|
|
基于支持向量分位数回归神经网络的区域短期风速预测
|
Abstract:
由于风速的间歇性导致了风电系统输出的波动性，可靠的风速预测可以有效提高风电装置的稳定性。在分位数回归的框架下，提出了支持向量–分位数回归神经网络(SV-QRNN)模型。首先，采用粒子群优化算法对支持向量机参数进行优化，得到支持向量。然后采用分位数回归神经网络算法推导出风速的条件分位数，以及不同置信度下的预测区间。实验结果表明，SV-QRNN模型能够较好地平衡预测性能和时间效率。同时还可以补贴发电调度决策，并允许电力市场充分发挥作用。
Due to the intermittent nature of wind speed, reliable wind speed prediction improves the volatility of wind system output due to wind speed instability. This paper proposes a support vector-qu- antile regression neural network (SV-QRNN) model under the framework of quantile regression. To begin with, particle swarm optimization algorithm is employed to optimize the parameters of support vector machine to obtain the support vector. Then the quantile regression neural network algorithm is adopted to derive the conditional quantile of wind speed, and the prediction interval under different confidence levels is obtained. The experimental results illustrate that the SV-QRNN model can better balance the prediction performance and time efficiency by comparing several other competitive models based on interval prediction. It can also subsidize generation scheduling decisions and allow the full performance of the electricity market.
| [1] | Liu, Y., Zhang, S., Chen, X., et al. (2018) Artificial Combined Model Based on Hybrid Nonlinear Neural Network Models and Statistics Linear Models—Research and Application for Wind Speed Forecasting. Sustainability, 10, 4601.
https://doi.org/10.3390/su10124601 |
| [2] | Miranda, M.S. and Dunn, R.W. (2006) One-Hour-Ahead Wind Speed Prediction Using a Bayesian Methodology. Power Engineering Society General Meeting IEEE, Montreal, 18-22 June 2006.
https://doi.org/10.1109/PES.2006.1709479 |
| [3] | Yang, X.Y., Yang, X. and Chen, S.Y. (2005) Wind Speed and Generated Power Forecasting in Wind Farm. Proceedings of the CSEE, Vol. 25, 1-5. |
| [4] | Ribeiro, G.T., Mariani, V.C. and dos Santos Coelho, L. (2019) Enhanced Ensemble Structures Using Wavelet Neural Networks Applied to Short-Term Load Forecasting. Engineering Applications of Artificial Intelligence, 82, 272-281.
https://doi.org/10.1016/j.engappai.2019.03.012 |
| [5] | Lei, M., Luan, S., Jiang, C., et al. (2009) A Review on the Forecasting of Wind Speed and Generated Power. Renewable & Sustainable Energy Reviews, 13, 915-920. https://doi.org/10.1016/j.rser.2008.02.002 |
| [6] | Costa, A., et al. (2008) A Review on the Young History of the Wind Power Short-Term Prediction. Renewable and Sustainable Energy Reviews, 12, 1725-1744. https://doi.org/10.1016/j.rser.2007.01.015 |
| [7] | Wang, H., et al. (2019) Sequence Transfer Correction Algorithm for Numerical Weather Prediction Wind Speed and Its Application in a Wind Power Forecasting System. Applied Energy, 237, 1-10.
https://doi.org/10.1016/j.apenergy.2018.12.076 |
| [8] | Lin, Y., Zhao, Y., Cheng, Z., et al. (2017) Short-Term Wind Power Prediction Based on Spatial Model. Renewable Energy, 101, 1067-1074. https://doi.org/10.1016/j.renene.2016.09.069 |
| [9] | Gomes, P. and Rui, C. (2012) Wind Speed and Wind Power Forecasting Using Statistical Models: Auto-Regressive Moving Average (ARMA) and Artificial Neural Networks (ANN). International Journal of Sustainable Energy Development (IJSED), 1, 41-50. https://doi.org/10.20533/ijsed.2046.3707.2012.0007 |
| [10] | Hodge, B.-M., et al. (2011) Improved Wind Power Forecasting with ARIMA Models. Computer Aided Chemical Engineering, 29, 1789-1793. https://doi.org/10.1016/B978-0-444-54298-4.50136-7 |
| [11] | Long, Y., et al. (2017) Impact of Meteorological Factors on the Incidence of Bacillary Dysentery in Beijing, China: A Time Series Analysis (1970-2012). PLoS ONE, 12, e0182937. https://doi.org/10.1371/journal.pone.0182937 |
| [12] | Zhou, J.Y., Shi, J. and Li, G. (2010) Fine Tuning Support Vector Machines for Short-Term Wind Speed Forecasting. Energy Conversion and Management, 52, 1990-1998. https://doi.org/10.1016/j.enconman.2010.11.007 |
| [13] | Lahouar, A. and Ben Hadj Slama, J. (2017) Hour-Ahead Wind Power Forecast Based on Random Forests. Renewable Energy, 109, 529-541. https://doi.org/10.1016/j.renene.2017.03.064 |
| [14] | Zhang, Z.D., et al. (2019) Wind Speed Prediction Method Using Shared Weight Long Short-Term Memory Network and Gaussian Process Regression. Applied Energy, 247, 270-284. https://doi.org/10.1016/j.apenergy.2019.04.047 |
| [15] | Mi, X., Hui, L. and Li, Y. (2019) Wind Speed Prediction Model Using Singular Spectrum Analysis, Empirical Mode Decomposition and Convolutional Support Vector Machine. Energy Conversion and Management, 180, 196-205.
https://doi.org/10.1016/j.enconman.2018.11.006 |
| [16] | Wang, J.J. and Li, Y.N. (2019) An Innovative Hybrid Approach for Multi-Step Ahead Wind Speed Prediction. Applied Soft Computing Journal, 78, 296-309. https://doi.org/10.1016/j.asoc.2019.02.034 |
| [17] | Zhou, Q., Wang, C. and Zhang, G. (2019) Hybrid Forecasting System Based on an Optimal Model Selection Strategy for Different Wind Speed Forecasting Problems. Applied Energy, 250, 1559-1580.
https://doi.org/10.1016/j.apenergy.2019.05.016 |
| [18] | Moreno, S.R. and dos Santos Coelho, L. (2018) Wind Speed Forecasting Approach Based on Singular Spectrum Analysis and Adaptive Neuro Fuzzy Inference System. Renewable Energy, 126, 736-754.
https://doi.org/10.1016/j.renene.2017.11.089 |
| [19] | Jureckova, J. (2006) Quantile Regression. Journal of the American Statistical Association, 101, 1723-1723.
https://doi.org/10.1198/jasa.2006.s143 |
| [20] | Cannon, A.J. (2010) Quantile Regression Neural Networks: Implementation in R and Application to Precipitation Downscaling. Computers and Geosciences, 37, 1277-1284. https://doi.org/10.1016/j.cageo.2010.07.005 |
| [21] | Wang, J. (2012) Bayesian Quantile Regression for Parametric Nonlinear Mixed Effects Models. Statistical Methods & Applications, 21, 279-295. https://doi.org/10.1007/s10260-012-0190-7 |
| [22] | Taylor, J.W. (2000) A Quantile Regression Neural Network Approach to Estimating the Conditional Density of Multiperiod Returns. Journal of Forecasting, 19, 299-311.
https://doi.org/10.1002/1099-131X(200007)19:4<299::AID-FOR775>3.0.CO;2-V |
| [23] | He, Y.Y. and Li, H.Y. (2018) Probability Density Forecasting of Wind Power Using Quantile Regression Neural Network and Kernel Density Estimation. Energy Conversion and Management, 164, 374-384.
https://doi.org/10.1016/j.enconman.2018.03.010 |
| [24] | Cran—Package QRNN. https://cran.r-project.org/web/packages/qrnn |
| [25] | Zhang, W., Quan, H. and Srinivasan, D. (2018) An Improved Quantile Regression Neural Network for Probabilistic Load Forecasting. IEEE Transactions on Smart Grid, 10, 4425-4434. https://doi.org/10.1109/TSG.2018.2859749 |
| [26] | Xu, Q., Deng, K., Jiang, C., et al. (2017) Composite Quantile Regression Neural Network with Applications. Expert Systems with Applications, 76, 129-139. https://doi.org/10.1016/j.eswa.2017.01.054 |
| [27] | Quan, H., Srinivasan, D. and Khosravi, A. (2014) Uncertainty Handling Using Neural Network-Based Prediction Intervals for Electrical Load Forecasting. Energy, 73, 916-925. https://doi.org/10.1016/j.energy.2014.06.104 |
| [28] | Ravi, V., Tejasviram, V., Sharma, A. and Khansama, R.R. (2017) Prediction Intervals via Support Vector-Quantile Regression Random Forest Hybrid. The 10th Annual ACM India Compute Conference, Bhopal, 16-17 November 2017, 129- 139. https://doi.org/10.1145/3140107.3140122 |
| [29] | Song, Q.S., et al. (2021) Robust Principal Component Analysis and Support Vector Machine for Detection of Microcracks with Distributed Optical Fiber Sensors. Mechanical Systems and Signal Processing, 146, Article ID: 107019.
https://doi.org/10.1016/j.ymssp.2020.107019 |
| [30] | Kouziokas, G.N. (2020) SVM Kernel Based on Particle Swarm Optimized Vector and Bayesian Optimized SVM in Atmospheric Particulate Matter Forecasting. Applied Soft Computing Journal, 93, Article ID: 106410.
https://doi.org/10.1016/j.asoc.2020.106410 |
| [31] | Zhou, Z.H. (2016) Machine Learning. Tsinghua University Press, Beijing. |
| [32] | Ordiano, J.G., Grll, L., Mikut, R., et al. (2019) Probabilistic Energy Forecasting Using Quantile Regressions Based on a New Nearest Neighbors Quantile Filter. |
| [33] | Chopra, N., Kumar, G. and Mehta, S. (2016) Hybrid GWO-PSO Algorithm for Solving Convex Economic Load Dispatch Problem. International Journal of Research in Advent Technology, 4, 37-41. |
| [34] | Zhang, G., Patuwo, B.E. and Hu, M.Y. (1998) Forecasting with Artificial Neural Networks: The State of the Art. International Journal of Forecasting, 14, 35-62. https://doi.org/10.1016/S0169-2070(97)00044-7 |
| [35] | Takeuchi, I. and Furuhashi, T. (2005) Non-Crossing Quantile Regressions by SVM. IEEE International Joint Conference on Neural Networks, Budapest, 25-29 July 2004, 1942-1948. |
| [36] | Kennedy, J. (2011) Particle Swarm Optimization. Proceedings of 1995 IEEE International Conference on Neural Networks, Perth, Vol. 4, 1942-1948. |
| [37] | Khosravi, A., Nahavandi, S. and Creighton, D. (2009) A Prediction Interval-Based Approach to Determine Optimal Structures of Neural Network Metamodels. Expert Systems with Applications, 37, 2377-2387.
https://doi.org/10.1016/j.eswa.2009.07.059 |
| [38] | Khosravi, A., Nahavandi, S. and Creighton, D. (2011) Prediction Interval Construction and Optimization for Adaptive Neurofuzzy Inference Systems. IEEE Transactions on Fuzzy Systems, 19, 983-988.
https://doi.org/10.1109/TFUZZ.2011.2130529 |
| [39] | Khosravi, A., Nahavandi, S., Creighton, D. and Atiya, A.F. (2011) Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals. IEEE Transactions on Neural Networks, 22, 337-346.
https://doi.org/10.1109/TNN.2010.2096824 |
| [40] | He, Y.Y., et al. (2019) Electricity Consumption Probability Density Forecasting Method Based on LASSO-Quantile Regression Neural Network. Applied Energy, 233-234, 565-575. https://doi.org/10.1016/j.apenergy.2018.10.061 |
