Fig 1.
The process structure of power fingerprint identification.
Fig 2.
One instance of a fridge in PLAID.
(a)The instantaneous voltage of the Fridge over 1 s. (b)The instantaneous current of the Fridge over 1 s. (c)The instantaneous power of the Fridge over 1 s.
Fig 3.
The binary V- I trajectory mapping for a fluorescent lamp(N = 32).
(a) Linear interpolation. (b) Bilinear interpolation.
Fig 4.
Color V-I trajectory images of 11 types of appliance loads in the PLAID dataset (N = 32).
Fig 5.
The structure of the Convolutional Block Attention Module (CBAM) model.
Fig 6.
(a)The ResNet network residual structure. (b)The structure of the CBAM-ResNet model.
Fig 7.
The experimental scheme of model transferring.
Fig 8.
The schematic diagram of the reweighted optimal classifier model.
Table 1.
The PLIAD dataset of appliance types and instance statistics.
Fig 9.
The comparison of several iterations.
Fig 10.
The training and validation accuracy of CBAM-ResNet34 and transferred CBAM-ResNet34 models are illustrated for comparison.
Fig 11.
The selection of parameter N.
Fig 12.
The confusion matrix for appliance loads of the PLAID dataset.
(a) Confusion matrix based on color V-I trajectory image before model transfer. (b) Confusion matrix based on color V-I trajectory image after model transfer.
Fig 13.
The F-score (%) for appliance loads of the PLAID dataset.
Fig 14.
The evaluated metrics between transferred ResNet34 models with and without CBAM.
Table 2.
Comparison of identification accuracy and training time between different training models on the PLAID dataset.
Table 3.
The F1 for different data balance algorithms using transferred CBAM-ResNet34.
Table 4.
The comparison of the proposed method and other power fingerprint identification methods.