Evaluation of Machine Learning Techniques for Solar Photovoltaic Power Output Forecasting in a Tropical Climate
Abstract
Solar energy has been increasingly integrated into power grid systems in developed countries such as Australia, Japan, Italy and United States thanks to the advancement of photovoltaic (PV) technologies and the acceptance through government policies. As PV power plants are widely integrated into conventional grid systems, the task of managing and maintaining the power system has become even more significantly challenging than before. Thus, a forecasting method is needed to improve the controllability and stability of PV power system performance and also to ensure a reliable and cost saving energy management of the power grid operations. A PV power output prediction models are developed in this project using several machine learning techniques which could be used to predict hourly PV power output using machine learning algorithms such as linear regression, Support Vector Machines (SVM) and Gaussian Process Regression (GPR). The data for variables are taken from Solar Lab of Faculty of Electrical Engineering (FKE) in Universiti Teknikal Malaysia Melaka (UTeM). The prediction models are designed, trained and tested using regression learner application in MATLAB software version R2017b. Based on the results, complex regression models such as the Exponential GPR is more accurate compared to a linear regression models such as the Interactions Linear Regression model overall. Additionally, the accuracy of these regression models can be further improved by excluding certain variables from being trained in the regression learner that may have an impact on the prediction models.
Downloads
References
A. Yona, T. Senjyu, A. Y. Saber, T. Funabashi, H. Sekine, and C. H. Kim, “Application of neural network to one-day-ahead 24 hours generating power forecasting for photovoltaic system,” 2007 Int. Conf. Intell. Syst. Appl. to Power Syst. ISAP, pp. 442–447, 2007.
Z. Li, S. M. Mahbobur Rahman, R. Vega, and B. Dong, “A hierarchical approach using machine learning methods in solar photovoltaic energy production forecasting,” Energies, vol. 9, no. 1, 2016.
A. Dolara, F. Grimaccia, S. Leva, M. Mussetta, and E. Ogliari, “A physical hybrid artificial neural network for short term forecasting of PV plant power output,” Energies, vol. 8, no. 2, pp. 1138–1153, 2015.
F. Grimaccia, S. Leva, M. Mussetta, and E. Ogliari, “ANN sizing procedure for the day-ahead output power forecast of a PV plant,” Appl. Sci., vol. 7, no. 6, 2017.
F. Grimaccia, S. Leva, M. Mussetta, and E. Ogliari, “Analysis and Validation of ANN PV Power Output Forecasting At 24 Hours Ahead,” ElectrIMACS, 2014.
M. Abuella and B. Chowdhury, “Solar power forecasting using support vector regression,” 2016 Int. Annu. Conf. Am. Soc. Eng. Manag. ASEM 2016, 2016.
N. Sharma, P. Sharma, D. Irwin, and P. Shenoy, “Predicting solar generation from weather forecasts using machine learning,” 2011 IEEE Int. Conf. Smart Grid Commun. SmartGridComm 2011, pp. 528–533, 2011.
R. V Sidrys, “Forecasting Power Output for Grid-connected Photovoltaic Power System without using Solar Radiation Measurement Cai,” Am. Archaeol., vol. 41, no. 4, pp. 449–464, 2012.
M. Rana, I. Koprinska, and V. G. Agelidis, “Forecasting solar power generated by grid connected PV systems using ensembles of neural networks,” Proc. Int. Jt. Conf. Neural Networks, vol. 2015-Septe, 2015.
C. Wan, J. Zhao, Y. Song, Z. Xu, J. Lin, and Z. Hu, “Photovoltaic and solar power forecasting for smart grid energy management,” CSEE J. Power Energy Syst., vol. 1, no. 4, pp. 38–46, 2016.
A. Gandelli, F. Grimaccia, S. Leva, M. Mussetta, and E. Ogliari, “Hybrid model analysis and validation for PV energy production forecasting,” Proc. Int. Jt. Conf. Neural Networks, no. December 2015, pp. 1957–1962, 2014.
T. T. Teo, T. Logenthiran, W. L. Woo, and K. Abidi, “Forecasting of photovoltaic power using regularized ensemble Extreme Learning Machine,” IEEE Reg. 10 Annu. Int. Conf. Proceedings/TENCON, no. November, pp. 455–458, 2017.
P. Mandal, S. T. S. Madhira, A. Ul haque, J. Meng, and R. L. Pineda, “Forecasting power output of solar photovoltaic system using wavelet transform and artificial intelligence techniques,” Procedia Comput. Sci., vol. 12, no. 915, pp. 332–337, 2012.
A. Alzahrani, P. Shamsi, C. Dagli, and M. Ferdowsi, “Solar Irradiance Forecasting Using Deep Neural Networks,” Procedia Comput. Sci., vol. 114, pp. 304–313, 2017.
H. K. Yadav, Y. Pal, and M. M. Tripathi, “Photovoltaic power forecasting methods in smart power grid,” 12th IEEE Int. Conf. Electron. Energy, Environ. Commun. Comput. Control (E3-C3), INDICON 2015, no. December, 2016.
H. S. Jang, K. Y. Bae, H. S. Park, and D. K. Sung, “Solar Power Prediction Based on Satellite Images and Support Vector Machine,” IEEE Trans. Sustain. Energy, vol. 7, no. 3, pp. 1255–1263, 2016.
O. Yazdanbaksh, A. Krahn, and S. Dick, “Predicting solar power output using complex fuzzy logic,” Proc. 2013 Jt. IFSA World Congr. NAFIPS Annu. Meet. IFSA/NAFIPS 2013, pp. 1243–1248, 2013.
N. Sharma, P. Sharma, D. Irwin, and P. Shenoy, “Predicting solar generation from weather forecasts using machine learning,” 2011 IEEE Int. Conf. Smart Grid Commun. SmartGridComm 2011, pp. 528–533, 2011.
E. G. Kardakos, M. C. Alexiadis, S. I. Vagropoulos, C. K. Simoglou, P. N. Biskas, and A. G. Bakirtzis, “Application of time series and artificial neural network models in short-term forecasting of PV power generation,” Proc. Univ. Power Eng. Conf., no. D, pp. 1–5, 2013.
Y. Li et al., “A machine-learning approach for regional photovoltaic power forecasting,” IEEE Power Energy Soc. Gen. Meet., vol. 2016-Novem, 2016.
P. Luo, S. Zhu, L. Han, and Q. Chen, “Short-term photovoltaic generation forecasting based on similar day selection and extreme learning machine,” IEEE Power Energy Soc. Gen. Meet., vol. 2018-Janua, pp. 1–5, 2018.
Y. K. Semero, J. Zhang, and D. Zheng, “PV power forecasting using an integrated GA-PSO-ANFIS approach and Gaussian process regression based feature selection strategy,” CSEE J. Power Energy Syst., vol. 4, no. 2, pp. 210–218, 2018.
H. Sheng, J. Xiao, Y. Cheng, Q. Ni, and S. Wang, “Short-Term Solar Power Forecasting Based on Weighted Gaussian Process Regression,” IEEE Trans. Ind. Electron., vol. 65, no. 1, pp. 300–308, 2018.
Published
How to Cite
Issue
Section
License
The articles may be used for research, teaching, and private study purposes. Any substantial or systematic reproduction, redistribution, reselling, loan, sub-licensing, systematic supply, or distribution in any form to anyone is expressly forbidden. Authors alone are responsible for the contents of their articles. The journal owns the copyright of the articles. However, within the framework of Creative Commons (CC) copyright license, authors can use their published works in non-profit environments and share them on their own platforms on the internet. The publisher shall not be liable for any loss, actions, claims, proceedings, demand, or costs or damages whatsoever or howsoever caused arising directly or indirectly in connection with or arising out of the use of the research material. All authors are requested to disclose any actual or potential conflict of interest including any financial, personal or other relationships with other people or organizations regarding the submitted work.
The author (s) guarantees that the submitted article is his/her/their original research. All authors participating in this study assumed public responsibility and confirmed that the article was not submitted for another journal. All the articles in the article do not violate the existing copyright rules and intellectual property rights of any person or organization. The article meets the ethical standards applicable to the research discipline.
The authors cannot withdraw the article they have uploaded to IJHaTI journal and upload it to another journal without the approval of the journal editor.
Authors are responsible for obtaining written permission to include any images or artwork for which they do not hold copyright in their articles, or to adapt any such images or artwork for inclusion in their articles. The copyright
