Non-invasive load identification based on LSTM-BP neural network
Liang Huang, Shi‐Jie Chen, Zaixun Ling, Yibo Cui, Qiong Wang
Abstract
Smart power consumption is an important part of ubiquitous power Internet of things. Load identification, as an important part of smart power consumption, is of great significance to users and power grid. Aiming at the problems of long training time and low recognition accuracy in existing algorithms, this paper proposes a non-invasive load identification algorithm based on LSTM-BP. Firstly, the data is normalized, and then the dimension of high-dimensional data is reduced by PCA. Then, LSTM-BP neural network is built for load identification. Finally, Redd data set is used to test and analyze the algorithm. Compared with the existing load identification algorithm based on event detection, this method has higher stability and accuracy.