Journal of Power Electronics

The Korean Institute of Power Electronics (전력전자학회)
권호 표지
DOI QR코드

DOI QR Code

Physical model and long short-term memory-based combined prediction of photovoltaic power generation

  • Yaoyu Wu (College of Economics and Management, Nanjing Forestry University) ;
  • Jing Liu (Department of Automation, North China Electric Power University) ;
  • Suhuan Li (Management Training Department, State Grid Jibei Electric Power Company Limited Management Training Center) ;
  • Mingyue Jin (Department of Automation, North China Electric Power University)
  • Received : 2023.05.20
  • Accepted : 2024.02.07
  • Published : 2024.07.20
⟨ Previous Next ⟩

Abstract

Solar energy is clean and pollution free. However, the evident intermittency and volatility of illumination make power systems uncertain. Therefore, establishing a photovoltaic prediction model to enhance prediction precision is conducive to lessening the uncertainty of photovoltaic (PV) power generation and to ensuring the safe and stable operation of power grid scheduling. The radiation from the sun to the Earth has a certain regularity, which can be estimated under ideal weather conditions. However, the radiation is affected by climate, cloud cover, and other reasons. Therefore, this paper puts forward a PV prediction model combining a physical model and a neural network that can modify solar radiation in complex weather through the neural network to enhance the accuracy of PV power prediction. First, a solar radiation model (SRM) is established by using the solar radiation mechanism to estimate the sum radiation value on the horizontal plane. Then the slope radiation value received by the PV panel is calculated by the slope irradiance conversion method. Second, the main factors that greatly influence PV power are screened out by the Pearson method. The calculated slope radiation and the main influencing factors are taken as inputs. The long short-term memory network (LSTM) is selected to set up the SRM-LSTM PV power prediction method. The significance of the suggested method is verified by the true data from Alice Springs, Australia. The results show that when compared with the backpropagation (BP) prediction method, the MAE and RMSE were reduced by 22.18% and 33.89% under complex weather conditions, respectively. When compared with the LSTM prediction method, the MAE and RMSE were reduced by 15.99% and 21.73%, respectively. These results demonstrate high accuracy.

Keywords

References

  1. Houchati, M., Beitelmal, A.M.H., Khraisheh, M.: Predictive modeling for rooftop solar energy throughput: a machine learning-based optimization for building energy demand scheduling. J. Energy Resour. ASME 144(1), 1-15 (2022) https://doi.org/10.1115/1.4050844
  2. Liu, L., Zhao, Y., Chang, D.L., Xie, J.Y., Ma, Z., Qie, S., Yin, H.G., Ronald, W.: Prediction of short-term PV power output and uncertainty analysis. Appl. Energy 228(6), 700-711 (2018) https://doi.org/10.1016/j.apenergy.2018.06.112
  3. Dai, Y., Wang, Y., Leng, M., et al.: LOWESS smoothing and random forest based GRU model: a short-term photovoltaic power generation forecasting method. Energy 256, 124661 (2022)
  4. Wang, J.X., Guo, L.L., Zhang, C.Y., Song, L., Duan, J.Y., Duan, L.Q.: Thermal power forecasting of solar power tower system by combining mechanism modeling and deep learning method. Energy 208, 118403 (2020)
  5. Rodriguez, F., Galarza, A., Vasquez, J.C., et al.: Using deep learning and meteorological parameters to forecast the photovoltaic generators intra-hour output power interval for smart grid control. Energy 239, 122116 (2022)
  6. Chen, X., Ding, K., Zhang, J., Han, W., Liu, Y.J., Yang, Z., Weng, S.: Online prediction of ultra-short-term photovoltaic power using chaotic characteristic analysis, improved PSO and KELM. Energy 248, 123574 (2022)
  7. Li, J., Niu, H., Meng, F., et al.: Prediction of short-term photovoltaic power via self-attention-based deep learning approach. J. Energy Resour. ASME 144(10), 101301 (2022)
  8. Huang, X., Li, Q., Tai, Y.H., Chen, Z.Q., Zhang, J., Shi, J.S., Gao, B.X., Liu, W.M.: Hybrid deep neural model for hourly solar irradiance forecasting. Renew. Energy 171(2), 1041-1060 (2021) https://doi.org/10.1016/j.renene.2021.02.161
  9. Mellit, A., Pavan, A.M., Lughi, V.: Deep learning neural networks for short-term photovoltaic power forecasting. Renew. Energy 172(2), 276-288 (2021) https://doi.org/10.1016/j.renene.2021.02.166
  10. Feng, Y., Gong, D., Zhang, Q., Cui, N.: Evaluation of temperature-based machine learning and empirical models for predicting daily global solar radiation. Energy Convers. Manag. 198, 111780 (2019)
  11. Lin, W., Zhang, B., Li, H., et al.: Multi-step prediction of photovoltaic power based on two-stage decomposition and BILSTM. Neurocomputing 504, 56-67 (2022) https://doi.org/10.1016/j.neucom.2022.06.117
  12. Cui, C.G., Zou, Y.H., Wei, L.L., Wang, Y.D.: Evaluating combination models of solar irradiance on inclined surfaces and forecasting photovoltaic power generation. IET Smart Grid 2(1), 123-130 (2019) https://doi.org/10.1049/iet-stg.2018.0110
  13. Mayer, M.J.: Influence of design data availability on the accuracy of physical photovoltaic power forecasts. Sol. Energy 227, 532-540 (2021) https://doi.org/10.1016/j.solener.2021.09.044
  14. Mayer, M.J., Grof, G.: Extensive comparison of physical models for photovoltaic power forecasting. Appl. Energy 283, 116239 (2021)
  15. Mayer, M.J.: Impact of the tilt angle, inverter sizing factor and row spacing on the photovoltaic power forecast accuracy. Appl. Energy 323, 119598 (2022)
  16. Wang, F., Lu, X., Mei, S., et al.: A satellite image data based ultra-short-term solar PV power forecasting method considering cloud information from neighboring plant. Energy 238, 121946 (2022) https://doi.org/10.1016/j.energy.2021.121946
  17. Zhang, J., Zhang, Q., Li, G., et al.: Hybrid model for renewable energy and load forecasting based on data mining and EWT. J. Electr. Eng. Technol. 17(3), 1517-1532 (2022) https://doi.org/10.1007/s42835-021-00986-0
  18. Das, S.: Short term forecasting of solar radiation and power output of 89.6 kWp solar PV power plant. Mater. Today Proc. 39, 1959-1969 (2021) https://doi.org/10.1016/j.matpr.2020.08.449
  19. Youssef, A., El-Telbany, M., Zekry, A.: The role of artificial intelligence in photo-voltaic systems design and control: a review. Renew. Sustain. Energy Rev. 78, 72-79 (2017) https://doi.org/10.1016/j.rser.2017.04.046
  20. Wang, X., Sun, Y., Luo, D., Peng, J.Q.: Comparative study of machine learning approaches for predicting short-term photovoltaic power output based on weather type classification. Energy 240, 122733 (2022)
  21. Lee, W., Kim, K., Park, J., Kim, J., Kim, A.Y.: Forecasting solar power using long-short term memory and convolutional neural networks. IEEE Access 6, 73068-73080 (2018) https://doi.org/10.1109/ACCESS.2018.2883330
  22. Xiao, Z., Huang, X., Liu, J., Li, C., Tai, Y.: A novel method based on time series ensemble model for hourly photovoltaic power prediction. Energy 276, 127542 (2023)
  23. Li, P., Zhou, K., Lu, X., Yang, S.L.: A hybrid deep learning model for short-term PV power forecasting. Appl. Energy 259, 114216 (2020)
  24. Zhao, W., Zhang, H., Zheng, J., Dai, Y.H., Huang, L.Q., Shang, W.L., Liang, Y.T.: A point prediction method based automatic machine learning for day-ahead power output of multi-region photovoltaic plants. Energy 223, 120026 (2021)
  25. Kreith, F., Kreider, J.F.: Principles of solar engineering (1978)
  26. Allen, R.G., Tasumi, M., Trezza, R.: Satellite-based energy balance for mapping evapotranspiration with internalized calibration (METRIC)-model. J. Irrig. Drain. Eng. 133(4), 380-394 (2007) https://doi.org/10.1061/(ASCE)0733-9437(2007)133:4(380)
  27. Campbell, G.S., Norman, J.M.: An introduction to environmental biophysics. Biol. Plant. 21, 104-104 (1979) https://doi.org/10.1007/BF02909456