A Hybrid Attention Model for Non-intrusive Load Monitoring based on Time Series Feature

被引：0

作者：

Meng, Zhaorui ^{[1
]}

Xie, Xiaozhu ^{[1
]}

Xie, Yanqi ^{[1
]}

Sun, Jinhua ^{[1
]}

机构：

[1] School of Computer and Information Engineering, Xiamen University of Technology, Fujian, Xiamen,361024, China

来源：

IAENG International Journal of Computer Science | 2024年 / 51卷 / 04期

关键词：

Deep neural networks - Electric power plant loads - Energy utilization - Extraction - Learning systems - Neural network models - Principal component analysis - Recurrent neural networks - Time series - Time series analysis;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Non-intrusive load monitoring (NILM) has become a widely used approach to monitor energy consumption by installing monitoring equipment at the power supply entrance. However, the accuracy of traditional deep neural network decomposition models falls short of meeting practical demand. To address this limitation, the present study introduces a novel hybrid neural network model, which integrates temporal feature extraction and an attention mechanism. The proposed model is designed to discern the salient attributes within power time series signals, thereby reducing the dimensionality of the resulting characteristic temporal signals via the application of Principal Component Analysis (PCA). Next, a Gated Recurrent Unit (GRU) neural network with an attention mechanism extracts the features of the generated information vector, and generates the load decomposition model after multiple iterations of learning. The experimental outcomes on the REDD public dataset substantiate the superiority of the proposed model over alternative deep learning techniques, including CNN, GRU, and GRU with attention. The proposed model demonstrates a significantly elevated degree of precision within the domain of load identification. © (2024) International Association of Engineers.

引用

页码：396 / 400