摘要
准确可靠的光伏发电功率预测对制定高效智能的负荷调度策略具有重要的指导意义。不同于常规方法,提出了一种基于变分模态分解和差分整合移动平均自回归模型的组合预测方法。变分模态分解可将原始信号分解为若干个具有不同中心频率和频率带宽的模态函数;差分整合移动平均自回归模型可对每一个模态函数建立预测模型。实验结果表明本文所提方法在对光伏发电功率预测时,优于基于经验模态分解法和局部均值分解法的预测模型,具有较高的预测准确度和稳健性。
Precise and reliable PV power forecasting technique plays an important guiding role for developing efficient load scheduling strategies.Different from the conventional method,this paper presents a combined prediction method based on the variational mode decomposition and autoregressive integrated moving average model.The variational mode decomposition method decomposes the original signal into several mode functions with different center frequencies and bandwidth,and the autoregressive integrated moving average method is used to establish a forecasting model for each mode function.The experiment results show that the proposed technique is superior to the prediction methods based on empirical mode decomposition method and local mean decomposition method for predicting photovoltaic power,and has high prediction accuracy and robustness.
作者
李伟进
童国炜
曾云洪
罗晓
王灵军
LI Weijin;TONG Guowei;ZENG Yunhong;LUO Xiao;WANG Lingjun(State Key Laboratory of Energy Conservation and Operation of Air-Conditioning Equipment and Systems,Gree Electric Appliances,Inc.of Zhuhai,Zhuhai 519070,China;Gree Electric Appliances,Inc.of Zhuhai,Zhuhai 519070,China)
出处
《电力科学与工程》
2020年第1期41-49,共9页
Electric Power Science and Engineering
关键词
光伏发电
功率预测
变分模态分解
差分整合移动平均自回归模型
photovoltaic
power forecast
variational mode decomposition
autoregressive integrated moving average model
