep Learning and Machine Learning Approaches," Journal of Ecological Engineering, vol. 21, no. 4, pp. 26-38, 2020.
[27] F. N. Zhihong Pang, Zheng O’Neill, "Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons," Renewable Energy, vol. 156, p. 279e289, 2020.
[28] A. Rutherford, Introducing ANOVA and ANCOVA: a GLM approach. Sage, 2001.
[29] J.-B. Du Prel, G. Hommel, B. Röhrig, and M. Blettner, "Confidence interval or p-value?: part 4 of a series on evaluation of scientific publications," Deutsches Ärzteblatt International, vol. 106, no. 19, p. 335, 2009.
[30] F. Chollet, Deep Learning with Python. New York: Manning Publications Co., 2018.
[31] J. R. S. Brownson, "Chapter 08 - Measure and Estimation of the Solar Resource," in Solar Energy Conversion Systems
Elsevier, 2014.
[32] "North Carolina Climate Office." https://climate.ncsu.edu/edu/Humidity (accessed December 31, , 2020).