PSSR-Net: A Pretraining Network for NILM Based on Power Sequence Shift Recognition
Qingrong Yang, Hao Wu, Hongjuan Zhang, Qing Ma · IEEE Transactions on Instrumentation and Measurement · 2025
Non-intrusive load monitoring (NILM) technology estimates individual appliance consumption by analyzing the total consumption collected from smart meters, enabling efficient energy management and consumption analysis. However, current deep learning (DL) based NILM methods face generalization challenges in different households due to diverse appliance compositions and usage patterns. Additionally, these methods require extensive synchronized training data, incurring substantial data collection and storage costs. This paper proposes a power sequence shift recognition network (PSSR-Net) with a novel pre-training approach: First, synthesize training data by adding appliance power sequences to background power signals with specific time shifts. Then, the DL model pre-trains by predicting these shift values. Finally, the pre-trained model transfers to new households through fine-tuning with limited real data. Unlike traditional methods requiring synchronized power data, our proposed PSSR-Net uses non-synchronized data to pre-train a backbone network with strong multi-appliance feature extraction capabilities, significantly reducing data collection costs while improving performance. Experimental results on two datasets demonstrate that PSSR-Net exhibits superior generalization ability when deployed to new households, achieving a 29.6% reduction in MAE and a 46% reduction in SAE compared to existing pre-training methods. Furthermore, the method maintains effectiveness even when using lower sampling rate data for pre-training.