网络首发:2026-02-05,
纸质出版:2026-02-05
移动端阅览
王育飞, 吴顾轩, 桑一岩, 等. 基于HGS-VMD-ENN的光伏发电功率超短期混沌预测模型[J]. 太阳能学报, 2026,47(1):64-71.
王育飞, 吴顾轩, 桑一岩, et al. 基于HGS-VMD-ENN的光伏发电功率超短期混沌预测模型[J]. 2026, 47(1): 64-71.
王育飞, 吴顾轩, 桑一岩, 等. 基于HGS-VMD-ENN的光伏发电功率超短期混沌预测模型[J]. 太阳能学报, 2026,47(1):64-71. DOI: doi:10.19912/j.0254-0096.tynxb.2024-1485.
王育飞, 吴顾轩, 桑一岩, et al. 基于HGS-VMD-ENN的光伏发电功率超短期混沌预测模型[J]. 2026, 47(1): 64-71. DOI: doi:10.19912/j.0254-0096.tynxb.2024-1485.
针对非晴空天气下光伏发电功率剧烈波动导致的预测准确度不足问题
提出一种基于饥饿游戏搜索算法(HGS)优化变分模态分解(VMD)和大脑情绪神经网络(ENN)的光伏发电功率超短期混沌预测模型。首先
为提高VMD自适应性
将HGS算法用于VMD核心参数寻优
并设计一种考虑加权排列熵和分解损失的HGS-VMD适应度函数
降低分解分量的复杂性和残差分量对预测结果的影响。其次
采用改进C-C法对VMD分解分量重构系统相空间
并将相空间重构矩阵输入ENN模型进行单步滚动预测。最后
基于实测光伏发电功率数据对所提预测模型进行仿真验证
结果表明所提预测模型能有效提高光伏发电功率在非晴空天气下的预测准确度。
Aiming at the problem of insufficient prediction accuracy due to the drastic fluctuation of PV power under non-clear-skg weather conditions
an ultra-short-term PV power chaotic prediction model based on hunger games search (HGS) optimized variational mode decomposition (VMD) and emotional neural network (ENN) is proposed. Firstly
the HGS algorithm is used for optimization of VMD core parameters to improve the adaptivity of VMD
and an HGS-VMD fitness function considering weighted permutation entropy and decomposition loss is designed to reduce the complexity of the decomposition component and the influence of the residual component on the prediction results. Then
the phase space is reconstructed using the improved C-C method for the VMD decomposition components
and after extracting their regularity information
the phase space reconstruction matrix is input into the ENN model for prediction. Finally
the proposed prediction model is verified by simulation based on the measured PV power data
and the results show that the proposed prediction model can effectively improve the prediction accuracy of PV power under non-clear-sky weather conditions.
舒印彪, 赵勇, 赵良, 等. “双碳”目标下我国能源电力低碳转型路径[J]. 中国电机工程学报, 2023, 43(5): 1663-1672.
辛保安, 单葆国, 李琼慧, 等. “双碳”目标下“能源三要素”再思考[J]. 中国电机工程学报, 2022, 42(9): 3117-3126.
王清亮,杨博,应欣峰,等.非晴空条件下光伏发电短期功率预测方法[J]. 太阳能学报, 2022, 43(3): 188-196.
YANG T, YANG Z N, LI F, et al.A short-term wind power forecasting method based on multivariate signal decomposition and variable selection[J]. Applied energy,2024, 360: 122759.
朱菊萍, 魏霞, 谢丽蓉, 等. 基于VMD和改进BiLSTM的短期风电功率预测[J]. 太阳能学报, 2024, 45(6): 422-428.
LIU Y F, LIU Y, CAI H H, et al.An innovative short-term multihorizon photovoltaic power output forecasting method based on variational mode decomposition and a capsule convolutional neural network[J]. Applied energy, 2023, 343: 121-139.
FU W L, WANG K, LI C S,et al.Multi-step short-term wind speed forecasting approach based on multi-scale dominant ingredient chaotic analysis, improved hybrid GWO-SCA optimization and ELM[J]. Energy conversion and management, 2019, 187: 356-377.
GAO T, NIU D X, JI Z S, et al.Mid-term electricity demand forecasting using improved variational mode decomposition and extreme learning machine optimized by sparrow search algorithm[J]. Energy, 2022, 261: 125328.
李青, 张新燕, 马天娇, 等. 基于ECBO-VMD-WKELM的风电功率超短期多步预测[J]. 电网技术, 2021, 45(8): 3070-3080.
张淑清, 李君, 姜安琦, 等. 基于FPA-VMD和BiLSTM神经网络的新型两阶段短期电力负荷预测[J]. 电网技术, 2022, 46(8): 3269-3279.
王育飞, 杨启星, 薛花. 考虑混沌特征的增强型大脑情绪神经网络光伏发电功率超短期预测模型[J]. 高电压技术, 2021, 47(4): 1165-1177.
XU X F, HU S T, SHI P M, et al.Natural phase space reconstruction-based broad learning system for short-term wind speed prediction: case studies of an offshore wind farm[J]. Energy, 2023, 262: 125342.
FU W L, ZHANG K, WANG K, et al.A hybrid approach for multi-step wind speed forecasting based on two-layer decomposition, improved hybrid DE-HHO optimization and KELM[J]. Renewable energy, 2021, 164: 211-229.
WANG Y F, YANG Q X, XUE H, et al.Ultra-short-term PV power prediction model based on HP-OVMD and enhanced emotional neural network[J]. IET renewable power generation, 2022, 16(11): 2233-2247.
张琰妮, 史加荣, 李津, 等. 融合残差与VMD-ELM-LSTM的短期风速预测[J]. 太阳能学报, 2023, 44(9):340-347.
王涛, 李薇, 许野, 等. 计及相似日的VMD-FE-LSTM光伏出力组合预测模型研究[J]. 太阳能学报, 2024, 45(5): 490-499.
YANG Y T, CHEN H L, AMIRH G.Hunger games search: visions, conception, implementation, deep analysis, perspectives, and towards performerce shifts[J]. Expert systems with applications, 2021, 177: 114864.
0
浏览量
1
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621