Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power Production
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 u...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Forecasting |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-9394/5/1/14 |
| _version_ | 1797611660367626240 |
|---|---|
| author | Ashish Sedai Rabin Dhakal Shishir Gautam Anibesh Dhamala Argenis Bilbao Qin Wang Adam Wigington Suhas Pol |
| author_facet | Ashish Sedai Rabin Dhakal Shishir Gautam Anibesh Dhamala Argenis Bilbao Qin Wang Adam Wigington Suhas Pol |
| author_sort | Ashish Sedai |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T06:31:52Z |
| format | Article |
| id | doaj.art-45a13300a1fb420592d8f0a80e0313cb |
| institution | Directory Open Access Journal |
| issn | 2571-9394 |
| language | English |
| last_indexed | 2024-03-11T06:31:52Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forecasting |
| spelling | doaj.art-45a13300a1fb420592d8f0a80e0313cb2023-11-17T11:08:22ZengMDPI AGForecasting2571-93942023-02-015125628410.3390/forecast5010014Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power ProductionAshish Sedai0Rabin Dhakal1Shishir Gautam2Anibesh Dhamala3Argenis Bilbao4Qin Wang5Adam Wigington6Suhas Pol7National Wind Institute, Texas Tech University, Lubbock, TX 79415, USAElectric Power Research Institute, Palo Alto, CA 94304, USADepartment of Mechanical Engineering, Tribhuvan University, Dharan 56700, NepalDepartment of Mechanical Engineering, Texas Tech University, Lubbock, TX 79401, USANational Wind Institute, Texas Tech University, Lubbock, TX 79415, USAElectric Power Research Institute, Palo Alto, CA 94304, USAElectric Power Research Institute, Palo Alto, CA 94304, USANational Wind Institute, Texas Tech University, Lubbock, TX 79415, USAThe 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.https://www.mdpi.com/2571-9394/5/1/14long-term forecastingstatisticalmachine learningneural networkprediction horizon |
| spellingShingle | Ashish Sedai Rabin Dhakal Shishir Gautam Anibesh Dhamala Argenis Bilbao Qin Wang Adam Wigington Suhas Pol Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power Production Forecasting long-term forecasting statistical machine learning neural network prediction horizon |
| title | Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power Production |
| title_full | Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power Production |
| title_fullStr | Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power Production |
| title_full_unstemmed | Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power Production |
| title_short | Performance Analysis of Statistical, Machine Learning and Deep Learning Models in Long-Term Forecasting of Solar Power Production |
| title_sort | performance analysis of statistical machine learning and deep learning models in long term forecasting of solar power production |
| topic | long-term forecasting statistical machine learning neural network prediction horizon |
| url | https://www.mdpi.com/2571-9394/5/1/14 |
| work_keys_str_mv | AT ashishsedai performanceanalysisofstatisticalmachinelearninganddeeplearningmodelsinlongtermforecastingofsolarpowerproduction AT rabindhakal performanceanalysisofstatisticalmachinelearninganddeeplearningmodelsinlongtermforecastingofsolarpowerproduction AT shishirgautam performanceanalysisofstatisticalmachinelearninganddeeplearningmodelsinlongtermforecastingofsolarpowerproduction AT anibeshdhamala performanceanalysisofstatisticalmachinelearninganddeeplearningmodelsinlongtermforecastingofsolarpowerproduction AT argenisbilbao performanceanalysisofstatisticalmachinelearninganddeeplearningmodelsinlongtermforecastingofsolarpowerproduction AT qinwang performanceanalysisofstatisticalmachinelearninganddeeplearningmodelsinlongtermforecastingofsolarpowerproduction AT adamwigington performanceanalysisofstatisticalmachinelearninganddeeplearningmodelsinlongtermforecastingofsolarpowerproduction AT suhaspol performanceanalysisofstatisticalmachinelearninganddeeplearningmodelsinlongtermforecastingofsolarpowerproduction |