基于全局与滑动窗口结合的Attention机制的非侵入式负荷分解算法

非侵入式负荷监测(non-intrusive load monitoring, NILM)是指在电力入口处安装监测设备,利用总用电负荷得到用电侧单个用电设备状态的方法。由此可以准确地刻画用户用电画像,故NILM是电网智能配电和给予用户侧精细化管理的关键技术之一。随着深度学习在NILM的应用,对于负荷的识别与功率分解能力有所提升,但在训练模型的速率与模型的预测准确率上依旧不高,为此,文章提出基于全局与滑动窗口相结合的注意力机制的负荷分解模型。该模型首先将输入总负荷功率序列通过功率嵌入矩阵映射到高维向量,并利用基于双向LSTM的编码器进行信息提取;通过引入全局与滑动窗口相结合的Attention机制,从提取的信息中选取与当前时刻相关度高的信息,用于解码并最终得到负荷分解结果。在数据集REFIT上验证了所提算法在速率和准确率上有更好的效果。

Non-intrusive load monitoring algorithm based on Attention mechanism combined with global and sliding window

Non-intrusive load monitoring (NILM) refers to the method of installing monitoring equipment at the power entrance and using the total electrical load to obtain the status of individual electrical equipment on the power consumption side. This can accurately portray the user"s power consumption portrait, so NILM is one of the key technologies for smart power distribution and fine management on the user side. With the application of deep learning in NILM, the ability of load identification and power decomposition has been improved, but the rate of training the model and the prediction accuracy of the model are still not high. For this reason, The article proposes a load decomposition model based on the attention mechanism that combines global and sliding windows. The model first maps the input total load power sequence to a high-dimensional vector through a power embedding matrix, and uses a BI-LSTM based encoder for information extraction; then, it selects from the extracted information by introducing an Attention mechanism that combines global and sliding windows Information with high correlation to the current moment is used for decoding and finally the power decomposition result is obtained. The data set REFIT is used to verify that the algorithm has a better effect on speed and accuracy.