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

被引：0

作者：

Pu Z. ^{[1
]}

Xia P. ^{[2
,3
]}

Zhang L. ^{[4
]}

Wang S. ^{[2
,3
]}

Wang Y. ^{[1
]}

Min M. ^{[2
,3
]}

机构：

[1] China General Nuclear Power Group（CGN）Wind Energy Co.，Ltd, Beijing

[2] Key Laboratory of Tropical Atmosphere-Ocean System, Ministry of Education, School of Atmospheric Sciences, Sun Yat-sen University, Zhuhai

[3] Guangdong Province Key Laboratory for Climate Change and Natural Disaster Studies, School of Atmospheric Sciences, Sun Yat-sen University, Zhuhai

[4] Key Laboratory of Radiometric Calibration and Validation for Environmental Satellites, National Satellite Meteorological Center, National Center for Space Weather, Innovation Center for FengYun Meteorological Satellite（FYSIC）, China Meteorological Administ

来源：

Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2023年 / 44卷 / 07期

关键词：

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

D O I：

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

中图分类号：

学科分类号：

摘要：

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. © 2023 Science Press. All rights reserved.

引用

页码：162 / 167

页数：5

共 36 条

[1]

LI F, CHEN Z, CHENG C, Et al., Review on forecast methods for photovoltaic power generation［J］, Advances in climate change research, 7, 2, pp. 136-142, (2011)

[2]

ZHU H L, SUN Q，, Et al., A power prediction method for photovoltaic power plant based on wavelet decomposition and artificial neural networks［J］, Energies, 9, 1, (2015)

[3]

Forecasting of photovoltaic power generation and model optimization：a review［J］, Renewable and sustainable energy reviews, 81, pp. 912-928, (2018)

[4]

KURBAN M., Hourly solar radiation forecasting using optimal coefficient 2- D linear filters and feed- forward neural networks［J］, Solar energy, 82, 8, pp. 714-726, (2008)

[5]

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, 84, 5, pp. 807-821, (2010)

[6]

WANG F, Et al., Short- term solar irradiance forecasting model based on artificial neural network using statistical feature parameters［J］, Energies, 5, 5, pp. 1355-1370, (2012)

[7]

DALTON G, BALDOCK T., Feasibility analysis of renewable energy supply options for a grid-connected large hotel［J］, Renewable energy, 34, 4, pp. 955-964, (2009)

[8]

WANG K J, LIU H D., Photovoltaic power forecasting based LSTM-convolutional network［J］, Energy, 189, (2019)

[9]

AHMED R, 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, 124, (2020)

[10]

HUANG J, AGRAWAL M，, Et al., Forecasting solar radiation on an hourly time scale using a coupled autoregressive and dynamical system（CARDS）model ［J］, Solar energy, 87, pp. 136-149, (2013)

← 1 2 3 4 →