Recurrent Fourier-Kolmogorov Arnold Networks for photovoltaic power forecasting
Abstract Accurate day-ahead forecasting of photovoltaic (PV) power generation is crucial for power system scheduling. To overcome the inaccuracies and inefficiencies of current PV power generation forecasting models, this paper introduces the Recurrent Fourier-Kolmogorov Arnold Network (RFKAN). Init...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-88959-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862469706121216 |
|---|---|
| author | Desheng Rong Zhongbao Lin Guomin Xie |
| author_facet | Desheng Rong Zhongbao Lin Guomin Xie |
| author_sort | Desheng Rong |
| collection | DOAJ |
| description | Abstract Accurate day-ahead forecasting of photovoltaic (PV) power generation is crucial for power system scheduling. To overcome the inaccuracies and inefficiencies of current PV power generation forecasting models, this paper introduces the Recurrent Fourier-Kolmogorov Arnold Network (RFKAN). Initially, recurrent kernel nodes are employed to investigate the interdependencies within sequences. Subsequently, Fourier series are applied to extract periodic features, enhancing forecasting accuracy and training speed. Ablation studies conducted using data from a PV power plant in Tieling City, Liaoning Province, validate the effectiveness of these two structural enhancements. Comparative experiments with baseline and state-of-the-art models further underscore the efficiency of RFKAN. The results indicate that RFKAN achieves the best forecasting performance with a grid depth of 100 and an input sequence length of 2, reducing RMSE and MAE by at least 5%, increasing CORR by 2%, and decreasing training time by 24% compared to advanced models. |
| format | Article |
| id | doaj-art-3c4b07160ba4426d91a2a4f73dcbbc8a |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-3c4b07160ba4426d91a2a4f73dcbbc8a2025-02-09T12:29:16ZengNature PortfolioScientific Reports2045-23222025-02-0115111410.1038/s41598-025-88959-5Recurrent Fourier-Kolmogorov Arnold Networks for photovoltaic power forecastingDesheng Rong0Zhongbao Lin1Guomin Xie2Faculty of Electrical and Control Engineering, Liaoning Technical UniversityFaculty of Electrical and Control Engineering, Liaoning Technical UniversityFaculty of Electrical and Control Engineering, Liaoning Technical UniversityAbstract Accurate day-ahead forecasting of photovoltaic (PV) power generation is crucial for power system scheduling. To overcome the inaccuracies and inefficiencies of current PV power generation forecasting models, this paper introduces the Recurrent Fourier-Kolmogorov Arnold Network (RFKAN). Initially, recurrent kernel nodes are employed to investigate the interdependencies within sequences. Subsequently, Fourier series are applied to extract periodic features, enhancing forecasting accuracy and training speed. Ablation studies conducted using data from a PV power plant in Tieling City, Liaoning Province, validate the effectiveness of these two structural enhancements. Comparative experiments with baseline and state-of-the-art models further underscore the efficiency of RFKAN. The results indicate that RFKAN achieves the best forecasting performance with a grid depth of 100 and an input sequence length of 2, reducing RMSE and MAE by at least 5%, increasing CORR by 2%, and decreasing training time by 24% compared to advanced models.https://doi.org/10.1038/s41598-025-88959-5Photovoltaic power forecastingRNN architectureFourier seriesRFKAN |
| spellingShingle | Desheng Rong Zhongbao Lin Guomin Xie Recurrent Fourier-Kolmogorov Arnold Networks for photovoltaic power forecasting Scientific Reports Photovoltaic power forecasting RNN architecture Fourier series RFKAN |
| title | Recurrent Fourier-Kolmogorov Arnold Networks for photovoltaic power forecasting |
| title_full | Recurrent Fourier-Kolmogorov Arnold Networks for photovoltaic power forecasting |
| title_fullStr | Recurrent Fourier-Kolmogorov Arnold Networks for photovoltaic power forecasting |
| title_full_unstemmed | Recurrent Fourier-Kolmogorov Arnold Networks for photovoltaic power forecasting |
| title_short | Recurrent Fourier-Kolmogorov Arnold Networks for photovoltaic power forecasting |
| title_sort | recurrent fourier kolmogorov arnold networks for photovoltaic power forecasting |
| topic | Photovoltaic power forecasting RNN architecture Fourier series RFKAN |
| url | https://doi.org/10.1038/s41598-025-88959-5 |
| work_keys_str_mv | AT deshengrong recurrentfourierkolmogorovarnoldnetworksforphotovoltaicpowerforecasting AT zhongbaolin recurrentfourierkolmogorovarnoldnetworksforphotovoltaicpowerforecasting AT guominxie recurrentfourierkolmogorovarnoldnetworksforphotovoltaicpowerforecasting |