RAPC-Net: Residual-Aware Physical Consistency Network for Multi-Appliance NILM

Abstract

Non-intrusive load monitoring (NILM) aims to estimate appliance-level power consumption from aggregate household measurements and provides an effective solution for fine-grained energy management. However, multi-appliance NILM remains challenging because the measured aggregate power generally contains unobserved household loads, jointly predicted appliance powers may violate basic physical relationships, and heterogeneous appliance activation patterns can lead to imbalanced optimization. To address these issues, this paper proposes a Residual-Aware Physical Consistency Network (RAPC-Net) for multi-appliance NILM. RAPC-Net jointly estimates multiple target appliances and the remaining household consumption through a shared temporal encoder, a multi-appliance prediction branch, and a residual-load prediction branch. Two watt-space physical consistency constraints are incorporated into the learning objective. The aggregate reconstruction constraint encourages the target-appliance predictions and the predicted residual load to jointly reconstruct the measured aggregate power, while the overestimation constraint suppresses physically infeasible predictions in which the sum of the predicted target-appliance powers exceeds the aggregate measurement. In addition, an automatic appliance-aware weighting strategy is developed based on appliance activation statistics to balance the contributions of different appliances and emphasize active samples without manually assigning appliance-specific loss coefficients. Experiments on the REFIT dataset, including an expanded ablation study and two house-independent comparisons, are conducted to evaluate the contributions of residual-load modeling, physical consistency constraints, and appliance-aware weighting. In the primary house-independent comparison, RAPC-Net achieves a Target-sum MAE of 85.97±15.45 W, which is close to the best competing result of 83.59±3.71 W, while reducing the Over-ratio to 0.025±0.020% and the violation energy to 9.10±5.47 Wh. Under an additional household partition, RAPC-Net maintains a Target-sum MAE of 127.29±7.05 W and achieves an Over-ratio of 0.019±0.011%. These results indicate that RAPC-Net improves the physical feasibility of joint multi-appliance predictions while maintaining comparable target-sum estimation accuracy.