基于CEEMDAN-SBiGRU-OMHA的短期电力负荷预测

Short Term Power Load Forecasting Based on CEEMDAN-SBiGRU-OMHA

为了提高短期电力负荷预测的精准度,充分挖掘电力负荷数据的复杂相关性,提出了一种优化多头注意力机制的CEEMDAN-SBiGRU组合预测模型,改进了特征提取和特征融合两个模块.首先,采用自适应噪声完全集成经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)将电力负荷数据分解成多个内在模态函数(IMF)和一个残差信号(RES);同时引入降噪自编码器DAE挖掘数据中受气象因素、工作日类型和温度变化的潜在特征.其次,将提取到的复杂特征输入至堆叠双向门控循环单元(stacked bidirectional gated recurrent unit,SBiGRU)模块中继续学习,以获取隐藏状态.最后,将获取的隐藏状态输入至加入残差机制和层归一化优化的多头注意力(optimized multi-head attention,OMHA)机制模块,可以准确地给重要特征分配更高的权重,解决噪声干扰问题.实验结果表明,CEEMDAN-SBiGRU-OMHA组合模型具有更高的精确性.

This study proposes a CEEMDAN-SBiGRU combined prediction model with an optimized multi-head attention mechanism to enhance the precision of short-term power load forecasting and fully explore the complex correlation of power load data.The model improves two modules:feature extraction and feature fusion.Firstly,the complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)is utilized to decompose the power load data into multiple intrinsic mode function(IMF)and a residual signal(RES);and a denoising autoencoder DAE is introduced to extract potential features from the data affected by meteorological factors,workday types,and temperature changes.Secondly,the extracted intricate features are fed into the stacked bidirectional gated recurrent unit(SBiGRU)module to obtain hidden states.Finally,the obtained hidden states are input into the optimized multi-head attention(OMHA)mechanism module,which incorporates residual mechanism and layer normalization,to accurately assign higher weights to important features and solve the problem of noise interference.The experimental results indicate that the CEEMDAN-SBiGRU-OMHA combined model achieves higher accuracy.