College of Electrical Engineering, Xinjiang University, Urumqi 830017, China
Show less
文章历史+
Received
Published
Revised
2025-03-27
2028-07-28
2025-11-06
Online Date
2026-09-20
PDF (9435K)
摘要
精准的风电功率预测对于新型电力系统的安全稳定运行和经济调度至关重要。针对传统点预测无法充分反映风电功率不确定性的问题,提出一种短期风电功率点预测与区间预测相结合的模型。首先,采用霜冰优化算法(rime optimization algorithm, RIME)优化变分模态分解(variational mode decomposition, VMD)参数,并对风电功率进行VMD分解。其次,应用皮尔逊相关系数法选取与风电功率关联性较大的气象因素,作为卷积神经网络-双向长短期记忆网络(convolutional neural network-bidirectional long short-term memory network, CNN-BiLSTM)预测模型的输入,最终将得到的各分量预测值叠加得到总点预测值。接着,在点预测的基础上构建自适应核密度估计(adaptive kernel density estimation, AKDE)区间预测模型,即解决了传统核密度估计在不同置信水平下鲁棒性较差的问题,也有效量化了风电功率预测的不确定性。最后,通过对新疆某风电场实测数据的验证与对比分析,得出本文方法在提升风电功率确定性预测精度和区间预测鲁棒性方面具有显著优势。
Abstract
Accurate wind power prediction is of vital importance for the secure and stable operation and economic dispatch of new-type power systems. To address the issue that traditional point prediction fails to reflect the uncertainty of wind power, a combined model of short-term point and interval prediction was proposed. First, the rime optimization algorithm (RIME) was used to optimize the parameters of variational mode decomposition (VMD), and VMD decomposition was performed on wind power. Then, meteorological factors with high correlation to wind power were selected using the Pearson correlation coefficient method,which were used as input for the convolutional neural network-bidirectional long short-term memory network(CNN-BiLSTM) prediction model. The point prediction was obtained by summing the predictions of all decomposed components. Next, based on the point forecast, an adaptive kernel density estimation (AKDE) model was constructed for interval prediction. The AKDE method improved robustness under different confidence levels and effectively quantifies uncertainty in wind power prediction. Finally, the model was validated using measured data from a wind farm in Xinjiang. The results show that the proposed method improves the accuracy of deterministic forecasting and enhances the robustness of interval prediction.
WUMUERWUZHAKE Ahezhuli, ABULIZI Maimaitireyimu, WU Xu-kun, XIE Li-rong.
Short-term Wind Power Interval Prediction Based on RIME-VMD and Adaptive Kernel Density Estimation[J].
Science Technology and Engineering, 2026, 26(3): 1054-1064 DOI:10.12404/j.issn.1671-1815.2502090
通过对图11中采用自适应带宽拟合得到的PDF求积分,可得到对应的累积概率密度函数(cumulative distribution function, CDF),从而获得给定置信区间下的误差分布边界,如图12所示。从图12中可以得出,在不同置区间下风电功率预测误差的上下界,取分位点为α=2.5%、α=5%和α=7.5%,就能获得置信区间为95%、90%和85%下的风电功率波动区间。
YangRenzheng, HuangYanguo, HeXuan. Short-term wind power prediction based on SSA-BiLSTM and singular spectrum analysis[J]. Science Technology and Engineering, 2024, 24(22): 9392-9399.
[3]
ZhaoX, SunB, WuN, et al. A new short-term wind power prediction methodology based on linear and nonlinear hybrid models[J]. Computers & Industrial Engineering, 2024, 196: 110477.
[4]
XuW, DaiW, LiD, et al. Short-term wind power prediction based on a variational mode decomposition-BiTCN-psformer hybrid model[J]. Energies, 2024, 17(16): 4089.
DingTingting, YangMing, YuYixiao, et al. Short-term wind power integration prediction method based on error correction[J]. High Voltage Engineering, 2022, 48(2): 488-496.
ShangLiqun, LiHongbo, HuangChenhao, et al. Short-term wind power prediction based on multivariate phase space reconstruction and optimized deep extreme learning machine[J]. Southern Power System Technology, 2023, 17(2): 82-91.
WuHuijun, GuoChaoyu, SuChengguo, et al. Combined prediction method for short-term wind power based on EEMD-GRU-MC[J]. Southern Power System Technology, 2023, 17(2): 66-73.
XiYulian, LingZhouyue, XuXiaomin. Research on short-term wind power CEEMDAN-SMA-LSSVM prediction model[J]. Science Technology and Engineering, 2024, 24(6): 2396-2404.
ChenFeng, YuYi, XuJingyou, et al. Prediction method of wind power output based on a Bayes-LSTM network[J]. Power System Protection and Control, 2023, 51(6): 170-178.
XiaoLiexi, ZhangYu, ZhouHui, et al. Ultra short term wind power prediction based on IAOA-VMD-LSTM[J]. Acta Energiae Solaris Sinica, 2023, 44(11): 239-246.
WangYaojian, GuJie, WenHonglin, et al. Short-term wind power probability prediction based on online Gaussian process regression[J]. Automation of Electric Power Systems, 2024, 48(11): 197-207.
[21]
HouG, WangJ, FanY, et al. A novel wind power deterministic and interval prediction framework based on the critic weight method, improved northern goshawk optimization, and kernel density estimation[J]. Renewable Energy, 2024, 226: 120360.
[22]
ZhaW, LiX, DuY, et al. Interval forecast method for wind power based on GCN-GRU[J]. Symmetry, 2024, 16(12): 1643.
XiaoBai, ZhangBo, WangXinwei, et al. Short-term wind power interval prediction based on combined mode decomposition and deep learning[J]. Automation of Electric Power Systems, 2023, 47(17): 110-117.
CuiXiwen, ZhangXiaodan, NiuDongxiao. An Ultra-short-term wind power point-interval prediction based on two-layer decomposition and MOISMA-SVM[J/OL]. (2024-11-06)[2025-03-2 7]. https://link.cnki.net/urlid/31.1289.tp.20241106.1306.004.
ZhangXuejing, HuHuanling, LingLiwen, et al. Interval prediction of agricultural price based on SSA-LSSVM-KDE[J]. Journal of Systems Science and Mathematical Sciences, 2024, 44(4): 1081-1096.
[29]
DragomiretskiyK, ZossoD. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
ShangLiqun, LiHongbo, HouYadong, et al. Short-term photovoltaic power generation prediction based on VMD-ISSA-KELM[J]. Power System Protection and Control, 2022, 50(21): 138-148.
[32]
SuH, ZhaoD, AliA H, et al. RIME: a physics-based optimization[J]. Neurocomputing, 2023, 532: 183-214.
YuWei, HuangHao, JinChenxing, et al. Ultra-short-term wind power forecasting based on multi-head self-attention feature transform and CNN-LSTM[J/OL]. (2024-12-05) [2025-03-27]. https://link.cnki.net/urlid/44.1643.tk.20241205.0934.002.
[38]
HouG L, WangJ J, FanY Z, et al. A novel wind power deterministic and interval prediction framework based on the critic weight method, improved northern goshawk optimization, and kernel density estimation[J]. Renewable Energy, 2024, 226: 120360.
MaWei, QiaoYing, LuZongxiang, et al. Short-term wind power prediction based on combination of screening and optimizing sensitive meteorological characteristics[J]. Power System Technology, 2023, 47(7): 2897-2908.