Wind Power Probability Density Prediction Based on Quantile Regression Model of Dilated Causal Convolutional Neural Network*

doi:10.23919/CJEE.2023.000001

中国电气工程学报（英文） ›› 2023, Vol. 9 ›› Issue (1): 120-128.doi: 10.23919/CJEE.2023.000001

收稿日期:2021-03-15 修回日期:2021-07-19 接受日期:2021-08-24 出版日期:2023-03-25 发布日期:2023-04-06

Wind Power Probability Density Prediction Based on Quantile Regression Model of Dilated Causal Convolutional Neural Network^*

Yunhao Yang¹, Heng Zhang², Shurong Peng^3,*, Sheng Su³, Bin Li³

1. College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China;
2. State Grid Jining Electric Power Corporation, Jining 272100, China;
3. School of Electrical & Information Engineering, Changsha University of Science & Technology, Changsha 410114, China

Received:2021-03-15 Revised:2021-07-19 Accepted:2021-08-24 Online:2023-03-25 Published:2023-04-06
Contact: *E-mail: 173764138@qq.com
About author:Yunhao Yang is an undergraduate from the College of Computer Science and Technology, Zhejiang University, Hangzhou, China. His research interest includes the applications of deep learning algorithms in the field of data digging.
Heng Zhang received an M.S. degree in Electrical Engineering at Changsha University of Science and Technology (CSUST), Changsha, China. He is currently working for the State Grid Jining Electric Power Corporation.
Shurong Peng is an Assistant Professor. She received a B.S. degree in Industrial Automation in 1996, an M.S. degree in Control Theory and Control Engineering in 2004, and a PhD in Control Science and Engineering in 2009 from Hunan University, Changsha, China. She joined CSUST, Changsha, China in 2004. From 2012 to 2013, she was a Research Assistant in Darmstadt TU in Germany. Her research interests include information processing in an intelligent grid and big data applications in power systems.
Sheng Su (M'05-SM'19) received a BS degree in Electrical Engineering from Wuhan University of Hydraulic & Electrical Engineering, Wuhan, China in 1998, an MS degree in Electrical Engineering from Wuhan University, Wuhan, China in 2002, and a PhD degree from HUST, Wuhan, China in 2009. He joined CSUST, Changsha, China in 2002. From 2004 to 2007, he was a Research Assistant with Hong Kong Polytechnic University, Hong Kong, China. From 2009 to 2012, he is a Postdoctoral Researcher with the Department of Automatic Control Engineering, HUST, Wuhan, China. He is currently a Professor with CSUST, Changsha, China. His research interests include cyber security defense and the application of big data in power systems.
Bin Li received an MS degree from Changsha University of Science & Technology, China in 2019. He is working at the School of Mechanical and Electrical Engineering, Hunan City University. His current research fields include power system informatization, planning, and new energy.
Supported by:
*National Natural Science Foundation of China (51777015) and the Research Foundation of Education Bureau of Hunan Province (20A021).

摘要/Abstract

Abstract: Aiming at the wind power prediction problem, a wind power probability prediction method based on the quantile regression of a dilated causal convolutional neural network is proposed. With the developed model, the Adam stochastic gradient descent technique is utilized to solve the cavity parameters of the causal convolutional neural network under different quantile conditions and obtain the probability density distribution of wind power at various times within the following 200 hours. The presented method can obtain more useful information than conventional point and interval predictions. Moreover, a prediction of the future complete probability distribution of wind power can be realized. According to the actual data forecast of wind power in the PJM network in the United States, the proposed probability density prediction approach can not only obtain more accurate point prediction results, it also obtains the complete probability density curve prediction results for wind power. Compared with two other quantile regression methods, the developed technique can achieve a higher accuracy and smaller prediction interval range under the same confidence level.

Key words: Dilated causal neural network, nuclear density estimation, wind power probability prediction, quantile regression, probability density distribution

. [J]. 中国电气工程学报（英文）, 2023, 9(1): 120-128.

Yunhao Yang, Heng Zhang, Shurong Peng, Sheng Su, Bin Li. Wind Power Probability Density Prediction Based on Quantile Regression Model of Dilated Causal Convolutional Neural Network^*[J]. Chinese Journal of Electrical Engineering, 2023, 9(1): 120-128.

参考文献

[1] J Ouyang, M Li, Z Zhang, et al.Multi-timescale active and reactive power-coordinated control of large-scale wind integrated power system for severe wind speed fluctuation.IEEE Access, 2019, 7: 51201-51210.
[2] M B Ozkan, P Karagoz.Data mining-based upscaling approach for regional wind power forecasting: Regional statistical hybrid wind power forecast technique (Regional SHWIP).IEEE Access, 2019, 7: 171790-171800.
[3] L Wang, H Li, S Fang.The model of wind power short-term prediction based on artificial fish swarm algorithm of support vector machine.Journal of Electrical Engineering, 2016, 11(10): 7-12.
[4] P Chen, Q Meng, Y Zhao.The electric vehicle charging load calculation based on the Monte Carlo method.Journal of Electrical Engineering, 2016, 11(11): 40-46.
[5] S Zhu,M Yang,X Han,et al.Joint probability density forecast of short-term multiple wind farms output power.Automation of Electric Power Systems, 2014, 38(19): 8-15.
[6] J Yan,Y Liu,S Han,et al.Wind power grouping forecasts and its uncertainty analysis using optimized relevance vector machine.Renewable ＆ Sustainable Energy Reviews, 2013, 27(6): 613-621.
[7] L Wang,H Li,X Wu, et al.Wind power chaotic time series prediction model based on improved local Volterra adaptive filter.Electric Power Automation Equipment, 2016, 36(8): 40-44.
[8] W Wu, Y Qiao, Z Lu, et al.Methods and prospects for probabilistic forecasting of wind power.Automation of Electric Power Systems, 2017, 41(18): 167-175.
[9] C Wan, J Lin, J Wang, et al.Direct quantile regression for nonparametric probabilistic forecasting of wind power generation.IEEE Transactions on Power Systems, 2017, 32(4): 2767-2778.
[10] P Pinson.Very-short-term probabilistic forecasting of wind power with generalized logit-normal distributions.Journal of the Royal Statistical Society, Series C (Applied Statistics), 2021, 61(4): 555-576.
[11] W Can, X Zhao, P Pinson.Probabilistic forecasting of wind power generation using extreme learning machine.IEEE Trans. Power Systems, 2014, 29(3): 1033-1044.
[12] F Lan, C Sang, J Liang, et al.Interval prediction for wind power based on conditional copula function.Proceedings of the CSEE, 2016, 36(S1): 79-86.
[13] X Yang, X Ma, N Kang, et al.Probability interval prediction of wind power based on KDE method with rough sets and weighted Markov chain.IEEE Access, 2018, 6: 51556-51565.
[14] W Wu, K Chen, Y Qiao, et al.Probabilistic short-term wind power forecasting based on deep neural networks. 2016 International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), Beijing, 2016: 1-8.
[15] J W Taylor.A quantile regression neural network approach to estimating the conditional density of multiperiod returns.Journal of Forecasting, 2000, 19(4): 299-311.
[16] Y He, H Li.Probability density forecasting of wind power using quantile regression neural network and kernel density estimation.Energy Conversion and Management, 2018, 14(4): 374-384.
[17] A van den Oord, S Dieleman, H Zen, et al. WaveNet: A generative model for raw audio. arXiv:1609.03499v2. 2016-09-19. https://doi.org/10.48550/arXiv.1609.03499.
[18] G Kechyn, L Yu, Y Zang, et al. Sales forecasting using WaveNet within the framework of the Kaggle competition. arXiv:1803.04037v1[cs.LG]. 2018-03-11. https://doi.org/10.48550/arXiv.1803.04037.
[19] A Borovykh, S Bohte, C W Oosterlee. Conditional time series forecasting with convolutional neural networks. arXiv:1703.04691v3[stat.ML]. 2017-10-16. https://doi.org/10.48550/arXiv.1703.04691.

Wind Power Probability Density Prediction Based on Quantile Regression Model of Dilated Causal Convolutional Neural Network^*

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价