Journal of the Korean Society of Industry Convergence (한국산업융합학회 논문집)

The Korean Society of Industry Convergence (한국산업융합학회)
권호 표지
DOI QR코드

DOI QR Code

Mid- and Short-term Power Generation Forecasting using Hybrid Model

하이브리드 모델을 이용하여 중단기 태양발전량 예측

  • Nam-Rye Son (Software Centered University Project Group)
  • 손남례 (전남대학교 소프트웨어중심대학사업단)
  • Received : 2023.07.19
  • Accepted : 2023.08.10
  • Published : 2023.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Solar energy forecasting is essential for (1) power system planning, management, and operation, requiring accurate predictions. It is crucial for (2) ensuring a continuous and sustainable power supply to customers and (3) optimizing the operation and control of renewable energy systems and the electricity market. Recently, research has been focusing on developing solar energy forecasting models that can provide daily plans for power usage and production and be verified in the electricity market. In these prediction models, various data, including solar energy generation and climate data, are chosen to be utilized in the forecasting process. The most commonly used climate data (such as temperature, relative humidity, precipitation, solar radiation, and wind speed) significantly influence the fluctuations in solar energy generation based on weather conditions. Therefore, this paper proposes a hybrid forecasting model by combining the strengths of the Prophet model and the GRU model, which exhibits excellent predictive performance. The forecasting periods for solar energy generation are tested in short-term (2 days, 7 days) and medium-term (15 days, 30 days) scenarios. The experimental results demonstrate that the proposed approach outperforms the conventional Prophet model by more than twice in terms of Root Mean Square Error (RMSE) and surpasses the modified GRU model by more than 1.5 times, showcasing superior performance.

Keywords

References

  1. International Renewable Energy Agency. Renewable Capacity Statistics; International Renewable Energy Agency: Masdar City, United Arab Emirates, 2020.
  2. https://www.letsrethinkenergy.com/
  3. G. Grazioli, S. Chlela, S. Selosse, and N. Maizl, N., "The Multi-Facets of Increasing the Renewable Energy Integration in Power Systems," Energies Vol.15, No. 6795, 2022.
  4. B. Xue., and J. Keng., "Dynamic transverse correction method of middle and long term energy forecasting based on statistic of forecasting errors," In Proceedings of the Conference on Power and Energy IPEC, Ho Chi Minh City, Vietnam, pp. 253-256, 2012.
  5. Brown, R.G., "Smoothing Forecasting and Prediction of Discrete Time Series," Prentice-Hall, Englewood Cliffs, NJ, USA, 1963.
  6. Y. Ohtsuka, T, O ga, and K . Kakamu, "Forecasting electricity demand in Japan: A Bayesian spatial autoregressive ARMA approach," Comp. Stat. Data Anal., No.54, pp.2721-2735, 2010.
  7. C.E. Holt, "Forecasting Seasonal and Trends by Exponentially Weighted Average,"Carnegie Institute of Technology, Pittsburgh, PA, USA, 1957.
  8. S.A. Kalogirou, C.C. Neocleous, C.C. Schizas, "Building heating load estimation using artificial neural networks," In Proceedings of the 17th International Conference on Parallel Architectures and Compilation Techniques, San Francisco, CA, USA, 10-14 November 1997.
  9. A. Bagnasco, F. Fresi, M. Saviozzi, F. Silvestro, A. Vinci, "Electrical consumption forecasting in hospital facilities: An application case,"Energy Build, No.103, pp.261-270., 2015.
  10. F. Gers, J. Schmidhuber, F. Cummins, "Learning to Forget: Continual Prediction with LSTM," In Proceedings of the 9th International Conference on Artificial Neural Networks, ICANN'99, Edinburgh, UK,pp. 850-855, 1999.
  11. P. Valenzuela, J. Gorricho, and de la Iglesia, "Automatic model and feature selection for time series forecasting: Achieving good performance and interpretability,"Information Sciences, No.423, pp.157-174, 2018.
  12. P. Sanguansat, and N. Klomjit, "A comparative study of machine learning techniques for short-term load forecasting,"Energies, Vol. 12, No.20, 2019.
  13. G. Fung, and E. Shih, "Evaluating the Forecasting Performance of Facebook's Prophet Model for Time Series Data," Journal of Open Source Software, Vol.4, No.43, 2019.
  14. Tasarruf Bashir, Chen Haoyong, "Short term electricity load forecasting using hybrid prophet-LSTM model optimized by BPNN," Energy Reports, Vol 8, Nov. 2022, pp.1678-1686. https://doi.org/10.1016/j.egyr.2021.12.067
  15. Serdar Arslan, "A hybrid forecasting model using LSTM and Prophet for energy consumption with decomposition of time series data," PeerJ Computer Science 8(3), June, 2022.
  16. Pin Li, Jin-suo Zhang, "A New Hybrid Method for China's Energy Supply Security Forecasting Based on ARIMA and XGBoost," Energies, 11(7), June, 2018.
  17. Yuanhua Chen, Muhammad S.B., Muhammad, A., Dingtian Xiao, "Evaluation of Machine Learning Models for Smart Grid Parameters: Performance Analysis of ARIMA and Bi-LSTM" Sustaiability 15(11), May 2023.
  18. G. Peter Zhang, "Time Series Forecasting using a Hybrid ARIMA and LSTM model," Vol. 50, pp. 159-175, 2003. https://doi.org/10.1016/S0925-2312(01)00702-0
  19. Agbessi A.P., Salami A.A., Agbosse K.S., Birregah B. "Peak Electrical Energy Consumption Prediction by ARIMA, LSTM, GRU, ARIMA-LSTM and ARIMA-GRU Approaches," Energies, MDPI, 16(12), 4739, June 2023. https://doi.org/10.3390/en16124739
  20. S. J. Taylor and B. Letham, "Prophet: forecasting at scale,"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.1389-1397, 2017
  21. K. Cho, Van Merrienboer, B., Bahdanau, D., and Y. Bengio, "On the properties of neural machine translation: Encoder-decoder approaches," 2014.