In recent years, the combination of modern power grid system and renewable energy has put forward higher requirements for the accurate prediction of electric power. Under this background, the CNN-LSTM model combines the spatial feature recognition of CNN and the time series analysis of LSTM, providing a novel and effective method for power prediction. In the empirical analysis, the wind power data set collected in this paper mainly includes wind power, wind speed, wind direction, air pressure, air density, temperature, etc. The wind power data set contains massive multidimensional data for verification, and the results show that the proposed CNN-LSTM model has high accuracy and reliability in power power prediction. Test set results RMSE=9100.1494, SMAPE=0.72639%. Compared with the traditional method, the model can capture the nonlinear relationship in the data better, improve the prediction accuracy, and provide more scientific decision basis for the power system management department. The results of this study are expected to promote the intelligent development of power system and provide theoretical support for the promotion and application of clean energy.

Jiayi Wang. Electric Power Prediction Based On CNN-LSTM Network Model. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 11: 67-71. https://doi.org/10.25236/AJCIS.2024.071109.

[1] Tang J, He B, Zhou B, et al. Process Quality Prediction Method Based on CNN_LSTM Hybrid Neural Network Model[J]. Ocean engineering, 2023.

[2] Sun B, Liu X, Wang J, et al. Short-term performance degradation prediction of a commercial vehicle fuel cell system based on CNN and LSTM hybrid neural network[J]. International Journal of Hydrogen Energy, 2023, 48(23):8613-8628.

[3] Han Z, Lv H, Liang Z, et al. Transmission line icing thickness prediction model based on ISSA-CNN-LSTM[J]. Journal of Physics: Conference Series, 2023, 2588(1).

[4] Wang K, Wu C, Shi J. Prediction of battery temperature in electric bus charging stage based on CNN-LSTM [J]. Applied Energy, 2023, 367.

[5] Dong Z, Yao L, Bao Y, et al. Prediction of Soil Organic Carbon Content in Complex Vegetation Areas Based on CNN-LSTM Model[J]. Soil Science & Plant Nutrition, 2024, 53(3).

[6] Zhang D, Wang S. A protein succinylation sites prediction method based on the hybrid architecture of LSTM network and CNN[J]. Journal of Bioinformatics and Computational Biology, 2022(2):20. DOI:10.1142/S0219720022500032.

[7] Zhang J, Zhao Z, Yan J C P. Ultra-Short-Term Wind Power Forecasting Based on CGAN-CNN-LSTM Model Supported by Lidar[J]. Sensors, 2023, 23(9).

[8] Wang C, Zhang M. Research on dynamic rolling force prediction model based on CNN-BN-LSTM[J]. Journal of Advanced Mechanical Design, Systems, and Manufacturing, 2022. DOI:10.1299/jamdsm.2022jamdsm0029.

[9] Heng F, Gao J, Xu R, et al. Multiaxial fatigue life prediction for various metallic materials based on the hybrid CNN‐LSTM neural network[J]. Fatigue & Fracture of Engineering Materials & Structures, 2023. DOI:10.1111/ffe.13977.