Fusion-ResNet: A Lightweight multi-label NILM Model Using PCA-ICA Feature Fusion

2025-11-15

AI Summary

To address critical challenges in non-intrusive load monitoring (NILM)—including severe overfitting, poor generalization, and low decomposition accuracy under multi-device concurrency—this paper proposes an end-to-end lightweight multi-label classification framework. Methodologically, it innovatively integrates principal component analysis (PCA) and independent component analysis (ICA) to enhance the discriminability of input features, and introduces a lightweight Fusion-ResNet architecture that balances model capacity and computational efficiency. Experimental results demonstrate that the framework significantly improves robustness and generalization under high-concurrency scenarios. On multiple public benchmarks, it achieves superior average F1-scores compared to state-of-the-art methods, while reducing both training and inference time by over 30%. These advantages underscore its strong potential for practical deployment in real-world NILM applications.

Technology Category

• Machine Learning: Hardware-aware ML
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Safety and Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Non-intrusive load monitoring (NILM) is an advanced load monitoring technique that uses data-driven algorithms to disaggregate the total power consumption of a household into the consumption of individual appliances. However, real-world NILM deployment still faces major challenges, including overfitting, low model generalization, and disaggregating a large number of appliances operating at the same time. To address these challenges, this work proposes an end-to-end framework for the NILM classification task, which consists of high-frequency labeled data, a feature extraction method, and a lightweight neural network. Within this framework, we introduce a novel feature extraction method that fuses Independent Component Analysis (ICA) and Principal Component Analysis (PCA) features. Moreover, we propose a lightweight architecture for multi-label NILM classification (Fusion-ResNet). The proposed feature-based model achieves a higher $F1$ score on average and across different appliances compared to state-of-the-art NILM classifiers while minimizing the training and inference time. Finally, we assessed the performance of our model against baselines with a varying number of simultaneously active devices. Results demonstrate that Fusion-ResNet is relatively robust to stress conditions with up to 15 concurrently active appliances.

Problem

• Addresses overfitting and low generalization in NILM
• Disaggregates power for multiple appliances operating simultaneously
• Reduces training and inference time with lightweight design

Innovation

• PCA-ICA feature fusion for NILM classification
• Lightweight Fusion-ResNet architecture for multi-label tasks
• Robust disaggregation with up to 15 concurrent appliances