Ultra-short-term Probabilistic Forecasting of Wind Power Based on Temporal Mixture Density Network

被引：0
|
作者：
Dong X. [1 ]
Sun Y. [1 ]
Pu T. [2 ]
Wang X. [2 ]
Li Y. [2 ]
机构：
[1] School of Electrical and Electronics Engineering, North China Electric Power University, Beijing
[2] China Electric Power Research Institute, Beijing
来源：
Dianli Xitong Zidonghua/Automation of Electric Power Systems | 2022年 / 46卷 / 14期
基金：
中国国家自然科学基金;
关键词：
interpretability; maximum likelihood estimation; mixture density network; probabilistic forecasting; temporal convolutional network; wind power;
D O I：
10.7500/AEPS20211208003
中图分类号：
学科分类号：
摘要：
Probabilistic forecasting of wind power can provide critical boundary conditions for the safe operation of new power systems. Improving forecasting accuracy is the key problem of the research for probabilistic forecasting of wind power, and improving the interpretability of implicit models is beneficial to the promotion and application of artificial intelligence models. Therefore, a temporal mixture density network is proposed, which extracts the local moment information of time series data of wind power as input channels. The temporal convolutional network is used to extract the multi-time-scale probabilistic features, and the mixed Beta distribution is used to construct the probabilistic forecasting information. The results of the case study show that the local moment channel effectively improves the convergence of the model training, and the mixed distribution parameters extracted by the temporal mixture density network have a certain interpretability. Compared with the existing models, the forecasting results of the temporal mixture density network have better accuracy. © 2022 Automation of Electric Power Systems Press. All rights reserved.
引用
收藏
页码：93 / 100
页数：7
相关论文
共 24 条
  • [1] WAN Can, SONG Yonghua, Theories， methodologies and applications of probabilistic forecasting for power systems with renewable energy sources［J］, Automation of Electric Power Systems, 45, 1, pp. 2-16, (2021)
  • [2] WANG J H，, MANTHOURI M., Interval deep generative neural network for wind speed forecasting［J］, IEEE Transactions on Smart Grid, 10, 4, pp. 3974-3989, (2019)
  • [3] YANG Mao, DONG Hao, Short-term wind power interval prediction based on wind speed of numerical weather prediction and Monte Carlo method［J］, Automation of Electric Power Systems, 45, 5, pp. 79-85, (2021)
  • [4] Direct quantile regression for nonparametric probabilistic forecasting of wind power generation［J］, IEEE Transactions on Power Systems, 32, 4, pp. 2767-2778, (2017)
  • [5] HAN X S，, YANG M，, Et al., Probabilistic prediction of regional wind power based on spatiotemporal quantile regression［J］, IEEE Transactions on Industry Applications, 56, 6, pp. 6117-6127, (2020)
  • [6] LIU Yanhua, LI Weihua, LIU Chong, Et al., Mixed skew distribution model of short-term wind power prediction error［J］, Proceedings of the CSEE, 35, 10, pp. 2375-2382, (2015)
  • [7] LI H Y., Probability density forecasting of wind power using quantile regression neural network and kernel density estimation［J］, Energy Conversion and Management, 164, pp. 374-384, (2018)
  • [8] LI K, BAI E W，, Et al., Hybrid probabilistic wind power forecasting using temporally local Gaussian process［J］, IEEE Transactions on Sustainable Energy, 7, 1, pp. 87-95, (2016)
  • [9] GIORGIO M，, LANGELLA R，, Et al., Markov chain modeling for very-short-term wind power forecasting［J］, Electric Power Systems Research, 122, pp. 152-158, (2015)
  • [10] DING Teng, FENG Donghan, LIN Xiaofan, Et al., Ultra-short-term wind speed forecasting based on improved ARIMA-GARCH model ［J］, Power System Technology, 41, 6, pp. 1808-1814, (2017)
123