Research on Non-invasive Load Decomposition Algorithm Based on Attention Mechanism of Convolutional Neural Network

As residential users pay more and more attention to the electricity consumption of electrical equipment, non-invasive load decomposition research has become one of the important applications of artificial intelligence algorithms for end users. Deep learning models have gradually gained unique advantages in the application of non-invasive load decomposition. In this paper, based on convolutional block attention module, the attention mechanism is introduced to update the weight distribution and obtain more effective feature maps. Then the long - term memory network is used to establish a time window to learn the data features and decompose the load. The deep learning framework proposed in this paper has a simple structure and can significantly improve the efficiency and accuracy of load decomposition. The method is validated based on the public dataset UKdale.