Author(s)

Feng Huang ¹, Renyuan Jia ¹, Shixiong Bai ¹, Hong You ¹

Affiliation(s)

¹ School of Electrical and Information Engineering, Hunan Institute of Engineering, Xiangtan, 411101, China

Corresponding Author

ABSTRACT

In this paper, a short-term power forecasting model is established by using non-linear fitting characteristics of Support Vector Machine (SVM). A grid method based on Variational Mode Decomposition (VMD) is designed to optimize the short-term power forecasting algorithm. First, the wind power data is pre-processed and decomposed to 6 stable power components using VMD algorithm, thus reducing the impact of excessive forecasting errors of oscillatory points at peaks and valleys. Then, the grid search method is used to optimize the kernel function and penalty factor of the SVM to establish a short-term power forecasting model. Finally, each stable component data is processed using the Grid-SVM power forecasting model, and then the results are combined to get the final power forecasting value. Analysis of test results show that the forecasting accuracy is about three times that of the traditional SVM power forecasting model, is two times that of the Grid-SVM power forecasting model. The forecasting accuracy and speed meet the requirements for safe operation of wind farms.

KEYWORDS

CITE THIS PAPER

Feng Huang, Renyuan Jia, Shixiong Bai, Hong You, New Design of Short-Term Wind Power Forecasting Algorithm Based on VMD-Grid-SVM. Frontiers in Power and Energy Systems (2022) Vol. 1: 1-9. DOI: http://dx.doi.org/10.23977/fpes.2022.010101.

REFERENCES

[1] Li, J., Zhou J., & Chen, B. (2020). Review of wind power scenario generation methods for optimal operation of renewable energy systems. Applied Energy, 280, 1-18.
[2] Singh, A., & Idris, A. (2020). Evolution of renewable energy in India: wind and solar. Journal of the Institution of Engineers (India): Series C, 101 (2), 415-427.
[3] Wei, Z., Zhang, Y., & Shi, D., et al. (2020). Support vector machine-based diagnosis and prediction of diabetes complications based on grid search and cross validation. China Medical Equipment, 17 (08), 8-11.
[4] Santhosh, M., Venkaiah, C., & Vinod Kumar D. (2020). Current advances and approaches in wind speed and wind power forecasting for improved renewable energy integration: A review. Engineering Reports, 2 (6), 1-20.
[5] Zhao, Y., Ye, L., & Li, Z., et al. (2016). A novel bidirectional mechanism based on time series model for wind power forecasting. Appl Energy, 177, 793-803.
[6] Ding, W., & Wei, L. (2020). Impact of wind power forecasting on the stability of wind farm grid connection. Electrical Appliances, 05, 32-35.
[7] Fan, G., Wang, W., & Liu, C. (2008). A short-term wind power forecasting system based on artificial neural network. Power System Technology, 22, 72-76.
[8] Yan, H., & Lu, G. (2018). Application research on complete ensemble empirical mode decomposition, wavelet transform and convolutional neural networks in short-term wind speed forecasting. Computer Engineering and Applications, 54 (9), 224-230.
[9] Wu, Y., Huang, L., & Lin, J., et al. (2019). Research on the evaluation method of wind power forecasting system. Applied Energy Technology, 12, 38-44.
[10] Peng, T., Zhou, J., & Zhang, C., et al. (2017). Multi-step ahead wind speed forecasting using a hybrid model based on two-stage decomposition technique and AdaBoost-extreme learning machine. Energy Conversion and Management, 153, 589-602.
[11] Yu, M., Wang, B., & Zhang, L., et al. (2015). Wind speed forecasting based on EEMD and ARIMA. Proceedings of Chinese Automation Congress (CAC), Wuhan, China.
[12] Gang, Z., Liu, H., & Zhang, J., et al. (2019). Wind power prediction based on variational mode decomposition multi-frequency combinations. Journal of Modern Power Systems and Clean Energy, 000 (002), 281-288.
[13] Ru, D., Wang, X., & He, X. (2019). Short-term wind speed forecasting method based on hybrid particle swarm algorithm and multi-quantile robust extreme learning machine. Power System Protection and Control, 47 (5), 115-122.
[14] Zhang, W., Qu, Z., & Zhang, K., et al. (2017). A combined model based on CEEMDAN and modified flower pollination algorithm for wind speed forecasting. Energy Conversion and Management, 136, 439-451.
[15] Wang, Y., Zhu, Y., & Wang, Q., et al. (2020). Complex fault source identification method for high-voltage trip-offs of wind farms based on SU-MRMR and PSO-SVM. IEEE Access, 99, 1-1.
[16] Dragomiretskiy, K., & Zosso, D. (2014). Variational mode decomposition. IEEE Transactions on Signal Processing, 62 (3), 531-544.
[17] Anita, P., & Mayank, P. (2019). An improved model for breast cancer classification using SVM with grid search method. International Journal of Innovative Technology and Exploring Engineering, 8 (8), 2731-2734.
[18] Chang, X., Shen, H., & Nie, F., et al. (2014). Compound rank-k projections for bilinear analysis. IEEE Transactions on Neural Networks and Learning Systems, 27 (7):1502-1513.
[19] Chang, X., Yu, Y, L., & Yi, Y., et al. (2016) Semantic pooling for complex event analysis in untrimmed videos. IEEE Transactions on Software Engineering, PP (99): 1617-1632.
[20] Sahoo, S.R., & Gupta, B.B. (2020). Multiple features based approach for automatic fake news detection on social networks using deep learning. Applied Soft Computing, 100 (3).
[21] Viet, D., Phuong, V., & Duong, M., et al. (2020). Models for short-term wind power forecasting based on improved artificial neural network using particle swarm optimization and genetic algorithms. Energies, 13 (11), 2873.
[22] Deng, S., Wang, X., & Shi, S., et al. (2020). Prediction of grouting power time series based on FIG and GWO-SVM. Journal of Hohai University (Natural Science Edition), 48 (05), 426-432.
[23] Fu, C., Li, G., & Lin, K., et al. (2019). Short-Term wind power prediction based on improved chicken algorithm optimization support vector machine. Sustainability, 11 (512), 1-15.
[24] Zhong, Z., & Wan, S. (2012). Point-by-point Lagrange multiplier method considering crack contact friction. Journal of Southeast University (Natural Science Edition), 42 (5), 994-999.
[25] Gu, K. (2016). Research of parameter optimization for SVM based on improved grid search and its application. Lanzhou University of Technology.
[26] Wang, J. (2020). Variable step-grid searching method combines the LIBSVM to identify fan fault. China Southern Agricultural Machinery, 51 (11), 93-95.
[27] Wei, Z., Zhang, Y., & Shi, D., et al. (2020). Support vector machine-based diagnosis and prediction of diabetes complications based on grid search and cross validation. China Medical Equipment, 17 (08), 8-11.
[28] Wu, C., Yao, & H., Du, et al. (2013). Research on parameter selection of support vector regression. Applied Mechanics and Materials, 344, 219-225.
[29] Zhang, G., & Wan, F. (2016). Application of grid search-based SVM in intrusion detection. Computer Technology and Development, 26 (1), 97-100.

Sponsors, Associates, and Links

• Journal of Metallurgy and Mineral Processing
  
  
• International Journal of Oil and Gas Science and Engineering
  
  
• Journal of Disaster Prevention and Reduction
  
  
• Smart Systems and Green Energy
  
  
• Journal of Mining Engineering and Safety Technology
  
  
• Thermal Power Engineering
  
  
• Energy Conversion Research