摘要
为处理非线性、非平稳和多维时序的光伏功率数据,提高预测精度和稳定性。提出一种基于[2]VMD-SSA-LSTM的多维时序光伏功率预测模型。通过数据预处理、VMD分解、SSA优化、LSTM建模和预测、预测精度评估和模型优化,可以构建一个准确地基于VMD-SSA-LSTM的多维时序光伏功率预测模型,用于准确预测光伏电站未来一段时间内的发电功率。
In order to deal with nonlinear,non-stationary and multi-dimensional time series of photovoltaic power data,the prediction accuracy and stability are improved.A multidimensional time series PV power prediction model based on VMD-SSA-LSTM is proposed.Through data preprocessing,VMD decomposition,SSA optimization,LSTM modeling and prediction,prediction accuracy assessment and model optimization,an accurate multidimensional time-series PV power prediction model based on VMD-SSA-LSTM can be constructed,which is used to accurately predict the power generation of PV power plants in the future period.
作者
刘锦峰
崔家铭
林宇龙
李姗珊
Liu Jinfeng;Cui Jiaming;Lin Yulong;Li Shanshan(School of Electrical and Control Engineering,Liaoning University of Engineering and Technology,Huludao Liaoning 125105,China)
出处
《现代工业经济和信息化》
2024年第9期261-262,266,共3页
Modern Industrial Economy and Informationization
关键词
光伏功率预测
变分模态分解
奇异谱分析
长短期记忆神经网络
photovoltaic power prediction
variational modal decomposition
singular spectrum analysis
long short-term memory neural network