Full Text Views
28
Solar power is the most widely used renewable energy source, which reduces pollution consequences from using conventional fossil fuels. However, supplying stable power from solar power generation remains challenging because it is difficult to forecast power generation. Accurate prediction of solar power generation would allow effective control of the amount of electricity stored in batteries, leading in a stable supply of electricity. Although the number of power plants is increasing, building a solar power prediction model for a newly constructed power plant usually requires collecting a new training dataset for the new power plant, which takes time to collect a sufficient amount of data. This paper aims to develop a highly accurate solar power prediction model for multiple power plants available for both new and existing power plants. The proposed method trains the model on existing multiple power plants to generate a general prediction model, and then uses it for a new power plant while waiting for the data to be collected. In addition, the proposed method tunes the general prediction model on the newly collected dataset and improves the accuracy for the new power plant. We evaluated the proposed method on 55 power plants in Japan with the dataset collected for two and a half years. As a result, the pre-trained models of our proposed method significantly reduces the average RMSE of the baseline method by 73.19%. This indicates that the model can generalize over multiple power plants, and training using datasets from other power plants is effective in reducing the RMSE. Fine-tuning the pre-trained model further reduces the RMSE by 8.12%.
Kundjanasith THONGLEK
Nara Institute of Science and Technology
Kohei ICHIKAWA
Nara Institute of Science and Technology
Keichi TAKAHASHI
Tohoku University
Chawanat NAKASAN
Kasetsart University
Kazufumi YUASA
NTT FACILITIES, INC.
Tadatoshi BABASAKI
NTT FACILITIES, INC.
Hajimu IIDA
Nara Institute of Science and Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Kundjanasith THONGLEK, Kohei ICHIKAWA, Keichi TAKAHASHI, Chawanat NAKASAN, Kazufumi YUASA, Tadatoshi BABASAKI, Hajimu IIDA, "Toward Predictive Modeling of Solar Power Generation for Multiple Power Plants" in IEICE TRANSACTIONS on Communications,
vol. E106-B, no. 7, pp. 547-556, July 2023, doi: 10.1587/transcom.2022EBT0003.
Abstract: Solar power is the most widely used renewable energy source, which reduces pollution consequences from using conventional fossil fuels. However, supplying stable power from solar power generation remains challenging because it is difficult to forecast power generation. Accurate prediction of solar power generation would allow effective control of the amount of electricity stored in batteries, leading in a stable supply of electricity. Although the number of power plants is increasing, building a solar power prediction model for a newly constructed power plant usually requires collecting a new training dataset for the new power plant, which takes time to collect a sufficient amount of data. This paper aims to develop a highly accurate solar power prediction model for multiple power plants available for both new and existing power plants. The proposed method trains the model on existing multiple power plants to generate a general prediction model, and then uses it for a new power plant while waiting for the data to be collected. In addition, the proposed method tunes the general prediction model on the newly collected dataset and improves the accuracy for the new power plant. We evaluated the proposed method on 55 power plants in Japan with the dataset collected for two and a half years. As a result, the pre-trained models of our proposed method significantly reduces the average RMSE of the baseline method by 73.19%. This indicates that the model can generalize over multiple power plants, and training using datasets from other power plants is effective in reducing the RMSE. Fine-tuning the pre-trained model further reduces the RMSE by 8.12%.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2022EBT0003/_p
Copy
@ARTICLE{e106-b_7_547,
author={Kundjanasith THONGLEK, Kohei ICHIKAWA, Keichi TAKAHASHI, Chawanat NAKASAN, Kazufumi YUASA, Tadatoshi BABASAKI, Hajimu IIDA, },
journal={IEICE TRANSACTIONS on Communications},
title={Toward Predictive Modeling of Solar Power Generation for Multiple Power Plants},
year={2023},
volume={E106-B},
number={7},
pages={547-556},
abstract={Solar power is the most widely used renewable energy source, which reduces pollution consequences from using conventional fossil fuels. However, supplying stable power from solar power generation remains challenging because it is difficult to forecast power generation. Accurate prediction of solar power generation would allow effective control of the amount of electricity stored in batteries, leading in a stable supply of electricity. Although the number of power plants is increasing, building a solar power prediction model for a newly constructed power plant usually requires collecting a new training dataset for the new power plant, which takes time to collect a sufficient amount of data. This paper aims to develop a highly accurate solar power prediction model for multiple power plants available for both new and existing power plants. The proposed method trains the model on existing multiple power plants to generate a general prediction model, and then uses it for a new power plant while waiting for the data to be collected. In addition, the proposed method tunes the general prediction model on the newly collected dataset and improves the accuracy for the new power plant. We evaluated the proposed method on 55 power plants in Japan with the dataset collected for two and a half years. As a result, the pre-trained models of our proposed method significantly reduces the average RMSE of the baseline method by 73.19%. This indicates that the model can generalize over multiple power plants, and training using datasets from other power plants is effective in reducing the RMSE. Fine-tuning the pre-trained model further reduces the RMSE by 8.12%.},
keywords={},
doi={10.1587/transcom.2022EBT0003},
ISSN={1745-1345},
month={July},}
Copy
TY - JOUR
TI - Toward Predictive Modeling of Solar Power Generation for Multiple Power Plants
T2 - IEICE TRANSACTIONS on Communications
SP - 547
EP - 556
AU - Kundjanasith THONGLEK
AU - Kohei ICHIKAWA
AU - Keichi TAKAHASHI
AU - Chawanat NAKASAN
AU - Kazufumi YUASA
AU - Tadatoshi BABASAKI
AU - Hajimu IIDA
PY - 2023
DO - 10.1587/transcom.2022EBT0003
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E106-B
IS - 7
JA - IEICE TRANSACTIONS on Communications
Y1 - July 2023
AB - Solar power is the most widely used renewable energy source, which reduces pollution consequences from using conventional fossil fuels. However, supplying stable power from solar power generation remains challenging because it is difficult to forecast power generation. Accurate prediction of solar power generation would allow effective control of the amount of electricity stored in batteries, leading in a stable supply of electricity. Although the number of power plants is increasing, building a solar power prediction model for a newly constructed power plant usually requires collecting a new training dataset for the new power plant, which takes time to collect a sufficient amount of data. This paper aims to develop a highly accurate solar power prediction model for multiple power plants available for both new and existing power plants. The proposed method trains the model on existing multiple power plants to generate a general prediction model, and then uses it for a new power plant while waiting for the data to be collected. In addition, the proposed method tunes the general prediction model on the newly collected dataset and improves the accuracy for the new power plant. We evaluated the proposed method on 55 power plants in Japan with the dataset collected for two and a half years. As a result, the pre-trained models of our proposed method significantly reduces the average RMSE of the baseline method by 73.19%. This indicates that the model can generalize over multiple power plants, and training using datasets from other power plants is effective in reducing the RMSE. Fine-tuning the pre-trained model further reduces the RMSE by 8.12%.
ER -