摘要
非侵入式负荷分解可以从家庭电能表的总功率读数分解出各用电器的功率,对于节能减排、智能用电等均具有重要意义。针对当前深度学习在非侵入式负荷分解中存在的分解准确率低、对使用频率低的电器分解误差大等问题,提出了一种基于Attention机制的时间卷积神经网络(temporal convolutional neural network,TCN)与长短期记忆网络(long short-term memory,LSTM)相结合的序列到点非侵入式负荷分解模型。该模型首先以重叠滑动窗口方式读取功率时间序列作为网络输入,利用TCN膨胀因果卷积扩大卷积核感受野,加入残差连接和批处理规范化,加快提取深层负荷特征的效率;然后利用LSTM捕捉功率序列演化模式完成负荷分解,在TCN特征提取侧和LSTM负荷分解侧引入双重Attention机制来提取重要负荷特征和历史关键时间点信息;最后在UK-dale和REDD数据集上进行训练与测试,实验结果表明本文模型性能良好,负荷分解准确率有明显提升。
Non-intrusive load decomposition can be used to decompose the power of individual appliances from the total power reading of a household electricity meter,which has important practical significance for energy conservation and emission reduction,intelligent power consumption and so on.In view of the current problems of deep learning in load decomposition,such as low decomposition accuracy and large decomposition error of electrical appliances that are used infrequently,this paper proposed a non-invasive load decomposition model of sequence-to-point based on attention mechanism,which combines time convolutional neural network(TCN)and long short-term memory network(LSTM).Firstly,the power time series were fed as the network input in overlapping sliding window mode,TCN expansion causal convolution was employed to expand the receptive field of convolution kernel,the residual link and batch standardization were added to accelerate the efficiency of extracting deep load features.Meanwhile,the attention mechanism was introduced to extract key information,and then LSTM was employed to decompose the load decomposition by capturing the evolution mode of power series.Finally,the experimental results on UK-dale and REDD data set show that the model performs well and significantly improves the decomposition accuracy.
作者
马佳成
王晓霞
杨迪
MA Jiacheng;WANG Xiaoxia;YANG Di(Department of Computer Science,North China Electric Power University,Baoding 071003,Hebei Province,China;Marketing Service Center,State Grid Hebei Electric Power Co.,Ltd.,Shijiazhuang 050000,Hebei Province,China)
出处
《电力信息与通信技术》
2023年第8期43-51,共9页
Electric Power Information and Communication Technology
关键词
非侵入式负荷分解
序列到点
注意力机制
时间卷积神经网络
长短期记忆网络
non-intrusive load decomposition
sequence to point
attention mechanism
temporal convolutional neural network
long short-term memory network