Feature Extraction of V-I Trajectory Using 2-D Fourier Series for Electrical Load Classification

• Published in: IEEE sensors journal 2022-09, Vol.22 (18), p.17988-17996
• Main Authors: Mulinari, Bruna Machado, Nolasco, Lucas da Silva, Oroski, Elder, Lazzaretti, Andre Eugenio, Linhares, Robson Ribeiro, Renaux, Douglas Paulo Bertrand
• Format: Article
• Language: English
• Subjects: Classification; Electrical loads; Embedded systems; Energy consumption; Evaluation; Feature extraction; Fourier 2-D (F2D); Fourier series; Load monitoring; Machine learning; Mathematical analysis; nonintrusive load monitoring (NILM); Robustness (mathematics); Sensors; Steady-state; Trajectory; Transient analysis; voltage–current (<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">V –<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">I ) trajectory
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2022.3194999

Nonintrusive load monitoring (NILM) techniques allow the individual consumption of devices in an installation to be reported to the user, collaborating in the awareness and managing consumers' energy use. One of the most critical steps in NILM procedures is feature extraction, which involves the quantitative description of the load signature. Most state-of-the-art methods, particularly those involving voltage-current ( V-I ) trajectories, are based on features that specialists design when manually analyzing signals-the so-called hand-crafted features. On the other hand, this work presents a mathematical method that describes the transient and steady-state (SS) load signature using a 2-D Fourier series, avoiding hand-crafted descriptors. The proposed approach evaluates load identification results with different classifiers and publicly available datasets. In addition to the evaluation of the proposed method's computational resources, such as execution time and memory footprint in an embedded system, their robustness to noise insertion is also assessed. The results of the proposed approach indicate an average per-class accuracy higher than 90%, equivalent or superior to hand-crafted V-I trajectory-based methods in most cases and even deep learning approaches recently presented in the literature. Such results reinforce the main contributions of this work: 1) a mathematical method to extract interpretable features; 2) results comparable or superior to other state-of-the-art methods; and 3) promising results in computational resources in an embedded system.