Research on Wind Power Prediction Model Based on Random Forest and SVR

Zehui Wang; Dianwei Chi

doi:10.4108/ew.5758

Authors

Zehui Wang Yantai University
Dianwei Chi Yantai Institute of Technology

DOI:

https://doi.org/10.4108/ew.5758

Keywords:

PCA, random forest, SVR, wind power, prediction

Abstract

Wind power generation is random and easily affected by external factors. In order to construct an effective prediction model based on wind power generation, a wind power prediction model based on principal component analysis (PCA) noise reduction, feature selection based on random forest model and support vector regression (SVR) algorithm is proposed. First, in the data preprocessing stage, PCA is used for sample data denoising; then the random forest model is used to calculate the importance evaluation value of each feature to optimize the selection of feature parameters; finally, The SVR algorithm is applied for training and prediction. Experiments show that the prediction effect of the model based on random forest and SVR is excellent, the root mean square error(RMSE) is 0.086, the average absolute percentage error(MAPE) is 23.47%, and the coefficient of determination(R2) is 0.991. Compared with the traditional SVR model, the root mean square error of the method proposed in this paper is reduced by 95.9%, and the prediction accuracy and the fit of the prediction curve are significantly improved.

Downloads

Download data is not yet available.

References

Ma,W.Z.; Cheng, R.L.; Shi, J.;Hua, D.; Sun, G.S.; Zhang, C. Imitation interval tide calculation considering wind farm model[J]. Guangdong Electric Power, 2019, 32(11): 10. DOI: https://doi.org/10.3390/en11113176

Han, Z.F.; Jing, Q.M.; Zhang, Y.K. Overview of wind power forecasting methods and new trends[J]. Power System Protection and Control, 2019, 47(24):10.

Ma, T.T.; Wang, C.; Peng, L.L. Power system short-term load forecasting considering demand response and deep structure multi-task learning[J]. Electrical Measurement and Instrumentation, 2019,56(16):50-60.

Wang,Y.Q.; Wang, Y.L.; Wang, L.B. An improved fruit fly algorithm optimizes the neural network short-term load forecasting model[J]. Electrical Measurement & Instrumentation, 2018, 55(22):7.

Ge, W.C.; Sun, P.; Li, J.J.; Hui, X.; Kong, X. Robust estimation model of wind power prediction confidence under different scenarios during peak load hours of power grid[J]. High Voltage Technology,2019,45(04):1281-1288.

Liu, X.J. Wind power output prediction methods and systems [D]. North China University of Electric Power, 2011.

Zhang, K.; Qu, Z.; Wang, J.; Zhang, W.; Yang, F. A novel hybrid approach based on cuckoo search optimization algorithm for short-term wind speed forecasting[J]. ENVIRONMENTAL PROGRESS & SUSTAINABLE ENERGY, 2017, 36(2):943-952. DOI: https://doi.org/10.1002/ep.12533

Zhang, H.C. Research on short-term power prediction method for wind farms based on neural network combination model[D]. Hunan University of Technology,2019.

Li, L.L.;Xu,Y.H.; Tian, X.Y.; Niu,Y.T. Short-term prediction of wind power based on combined model[J]. Journal of Electrical Engineering Technology,2014,29(S1):475-480.

Wang, T.; Gao, J.; Wang, Y.Y. Research on wind power power prediction based on improved empirical mode decomposition and support vector machine [J/OL]. Electrical Measurement and Instrumentation: 1-6 [2020-9-24]

Zhao, R.Z.; Ding, Y.F. Short-term wind power prediction based on MEEMD-KELM[J]. Electrical Measurement & Instrumentation, 2020, 57(21):7.

Huang, X.X.; Yu, H.J.; Gong, X.Y. Short-term prediction of wind power based on PSO-GA-SVM[J]. Electrical Engineering Technology, 2020(6): 4.

Huang, F.; Xiang, X.C.; Wang, R.; Jia, R.Y, You, H. A Short-Term Wind Power Prediction Algorithm Based on VMD-PSO-SVM [J]. Journal of Hunan Institute of Engineering (Natural Science Edition), 2022, 32( 02):7-12.

Zhao, X.; Wang, W.J.; Zeng, Y.Y. Improved modular PCA new algorithm for face recognition [J]. Computer Engineering and Applications, 2015, 51(2):161-164, 175.

Dong, E.Z.;Wei, K.X.;Yu, X. A car model recognition algorithm incorporating PCA with LBP feature reduction [J]. Computer Engineering and Science, 2017, 39(2): 359-363.

Dong, H. Non-convex compressed sensing reconstruction based on PCA dictionary and two-stage optimization [D]. Xi'an: Xidian University, 2013.

Huang, R.J.;Sun, W.D.; Guang, L.Manifold-based constraint Laplacian score for multi-label feature selection.[J].Pattern Recognition Letters,2018.112346-352. DOI: https://doi.org/10.1016/j.patrec.2018.08.021

Cai. J.; Luo, J.W.;Yang, S..Feature selection in machine learning: A new perspective[J].Neurocomputing,2018,300(Jul.26).70-79. DOI: https://doi.org/10.1016/j.neucom.2017.11.077

Mursalin Md,Chen Yuehui,Chawla Nitesh V.,et al.Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier[J].Neurocomputing,2017,241(Jun.7).204-214 . DOI: https://doi.org/10.1016/j.neucom.2017.02.053

Lin, C.D.; Peng, G.L. Application of Random Forest in the Determination of Enterprise Credit Evaluation Index System[J]. Journal of Xiamen University: Natural Science Edition, 2007, 46(2): 5.

Zhang, H.L.; Gao, X.L.; Liu, Y.Q. Comparative study on the adaptability of three mainstream wind farm power measurement algorithms [J]. Modern Electric Power, 2015, 32(6): 15-20.

Zhou, Q.; Mou,C.; Yang, D. Overview of the Research Progress of Educational Data Mining[J]. Journal of Software, 2015, 26(11): 3026-3042.