A Novel Schematic Design of Enhanced State Gated Transformers for Energy Disaggregation of Nonintrusive Load Monitoring

Nonintrusive load monitoring (NILM) is a technique for estimating the energy consumption of individual appliances without the need for direct metering. In this letter, we examine the attention mechanism of transformers and present two transformer-based NILM approaches, named state gated transformer (SGT) and enhanced state gated transformer (eSGT) to learn complex nonlinear relationships between aggregate and individual power consumption of appliances. The proposed SGT employs parallel self-attention networks, whereas the proposed eSGT enhances the former with a cross-coupled pair structure. We present the schematic design of transformers which allows for concise characterization of the attention mechanism, inspiring the exploration of novel designs at the circuit level. Our experimental results demonstrate the effectiveness and versatility of the proposed approach for real-world NILM datasets.