Non-Intrusive Load Classification and Recognition Using Soft-Voting Ensemble Learning Algorithm With Decision Tree, K-Nearest Neighbor Algorithm and Multilayer Perceptron

Non-intrusive load monitoring (NILM) detects the energy consumption of individual appliances by monitoring the overall electricity usage in a building. By analyzing voltage and current characteristics, NILM can recognize the usage patterns of various appliances, thus facilitating energy conservation and management. To implement non-intrusive load classification and recognition more effectively, this study proposes an ensemble learning algorithm based on soft voting, which comprises a decision tree, K-nearest neighbor algorithm, and multilayer perceptron (EL-SV
$_{\mathrm {DT-KNN-MLP}}$
). In this study, the voltage and current features in the plug-load appliance identification dataset (PLAID) and worldwide household and industry transient energy dataset (WHITED) are used as input data. The dataset is examined thoroughly and preprocessed before it is fed into the EL-SV
$_{\mathrm {DT-KNN-MLP}}$
. During preprocessing, six different normalization techniques are applied to the data to improve the accuracy and reliability of the machine-learning model, thus rendering the proposed algorithm more adept at classifying and recognizing appliances. The proposed method is validated by comparing it with other machine learning algorithms in terms of accuracy, precision, recall, and F1 score under the six different normalization methods. For the PLAID, the proposed algorithm can achieve high accuracy scores of 99.79%, 98%, 98.11%, 98.36%, 96.42%, and 98.76% under the min–max normalization, MaxAbs scaler, robust scaler, z-score normalization, L1 normalization, and Yeo–Johnson transformation, respectively. Similarly, for the WHITED, the proposed algorithm can achieve high accuracy scores of 99.31%, 98.14%, 98.3%, 98.35%, 97.65%, and 98.02% under the abovementioned normalization methods. The results show that the proposed EL-SV
$_{\mathrm {DT-KNN-MLP}}$
algorithm outperforms the other ten machine learning algorithms examined in this study.