摘要
针对现有模型难以捕获电力负荷不确定趋势这一问题,文中提出了一种基于Prophet-EEMD-CNN的负荷预测模型。首先,引入Prophet算法来识别负荷数据的周期和趋势特征。然后,采用集合经验模分解(EEMD)方法来分解剩余数据,获得具有特定模态的分量。最后,提取特征数据并放入卷积神经网络(CNN)的输入层,以获得最终的预测值。实验结果表明,文中提出的模型对电力负荷数据具有较高的预测性能。
This paper proposes a load forecasting model based on Prophet-EEMD-CNN to address the issue of existing models struggling to capture the uncertain trends in electrical load.Firstly,the Prophet algorithm is introduced to identify the cyclical and trend characteristics of load data.Then,the Ensemble Empirical Mode Decomposition(EEMD)method is employed to decompose the residual data to obtain components with specific modalities.Finally,the extracted feature data is fed into the input layer of a Convolutional Neural Network(CNN)to obtain the final prediction values.Experimental results indicate that the proposed model has high predictive performance for electrical load data.
作者
郑诗川
ZHENG Shichuan(Sichuan University of Light Industry and Technology,Yibin,Sichuan 643002,China)
出处
《移动信息》
2024年第5期238-240,243,共4页
MOBILE INFORMATION
关键词
电力负荷预测
卷积神经网络
周期特征
Energy consumption prediction
Convolutional neural network
Periodic characteristics
