Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power Production

被引:18
作者
Sedai, Ashish [1 ]
Dhakal, Rabin [2 ]
Gautam, Shishir [3 ]
Dhamala, Anibesh [4 ]
Bilbao, Argenis [1 ]
Wang, Qin [2 ]
Wigington, Adam [2 ]
Pol, Suhas [1 ,5 ]
机构
[1] Texas Tech Univ, Natl Wind Inst, Lubbock, TX 79415 USA
[2] Elect Power Res Inst, Palo Alto, CA 94304 USA
[3] Tribhuvan Univ, Dept Mech Engn, Dharan 56700, Nepal
[4] Texas Tech Univ, Dept Mech Engn, Lubbock, TX 79401 USA
[5] Texas Tech Univ, Renewable Energy Program, Lubbock, TX 79401 USA
来源
FORECASTING | 2023年 / 5卷 / 01期
关键词
long-term forecasting; statistical; machine learning; neural network; prediction horizon; PREDICTION; APPROXIMATION; SUNSHINE;
D O I
10.3390/forecast5010014
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
The Machine Learning/Deep Learning (ML/DL) forecasting model has helped stakeholders overcome uncertainties associated with renewable energy resources and time planning for probable near-term power fluctuations. Nevertheless, the effectiveness of long-term forecasting of renewable energy resources using an existing ML/DL model is still debatable and needs additional research. Considering the constraints inherent in current empirical or physical-based forecasting models, the study utilizes ML/DL models to provide long-term predictions for solar power production. This study aims to examine the efficacy of several existing forecasting models. The study suggests approaches to enhance the accuracy of long-term forecasting of solar power generation for a case study power plant. It summarizes and compares the statistical model (ARIMA), ML model (SVR), DL models (LSTM, GRU, etc.), and ensemble models (RF, hybrid) with respect to long-term prediction. The performances of the univariate and multivariate models are summarized and compared based on their ability to accurately predict solar power generation for the next 1, 3, 5, and 15 days for a 100-kW solar power plant in Lubbock, TX, USA. Conclusions are drawn predicting the accuracy of various model changes with variation in the prediction time frame and input variables. In summary, the Random Forest model predicted long-term solar power generation with 50% better accuracy over the univariate statistical model and 10% better accuracy over multivariate ML/DL models.
引用
收藏
页码:256 / 284
页数:29
相关论文
共 61 条
[1]   Deep RNN-Based Photovoltaic Power Short-Term Forecast Using Power IoT Sensors [J].
Ahn, Hyung Keun ;
Park, Neungsoo .
ENERGIES, 2021, 14 (02)
[2]  
Akinoglu B. G., 1991, Renewable Energy, V1, P479, DOI 10.1016/0960-1481(91)90061-S
[3]  
[Anonymous], BUILDING ARIMA ARIMA
[4]  
[Anonymous], SOCIOL METHOD RES
[5]   A novel machine learning method for estimating football players' value in the transfer market [J].
Behravan, Iman ;
Razavi, Seyed Mohammad .
SOFT COMPUTING, 2021, 25 (03) :2499-2511
[6]  
Bisong E., 2019, Matplotlib and seaborn. Building machine learning and deep learning models on google cloud platform: A comprehensive guide for beginners, P151
[7]   Predicting intentions to comply with speed limits using a 'decision tree' applied to an extended version of the theory of planned behaviour [J].
Bordarie, Jimmy .
TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR, 2019, 63 :174-185
[8]   RNN / LSTM with modified Adam optimizer in deep learning approach for automobile spare parts demand forecasting [J].
Chandriah, Kiran Kumar ;
Naraganahalli, Raghavendra V. .
MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (17) :26145-26159
[9]  
Choudhary A, 2019, 2019 3RD INTERNATIONAL CONFERENCE ON RECENT DEVELOPMENTS IN CONTROL, AUTOMATION & POWER ENGINEERING (RDCAPE), P169, DOI [10.1109/RDCAPE47089.2019.8979001, 10.1109/rdcape47089.2019.8979001]
[10]  
Dey R, 2017, MIDWEST SYMP CIRCUIT, P1597, DOI 10.1109/MWSCAS.2017.8053243