COMPARATIVE ANALYSIS OF MACHINE LEARNING AND STATISTICAL METHODS IN SOLAR ENERGY PREDICTION

Pu Zhiyong; Xia Pan; Zhang Lu; Wang Shuo; Wang Yun; Min Min

doi:10.19912/j.0254-0096.tynxb.2022-0290

PDF(1222 KB)

Acta Energiae Solaris Sinica ›› 2023, Vol. 44 ›› Issue (7) : 162-167. DOI: 10.19912/j.0254-0096.tynxb.2022-0290

COMPARATIVE ANALYSIS OF MACHINE LEARNING AND STATISTICAL METHODS IN SOLAR ENERGY PREDICTION

Pu Zhiyong¹, Xia Pan^2,3, Zhang Lu⁴, Wang Shuo^2,3, Wang Yun¹, Min Min^2,3

Author information +

History +

Abstract

This paper firstly reviews the development process and characteristics of traditional solar energy prediction methods. Then, the new solar energy prediction methods based on advanced machine learning algorithm in recent years are summarized . The current state-of-the-art progress of support vector machine, artificial neural network, and long/short-term memory network algorithms is mainly analyzed, respectively. The analysis shows that the solar energy prediction method based on machine learning has high prediction accuracy, small root mean square error and average deviation error, short prediction process time and timely prediction results. Finally, the advantages and disadvantages of traditional and machine learning prediction methods are summarized. It is pointed out that, the generalization ability of machine learning model is weak （weak universality）, it is very easy to be disturbed by external environmental factors. It is also difficult to give suitable physical explanations for their prediction process and results.

Key words

solar energy / forecasting / machine learning / deep learning / neural network

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Pu Zhiyong, Xia Pan, Zhang Lu, Wang Shuo, Wang Yun, Min Min. COMPARATIVE ANALYSIS OF MACHINE LEARNING AND STATISTICAL METHODS IN SOLAR ENERGY PREDICTION[J]. Acta Energiae Solaris Sinica. 2023, 44(7): 162-167 https://doi.org/10.19912/j.0254-0096.tynxb.2022-0290

References

[1] 李芬, 陈正洪, 成驰, 等. 太阳能光伏发电量预报方法的发展[J]. 气候变化研究进展, 2011, 7(2): 136-142.
LI F, CHEN Z H, CHENG C, et al.Review on forecast methods for photovoltaic power generation[J]. Advances in climate change research, 2011, 7(2): 136-142.
[2] ZHU H L, LI X, SUN Q, et al.A power prediction method for photovoltaic power plant based on wavelet decomposition and artificial neural networks[J]. Energies, 2015, 9(1): 11.
[3] DAS U K, TEY K S, SEYEDMAHMOUDIAN M, et al.Forecasting of photovoltaic power generation and model optimization: a review[J]. Renewable and sustainable energy reviews, 2018, 81: 912-928.
[4] HOCAOğLU F O, GEREK Ö N, KURBAN M. Hourly solar radiation forecasting using optimal coefficient 2-D linear filters and feed-forward neural networks[J]. Solar energy, 2008, 82(8): 714-726.
[5] MELLIT A, PAVAN A M.A 24 h forecast of solar irradiance using artificial neural network: application for performance prediction of a grid-connected PV plant at Trieste, Italy[J]. Solar energy, 2010, 84(5): 807-821.
[6] WANG F, MI Z Q, SU S, et al.Short-term solar irradiance forecasting model based on artificial neural network using statistical feature parameters[J]. Energies, 2012, 5(5): 1355-1370.
[7] DALTON G, LOCKINGTON D, BALDOCK T.Feasibility analysis of renewable energy supply options for a grid-connected large hotel[J]. Renewable energy, 2009, 34(4): 955-964.
[8] WANG K J, QI X X, LIU H D.Photovoltaic power forecasting based LSTM-convolutional network[J]. Energy, 2019, 189: 116225.
[9] AHMED R, SREERAM V, MISHRA Y, et al.A review and evaluation of the state-of-the-art in PV solar power forecasting: techniques and optimization[J]. Renewable and sustainable energy reviews, 2020, 124: 109792.
[10] HUANG J, KOROLKIEWICZ M, AGRAWAL M, et al.Forecasting solar radiation on an hourly time scale using a coupled autoregressive and dynamical system(CARDS) model[J]. Solar energy, 2013, 87: 136-149.
[11] HINTON G E, SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[12] REICHSTEIN M, CAMPS-VALLS G, STEVENS B, et al.Deep learning and process understanding for data-driven Earth system science[J]. Nature, 2019, 566(7743): 195-204.
[13] VOYANT C, NOTTON G, KALOGIROU S, et al.Machine learning methods for solar radiation forecasting: a review[J]. Renewable energy, 2017, 105: 569-582.
[14] DAVID M, RAMAHATANA F, TROMBE P J, et al.Probabilistic forecasting of the solar irradiance with recursive ARMA and GARCH models[J]. Solar energy, 2016, 133: 55-72.
[15] SUN H W, YAN D, ZHAO N, et al.Empirical investigation on modeling solar radiation series with ARMA-GARCH models[J]. Energy conversion and management, 2015, 92: 385-395.
[16] VOYANT C, MUSELLI M, PAOLI C, et al.Hybrid methodology for hourly global radiation forecasting in Mediterranean area[J]. Renewable energy, 2013, 53: 1-11.
[17] 刘福盛. 基于神经网络的光伏功率短期预测方法的研究[D]. 吉林: 东北电力大学, 2017.
LIU F S.Study on short-term photovoltaic power forecasting method based on artificial neural network[D]. Jinlin: Northeast Electric Power University, 2017.
[18] 陈志宝, 丁杰, 周海, 等. 地基云图结合径向基函数人工神经网络的光伏功率超短期预测模型[J]. 中国电机工程学报, 2015, 35(3): 561-567.
CHEN Z B, DING J, ZHOU H, et al.A model of very short-term photovoltaic power forecasting based on ground-based cloud images and RBF neural network[J]. Proceedings of the CSEE, 2015, 35(3): 561-567.
[19] JUNIOR J G D S F, OOZEKI T, OHTAKE H, et al. Forecasting regional photovoltaic power generation-a comparison of strategies to obtain one-day-ahead data[J]. Energy procedia, 2014, 57: 1337-1345.
[20] MA J M, JIANG H C, HUANG K Z, et al.Novel field-support vector regression-based soft sensor for accurate estimation of solar irradiance[J]. IEEE transactions on circuits and systems I: regular papers, 2017, 64(12): 3183-3191.
[21] ARIKAN C, OZDEMIR M.Classification of power quality disturbances at power system frequency and out of power system frequency using support vector machines[J]. Prz Elektrotech, 2013, 89: 284-291.
[22] 马志春, 刘振永, 吴淑花. 基于支持向量机的光伏发电功率预测系统设计[J]. 现代电子技术, 2021, 44(10): 91-94.
MA Z C, LIU Z Y, WU S H.Design of photovoltaic power prediction system based on support vector machine[J]. Modern electronics Technique, 2021, 44(10): 91-94.
[23] MOSAVI A, SALIMI M, FAIZOLLAHZADEH ARDABILI S, et al.State of the art of machine learning models in energy systems, a systematic review[J]. Energies, 2019, 12(7): 1301.
[24] QAZI A, FAYAZ H, WADI A, et al.The artificial neural network for solar radiation prediction and designing solar systems: a systematic literature review[J]. Journal of cleaner production, 2015, 104: 1-12.
[25] ALAM S, KAUSHIK S C, GARG S N.Computation of beam solar radiation at normal incidence using artificial neural network[J]. Renewable energy, 2006, 31(10): 1483-1491.
[26] FERNáNDEZ E F, ALMONACID F, SARMAH N, et al. A model based on artificial neuronal network for the prediction of the maximum power of a low concentration photovoltaic module for building integration[J]. Solar energy, 2014, 100: 148-158.
[27] ELSHEIKH A H, SHARSHIR S W, ABDELAZIZ M, et al.Modeling of solar energy systems using artificial neural network: a comprehensive review[J]. Solar energy, 2019, 180: 622-639.
[28] LINARES-RODRIGUEZ A, RUIZ-ARIAS J A, POZO-VAZQUEZ D, et al. An artificial neural network ensemble model for estimating global solar radiation from Meteosat satellite images[J]. Energy, 2013, 61: 636-645.
[29] LINARES-RODRIGUEZ A, QUESADA-RUIZ S, POZO-VAZQUEZ D, et al.An evolutionary artificial neural network ensemble model for estimating hourly direct normal irradiances from meteosat imagery[J]. Energy, 2015, 91: 264-273.
[30] LIPTON Z C, BERKOWITZ J, ELKAN C.A critical review of recurrent neural networks for sequence learning[J]. ArXiv preprint arXiv, 2015, 1506.00019.
[31] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[32] GHIMIRE S, DEO R C, RAJ N, et al.Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms[J]. Applied energy, 2019, 253: 113541.
[33] LI C, ZHANG Y N, ZHAO G H, et al.Hourly solar irradiance prediction using deep BiLSTM network[J]. Earth science informatics, 2021, 14(1): 299-309.
[34] 郑小山. 基于深度学习的太阳能发电功率预测方法研究[D]. 天津: 天津大学, 2020.
ZHENG X S.Research on solar power generation prediction based on deep learning[D]. Tianjin: Tianjin University, 2020.
[35] 孟珊珊, 郑健, 吴昊. 碟式太阳能集热器出口空气温度预测研究[J]. 太阳能, 2016(9): 54-59.
MENG S S, ZHENG J, WU H.Study on prediction of outlet air temperature of dish solar collector[J]. Solar energy, 2016(9): 54-59.
[36] 朱正林, 刘权, 张欢. 基于优化广义回归神经网络的碟式太阳能温度预测研究[J]. 南京工程学院学报(自然科学版), 2020, 18(1): 1-5.
ZHU Z L, LIU Q, ZHANG H.Prediction of dish solar temperature based on optimized generalized regression neural network[J]. Journal of Nanjing Institute of Technology (natural science edition), 2020, 18(1): 1-5.