Performance of Deep Learning Techniques for Forecasting PV Power Generation: A Case Study on a 1.5 MWp Floating PV Power Plant
Recently, deep learning techniques have become popular and are widely employed in several research areas, such as optimization, pattern recognition, object identification, and forecasting, due to the advanced development of computer programming technologies. A significant number of renewable energy...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/5/2119 |
| _version_ | 1797615423062016000 |
|---|---|
| author | Nonthawat Khortsriwong Promphak Boonraksa Terapong Boonraksa Thipwan Fangsuwannarak Asada Boonsrirat Watcharakorn Pinthurat Boonruang Marungsri |
| author_facet | Nonthawat Khortsriwong Promphak Boonraksa Terapong Boonraksa Thipwan Fangsuwannarak Asada Boonsrirat Watcharakorn Pinthurat Boonruang Marungsri |
| author_sort | Nonthawat Khortsriwong |
| collection | DOAJ |
| description | Recently, deep learning techniques have become popular and are widely employed in several research areas, such as optimization, pattern recognition, object identification, and forecasting, due to the advanced development of computer programming technologies. A significant number of renewable energy sources (RESs) as environmentally friendly sources, especially solar photovoltaic (PV) sources, have been integrated into modern power systems. However, the PV source is highly fluctuating and difficult to predict accurately for short-term PV output power generation, leading to ineffective system planning and affecting energy security. Compared to conventional predictive approaches, such as linear regression, predictive-based deep learning methods are promising in predicting short-term PV power generation with high accuracy. This paper investigates the performance of several well-known deep learning techniques to forecast short-term PV power generation in the real-site floating PV power plant of 1.5 MWp capacity at Suranaree University of Technology Hospital, Thailand. The considered deep learning techniques include single models (RNN, CNN, LSTM, GRU, BiLSTM, and BiGRU) and hybrid models (CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU). Five-minute resolution data from the real floating PV power plant is used to train and test the deep learning models. Accuracy indices of MAE, MAPE, and RMSE are applied to quantify errors between actual and forecasted values obtained from the different deep learning techniques. The obtained results show that, with the same training dataset, the performance of the deep learning models differs when testing under different weather conditions and time horizons. The CNN-BiGRU model offers the best performance for one-day PV forecasting, while the BiLSTM model is the most preferable for one-week PV forecasting. |
| first_indexed | 2024-03-11T07:26:06Z |
| format | Article |
| id | doaj.art-02ebe1dba8014aa88f594d2028264a4c |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T07:26:06Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-02ebe1dba8014aa88f594d2028264a4c2023-11-17T07:34:26ZengMDPI AGEnergies1996-10732023-02-01165211910.3390/en16052119Performance of Deep Learning Techniques for Forecasting PV Power Generation: A Case Study on a 1.5 MWp Floating PV Power PlantNonthawat Khortsriwong0Promphak Boonraksa1Terapong Boonraksa2Thipwan Fangsuwannarak3Asada Boonsrirat4Watcharakorn Pinthurat5Boonruang Marungsri6School of Electrical Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, ThailandSchool of Electrical Engineering, Rajamangala University of Technology Suvarnabhumi, Nonthaburi 11000, ThailandSchool of Electrical Engineering, Rajamangala University of Technology Rattanakosin, Nakhon Pathom 73170, ThailandSchool of Electrical Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, ThailandEnergy Solution Business, SCG Chemicals Public Co., Ltd., Bangsue, Bangkok 10800, ThailandSchool of Electrical Engineering and Telecommunications, The University of New South Wales, Sydney 2052, AustraliaSchool of Electrical Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, ThailandRecently, deep learning techniques have become popular and are widely employed in several research areas, such as optimization, pattern recognition, object identification, and forecasting, due to the advanced development of computer programming technologies. A significant number of renewable energy sources (RESs) as environmentally friendly sources, especially solar photovoltaic (PV) sources, have been integrated into modern power systems. However, the PV source is highly fluctuating and difficult to predict accurately for short-term PV output power generation, leading to ineffective system planning and affecting energy security. Compared to conventional predictive approaches, such as linear regression, predictive-based deep learning methods are promising in predicting short-term PV power generation with high accuracy. This paper investigates the performance of several well-known deep learning techniques to forecast short-term PV power generation in the real-site floating PV power plant of 1.5 MWp capacity at Suranaree University of Technology Hospital, Thailand. The considered deep learning techniques include single models (RNN, CNN, LSTM, GRU, BiLSTM, and BiGRU) and hybrid models (CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU). Five-minute resolution data from the real floating PV power plant is used to train and test the deep learning models. Accuracy indices of MAE, MAPE, and RMSE are applied to quantify errors between actual and forecasted values obtained from the different deep learning techniques. The obtained results show that, with the same training dataset, the performance of the deep learning models differs when testing under different weather conditions and time horizons. The CNN-BiGRU model offers the best performance for one-day PV forecasting, while the BiLSTM model is the most preferable for one-week PV forecasting.https://www.mdpi.com/1996-1073/16/5/2119floating PV power plantdeep learning techniquesshort-term PV power forecastingPV generationneural networks |
| spellingShingle | Nonthawat Khortsriwong Promphak Boonraksa Terapong Boonraksa Thipwan Fangsuwannarak Asada Boonsrirat Watcharakorn Pinthurat Boonruang Marungsri Performance of Deep Learning Techniques for Forecasting PV Power Generation: A Case Study on a 1.5 MWp Floating PV Power Plant Energies floating PV power plant deep learning techniques short-term PV power forecasting PV generation neural networks |
| title | Performance of Deep Learning Techniques for Forecasting PV Power Generation: A Case Study on a 1.5 MWp Floating PV Power Plant |
| title_full | Performance of Deep Learning Techniques for Forecasting PV Power Generation: A Case Study on a 1.5 MWp Floating PV Power Plant |
| title_fullStr | Performance of Deep Learning Techniques for Forecasting PV Power Generation: A Case Study on a 1.5 MWp Floating PV Power Plant |
| title_full_unstemmed | Performance of Deep Learning Techniques for Forecasting PV Power Generation: A Case Study on a 1.5 MWp Floating PV Power Plant |
| title_short | Performance of Deep Learning Techniques for Forecasting PV Power Generation: A Case Study on a 1.5 MWp Floating PV Power Plant |
| title_sort | performance of deep learning techniques for forecasting pv power generation a case study on a 1 5 mwp floating pv power plant |
| topic | floating PV power plant deep learning techniques short-term PV power forecasting PV generation neural networks |
| url | https://www.mdpi.com/1996-1073/16/5/2119 |
| work_keys_str_mv | AT nonthawatkhortsriwong performanceofdeeplearningtechniquesforforecastingpvpowergenerationacasestudyona15mwpfloatingpvpowerplant AT promphakboonraksa performanceofdeeplearningtechniquesforforecastingpvpowergenerationacasestudyona15mwpfloatingpvpowerplant AT terapongboonraksa performanceofdeeplearningtechniquesforforecastingpvpowergenerationacasestudyona15mwpfloatingpvpowerplant AT thipwanfangsuwannarak performanceofdeeplearningtechniquesforforecastingpvpowergenerationacasestudyona15mwpfloatingpvpowerplant AT asadaboonsrirat performanceofdeeplearningtechniquesforforecastingpvpowergenerationacasestudyona15mwpfloatingpvpowerplant AT watcharakornpinthurat performanceofdeeplearningtechniquesforforecastingpvpowergenerationacasestudyona15mwpfloatingpvpowerplant AT boonruangmarungsri performanceofdeeplearningtechniquesforforecastingpvpowergenerationacasestudyona15mwpfloatingpvpowerplant |