Enhancing Non-Intrusive Load Monitoring with Features Extracted by Independent Component Analysis
This work addresses energy disaggregation for non-intrusive load monitoring, offering incremental improvements in accuracy and robustness for applications in smart energy management.
The paper tackles the challenges of energy disaggregation, such as limited data and complex multi-appliance scenarios, by proposing a neural network architecture using independent component analysis, which outperforms existing algorithms on real-world data with improved overfitting resistance and low complexity.
In this paper, a novel neural network architecture is proposed to address the challenges in energy disaggregation algorithms. These challenges include the limited availability of data and the complexity of disaggregating a large number of appliances operating simultaneously. The proposed model utilizes independent component analysis as the backbone of the neural network and is evaluated using the F1-score for varying numbers of appliances working concurrently. Our results demonstrate that the model is less prone to overfitting, exhibits low complexity, and effectively decomposes signals with many individual components. Furthermore, we show that the proposed model outperforms existing algorithms when applied to real-world data.