Prediction model of photovoltaic power generation based on improved granular computing and neural networks

Authors

  • Zhibo Yang
  • Suhan Wang

DOI:

https://doi.org/10.54097/dkbkvz97

Keywords:

photovoltaic power prediction; granular computing; BP neural network; frequency domain analysis; periodic extraction.

Abstract

The application potential of solar energy generation is immense, yet its volatility poses significant challenges to power supply. With the aim of enhancing the accuracy of photovoltaic power generation prediction to better address its variability and stochastic nature, this study proposes a method based on enhanced granular computing and neural networks. The model utilizes wavelet transform to analyze the original time series in the frequency domain and employs fast Fourier transform to extract major periodic components. These components are then used to construct granularity matrices for training a backpropagation neural network (BPNN), aiming to achieve precise prediction of photovoltaic power generation. The research findings demonstrate that the model achieves an average error rate of around 17% on the test dataset, exhibiting outstanding performance compared to other classical time series prediction models. This study provides an effective method and reference for photovoltaic power generation prediction, contributing significantly to the field.

Downloads

Download data is not yet available.

References

Li J. Analysis of the Current Status and Development Trends of Photovoltaic Grid Connection Technology [J]. Market Weekly, 2017(28): 1.

Fang P, Gao Y, Pan G, et al. Research on forecasting method of mid-and long-term photovoltaic power generation based on LSTM neural Network[J]. Renewable Energy Resources., 2022, 40: 48-54.

Shi K, Zhang D, Han X, et al. Digital twin model of photovoltaic power generation prediction based on LSTM and transfer learning[J]. Power System Technology, 2022, 46(4): 1363-1371.

Qiao Y, Sun R, Ding R, et al. Distributed Photovoltaic Station Cluster Short-term Power Forecasting Part II: Gridding Prediction[J]. Power System Technology, 2021, 45(6): 2210-2218.

Huang L, Shu J, Jiang G, et al. Photovoltaic generation forecast based on multidimensional time-series and local support vector regression in microgrids[J]. Automation of Electric Power Systems, 2014, 38(5): 19-24.

Zhang Q, Ma Y, Li G, et al. Applications of Frequency Domain Decomposition and Deep Learning Algorithms in Short-term Load and Photovoltaic Power Forecasting [J]. Proceedings of the CSEE, 239(08): 2221-2230+5.

Guoyin W, Qinghua Z, Jun H. An overview of granular computing[J]. CAAI Transactions on Intelligent Systems, 2007, 2(6): 8-26.

Jafarian M , Ranjbar A . Fuzzy modeling techniques and artificial neural networks to estimate annual enerutput of a wind turbine[J]. Renewable Energy, 2010, 35(9): 2008-2014.

Shen Z, Yang W. BP Neural Network Via Granular Computing for Prediction of Financial Trends [J]. Journal of Chinese Computer Systems, 2019, 40(03): 527-532.

Pan Q, Meng J, Zhang L, et al. Wavelet filtering method and its application[J]. Journal of Electronics & Information Technology, 2007, 29(1): 236-242.

Wu D. Analysis of Signals and Linear Systems(4th Edition)[M]. Higher Education Press, 2005.

Qiu T. Study on Approaches to Ontology Learning Oriented Granular Computing [D]. Beijing Jiaotong University, 2009.

Mao Y, Chunlin Y. Research on wind power real-time forecasting based on fuzzy granular computing [J]. Journal Of Northeast Electric Power University, 2017, 37(05): 1-7.

Moreira M.O, et al. Design of experiments using artificial neural network ensemble for phottaic generation forecasting[J]. Renewable and Sustainable Energy Reviews, 2021, 135110450-.

Xu G. Research on Intelligent Prediction of Photovoltaic Power Generation Considering the Influence of Multiple Factors [J]. Industrial Applications and Communications, 2023, 42(10): 162-166. 10. 20033/j. 1003-7241. (2023)10-0162-05.

Su Z, Zhang Z X, Piao Z L, et al. Application time series based on wavelet transform on wind power ultra-short term prediction[J]. Renewable Energy Resources, 2017, 9: 1381-1386.

Tang C Y, Miao R. Hydrological Time Series Decomposition and Period Identification Based on Wavelet Transform [J]. Yangtze River, 2006, (12): 32-34.

Walden, Andrew T . Wavelet methods for time series analysis /[M]. Cambridge University Press, 2000.

Downloads

Published

30-06-2024

How to Cite

Yang, Z., & Wang, S. (2024). Prediction model of photovoltaic power generation based on improved granular computing and neural networks. Highlights in Science, Engineering and Technology, 105, 62-73. https://doi.org/10.54097/dkbkvz97