基于改进贝叶斯优化的TCN-GRU 风光功率预测

© 2025 by the Author(s). Licensee Art and Technology, USA. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC BY-NC 4.0) ( https://creativecommons.org/licenses/by-nc/4.0/ )

Download PDF

Cite

XML

HTML

Abstract

【目的】风能和太阳能因其清洁、可再生的特性，在能源转型中发挥着关键作用，但其出力受自然条件制约，兼具强随机性与波动性，导致功率预测难度显著提升。因此，提高二者的预测精度与效率成为亟待解决的问题。【方法】本文提出了一种基于改进自适应经验模态分解（improved complete ensemble empirical mode de- composition with adaptive noise，ICEEMDAN）和改进贝叶斯优化（surrogate safety-aware bayesian optimization，SSABO）的时域卷积网络- 门控循环单元（temporal con- volutional network - gated recurrent unit，TCN-GRU）风光功率综合预测模型，并结合自适应带宽核密度估计（adap- tive bandwidth kernel density estimation，ABKDE）实现区间预测，以量化出力波动的不确定性。其中，ICEEMDAN 算法通过自适应信号分解，有效抑制模态混叠问题，降低噪声干扰，充分提取数据特征。TCN-GRU 模型简化了模型结构并提高了计算效率；引入SSABO 优化关键参数，模型的收敛速度更快、寻优精度更高，显著提升了训练效率和预测精度。【结果】研究表明：ICEEMDAN 算法有效解决了伪模态问题，数据分解效果优于传统CEEMDAN；SSABO 优化后的TCN-GRU 模型在风电和光伏数据集上的预测误差较未优化模型均有较大幅度的降低；ABKDE 区间预测在不同置信水平下的覆盖率均优于理论值，验证了模型输出不确定性的可靠性。【结论】该模型适用于不同能源类型的预测，且具备较高的精度和效率，为风光功率预测提供了一种有效的解决方案。

Keywords

风光互补发电系统

功率预测

CNN-GRU 模型

贝叶斯优化

区间预测

预测误差

稳定性

References

[1] 周金涛,何山,王维庆,等.基于黑翅鸢算法和VMD的短期风电功率预测[J].太阳能学报,2025,46(12):762-773.
ZHOU Jintao,HE Shan,WANG Weiqing,et al.Short- Term Wind Power Prediction based on Black-winged Kite Algorithm and Vmd[J].Acta Energiae Solaris Sinica,2025,46(12):762-773.

[2] 白婕,秦晓辉,安鹏,等.计及高影响天气事件的风光长期时间序列预测研究现状与关键技术展望[J].电网技术,2026,50(2):829-848.
BAI Jie,QIN Xiaohui,AN Peng,et al.Research Status and Key Technology Prospects of Long-term Time Series Forecasting of Wind and Solar Power Consid- ering the High-impact Weather Events[J].Power System Technology,2026,50(2):829-848.

[3] 黄晟,潘丽君,屈尹鹏,等.基于改进深度Q网络的无预测风电场日前拓扑优化[J].电力系统自动化,2025, 49(2):122-132.
HUANG Sheng,PAN Lijun,QU Yinpeng,et al.Day- ahead Topology Optimization for Wind Farm without Forecasting based on Improved Deep Q Network[J]. Automation of Electric Power Systems,2025,49(2): 122-132.

[4] 杨超颖,赵军,李慧蓬,等.基于时序特征交互与功率气象特征融合的风电超短期预测方法[J/OL].华北电力大学学报(自然科学版),2025:1-10.(2025-12-17). https: //link.cnki.net/urlid/10.1999.tm.20251217.0910.002.
YANG Chaoying,ZHAO Jun,LI Huipeng,et al.Ultra- Short-Term Wind Power Forecasting Based on Tempor- al Feature Interaction and Power-Meteorological Feat- ure Fusion[J/OL].Journal of North China Electric Power University (Natural Science Edition),2025:1- 10.(2025-12-17). https://link.cnki.net/urlid/10.1999. tm.20251217.0910.002.

[5] 高帆,包道日娜,赵明智,等.多场景规划下混合储能对风光耦合出力波动的平抑特性[J].电工技术学报, 2025,40(9):2827-2839.
GAO Fan,BAO Daorina,ZHAO Mingzhi,et al.Smoo- thing Characteristic of Wind-Solar Coupled Output Fluctuations by Hybrid Energy Storage under Multi- Scenario Planning[J].Transactions of China Electro- technical Society,2025,40(9):2827-2839.

[6] 肖剑,别克扎提·巴合提,张辉,等.多尺度自适应时频交互协同风电集群功率预测[J/OL].电力系统及其自动化学报,2025:1-11.(2025-12-09). https://doi.org/10.196 35/j.cnki.csu-epsa.001759.
XIAO Jian;BIEKEZATI Baheti;ZHANG Hui;ZHANG Keren.Multi-Scale Adaptive Time-Frequency Coope- rative Method for Wind Power Cluster Forecasting [J/OL].Proceedings of the CSU-EPSA,2025:1-11. (2025-12-09). https://doi.org/10.19635/j.cnki.csuepsa. 001759.

[7] 崔杨,朱晗,王议坚,等.基于CNN-SAEDN-Res的短期电力负荷预测方法[J].电力自动化设备,2024,44(4): 164-170.
CUI Yang,ZHU Han,WANG Yijian,et al.Short-term Power Load Forecasting Method based on CNN- SAEDN-Res[J].Electric Power Automation Equip- ment,2024,44(4):164-170.

[8] 陈臣鹏,赵鑫,毕贵红,等.基于多模式分解和麻雀优化残差网络的短期风速预测模型[J].电网技术,2022, 46(8):2975-2985.
CHEN Chenpeng,ZHAO Xin,BI Guihong,et al.SSA- Res-GRU Short-Term Wind Speed Prediction Model based on Multi-Model Decomposition[J].Power System Technology,2022,46(8):2975-2985.

[9] 滕婧,姜亚君,师瑞峰,等.基于频率增强融合时空信息的超短期风电功率预测[J].太阳能学报,2025,46(9): 198-207.
TENG Jing,JIANG Yajun,SHI Ruifeng,et al.Ultra- short-term Wind Power Prediction based on Frequency Enhancement and Spatio-temporal Information Fusi- on[J].Acta Energiae Solaris Sinica,2025,46(9):198-207.

[10] 陈磊,黄凯阳,张怡,等.基于信息重组和TCN-LSTM- MHSA的超短期风电功率预测[J/OL].南方电网技术,2024:1-10.(2024-06-27). https://kns.cnki.net/ kcms/detail/44.1643.TK.20240626.1553.009.html.
CHEN Lei,HUANG Kaiyang,ZHANG Yi,et al.Ultra- short-term Wind Power Forecasting based on Inform- ation Reorganization and TCN-LSTM-MHSA[J/OL]. Southern Power System Technology,2024:1-10.(2024- 06-27). https://kns.cnki.net/kcms/detail/44.1643.TK. 20240626.1553.009.html.

[11] 盛四清,袁伟智.基于二次分解和BiLSTM-XGBoost- ARIMA组合模型的短期风速预测[J/OL].华北电力大学学报(自然科学版),2024:1-13.(2024-07-29). https:// kns.cnki.net/kcms/detail/13.1212.tm.20240726.1332.004.html.
SHENG Siqing,YUAN Weizhi.Short-term Wind Speed Prediction based on Quadratic Decomposition and BiLSTM-XGBoost-ARIMA Combination Model[J/OL]. Journal of North China Electric Power University (Natural Science Edition),2024:1-13.(2024-07-29). https://kns.cnki.net/kcms/detail/13.1212.tm.20240726.1332.004.html.

[12] 依沙克·司马义,陈昊,张正强,等.基于NWP信息的SSA优化EEMD-LSTM风电超短期功率预测[J].太阳能学报,2025,46(8):176-183.
YISHAKE·Simayi,CHEN Hao,ZHANG Zhengqiang,et al.Ultra-Short-Term Wind Power Prediction Based on Nwp Information Using SSA Optimized EEMd- LSTM[J]. Acta Energiae Solaris Sinica,2025,46(8): 176-183.

[13] WANG H,YAN J,ZHANG J W,et al.Short-Term Inte- grated Forecasting Method for Wind Power,Solar Power,and System Load based on Variable Attention Mechanism and Multi-task Learning[J].Energy,2024, 304:132188.

[14] 冯双磊,王铮,王伟胜,等.基于CycleGAN的区域风速网格化预测方法[J/OL].中国电机工程学报,2025:1- 14.(2025-08-19). https://link.cnki.net/urlid/11.2107.TM. 20250819.1601.004.
FENG Shuanglei,WANG Zheng,WANG Weisheng,et al.Gridded Forecasting of Local Wind Speeds Based on CycleGAN[J/OL].Proceedings of the CSEE,2025:1-14. (2025-08-19). https://link.cnki.net/urlid/11.2107.TM. 20250819.1601.004.

[15] 赖纪东,谢天月,苏建徽,等.基于粒子群优化算法的孤岛微电网电压不平衡补偿协调控制[J].电力系统自动化,2020,44(16):121-129.
LAI Jidong,XIE Tianyue,SU Jianhui,et al.Coordinated Control of Voltage Unbalance Compensation in Island- ed Microgrid Based on Particle Swarm Optimization Algorithm[J].Automation of Electric Power Systems, 2020,44(16):121-129.

[16] 赵如意,王晓辉,郑碧煌,等.基于特征优化和混合改进灰狼算法优化BiLSTM网络的短期光伏功率预测[J].电网技术,2025,49(1):209-222.
ZHAO Ruyi,WANG Xiaohui,ZHENG Bihuang,et al. Short-Term Photovoltaic Power Prediction based on Feature Optimization and Hybrid Improved Grey Wolf Algorithm-Optimized BiLSTM Network[J].Power System Technology,2025,49(1):209-222.

[17] 殷豪,丁伟锋,陈顺,等.基于长短时记忆网络-纵横交叉算法的含高比例新能源电力市场日前电价预测[J].电网技术,2022,46(2):472-480.
YIN Hao,DING Weifeng,CHEN Shun,et al.Day-Ahead Electricity Price Forecasting of Electricity Market with High Proportion of New Energy Based on LSTM-CSO Model[J].Power System Technology,2022,46(2):472- 480.

[18] 孙艳,陈雁,莫东,等.基于风险分摊的多风电场机会约束机组组合求解方法[J].电网技术,2022,46(8):2996- 3006.
SUN Yan,CHEN Yan,MO Dong,et al.Joint Chance Constrained Unit Commitment with Wind Farms based on Risk Sharing[J].Power System Technology,2022, 46(8):2996-3006.

[19] 黄震,侯凯元,夏德明,等.基于HHO-Transformer架构的7天时间尺度新能源发电功率预测[J/OL].上海交通大学学报,2025:1-15.(2025-12-25). https://doi.org/ 10.16183/j.cnki.jsjtu.2025.336.
HUANG Zhen,HOU Kaiyuan,XIA Deming,et al.Fore- casting of Renewable Energy Power Generation based on HHO-Transformer Architecture for 7-Day Time Scales[J/OL].Journal of Shanghai Jiao Tong University, 2025:1-15.(2025-12-25).https://doi.org/10.16183/j.cnki.jsjtu.2025.336.

[20] 郑哲明,孔玲玲,何印.基于CPO-ICEEMDAN-DBO- TCN-GRU模型短期风电功率预测[J].现代电子技术,2025,48(24):88-94.
ZHENG Zheming,KONG Lingling,HE Yin.Short-Term Wind Power Prediction based on CPO-ICEEMDAN- DBO-TCN-GRU Model[J].Modern Electronic Tech- nique,2025,48(24):88-94.

[21] 叶林,裴铭,路朋,等.基于天气分型的短期光伏功率组合预测方法[J].电力系统自动化,2021,45(1):44-54.
YE Lin,PEI Ming,LU Peng,et al.Combination Fore- casting Method of Short-term Photovoltaic Power based on Weather Classification[J].Automation of Electric Power Systems,2021,45(1):44-54.

[22] 范竞敏,贺广林,王新刚,等.基于VMD-TCN-GRU-AM的超短期风电预测[J].太阳能学报,2025,46(6):538- 547.
FAN Jingmin,HE Guanglin,WANG Xingang,et al.Ultra Short Term Wind Power Prediction based on VMD- Tcn-Gru-Am[J].Acta Energiae Solaris Sinica,2025, 46(6):538-547.

[23] 李笑竹,王维庆.基于贝叶斯理论的分布鲁棒优化在储能配置上的应用[J].电网技术,2022,46(10):4001- 4011.
LI Xiaozhu,WANG Weiqing.Application of Distributed Robust Optimization based on Bayesian Theory in All- ocation of Energy Storage[J].Power System Technology, 2022,46(10):4001-4011.

[24] ZHANG Y G,PAN Z Y,WANG H,et al.Achieving Wind Power and Photovoltaic Power Prediction:an Intelligent Prediction System based on a Deep Learning Appro- ach[J].Energy,2023,283:129005.

[25] 成晓明,王磊,张鹏超,等.区域级电力负荷数据特性研究与短期预测[J].电网技术,2022,46(3):1092-1099.
CHENG Xiaoming,WANG Lei,ZHANG Pengchao,et al.Data Characteristics and Short-Term Forecasting of Regional Power Load[J].Power System Technology, 2022,46(3):1092-1099.

[26] 杨康,李蓝青,李艺丰,等.一种新型分布式光伏出力区间预测方法[J].发电技术,2024,45(4):684-695.
YANG Kang,LI Lanqing,LI Yifeng,et al.A Novel Distributed Photovoltaic Output Interval Prediction Method[J].Power Generation Technology,2024,45(4): 684-695

[27] 闫朝阳,李蓝青,徐浩嘉,等.基于白鲨算法与改进长短期记忆网络的光伏出力预测[J].发电技术,2025,46(4): 778-787.
YAN Chaoyang,LI Lanqing,XU Haojia,et al.Photo- voltaic Output Prediction Based on Improved Long Short-Term Memory Network Using White Shark Optimization Algorithm[J].Power Generation Technol- ogy,2025,46(4):778-787.

[28] 付小标,侯嘉琪,李宝聚,等.一种二模态天气分型方法及其在光伏功率概率预测的应用[J].发电技术,2024, 45(2):299-311.
FU Xiaobiao,HOU Jiaqi,LI Baoju,et al.A Two-Modal Weather Classification Method and Its Application in Photovoltaic Power Probability Prediction[J].Power Generation Technology,2024,45(2):299-311.

[29] Elia Group.Open Data Elia:Belgian grid data (2024) [EB/OL].(2024-05-22)[2025-10-08].https://www.elia.be/en/grid-data/open-data.

Previous article in this issue

Next article in this issue