Abstract

Accurate forecasting of generation is vital for integrating solar power plants into the grid. In this study, an attention-based LSTM model was developed using 15-minute generation and meteorological data from a 5 MW plant in Konya. The model was compared with ARIMA, vanilla LSTM and GRU models. The proposed model reduced the mean absolute percentage error to 6.2% for a one-hour horizon. On cloudy days, attention weights were observed to concentrate on changes in irradiance.

Declarations

Ethics Approval
Bu çalışma etik kurul onayı gerektirmemektedir.
Conflict of Interest
Yazarlar herhangi bir çıkar çatışması olmadığını beyan eder.

References 5

  1. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
  2. Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). Wiley.
  3. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
  4. Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In International Conference on Learning Representations.
  5. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), 1929–1958.

How to Cite

Kurt, O., & Güneş, N. (2024). An Attention-Based LSTM Model for Short-Term Solar Power Forecasting. International Journal of Science and Technology Research, 6(2), 15–26. https://doi.org/10.99999/ubtad.2024.5

License

CC BY 4.0

© 2024 Oğuzhan Kurt, Nazlı Güneş. This article is distributed under the terms of the CC BY 4.0 license, which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. License text