A New Convolutional Neural Network-Based System for NILM Applications

Abstract

Electrical load planning and demand response programs are often based on the analysis of individual load level measurements obtained from houses or buildings. The identification of individual appliances' power consumption is essential, since it allows improvements, which can reduce appliances' power consumption. In this paper, the problem of identifying the electrical loads connected to a house, starting from the total electric current measurement, is investigated. The proposed system is capable of extracting the energy demand of each individual device using a non-intrusive load monitoring (NILM) technique. A NILM algorithm based on a convolutional neural network is proposed. The proposed algorithm allows simultaneous detection and classification of events without having to perform double processing. As a result, the calculation times can be reduced. Another important advantage is that only the acquisition of current is required. The proposed measurement system is also described in this paper. Measurements are conducted using a test system, which is capable of generating the electrical loads found on a typical house. The most important experimental results are also included and discussed in the paper.

Non-Intrusive Load Monitoring Using a CNN-LSTM-RF Model Considering Label Correlation and Class-Imbalance

“…Several classic NILM methods are used for this comparative study. The alternative methods considered are the KNN [40], the CNN-LSTM [21]- [27], the combinatorial optimization (CO) [30], the FHMM [33] and the priori biased NILM method (PBN) [41]. In the KNN model, the k value is set to 5, the weights method is uniform, and the algorithm is auto.…”

“…He compares the ability of the CNN, LSTM and Stacked Denoising Autoencoders models in NILM. More studies utilizing neural networks and deep learning to solve this problem have followed [11]- [13]. Ref.…”

“…Medeiros transforms the values of active and reactive power into a matrix form for CNN training, and reaches a high accuracy in NILM [26]. Fabrizio proposes a new CNN-based system for NILM applications that achieves encouraging results on the public-use dataset BLUED [27].…”

Deep Flexible Transmitter Networks for Non-Intrusive Load Monitoring of Power Distribution Networks

“…Derivative analysis and filter analysis have been proposed to improve classification performance [18]. Reference [19] combined multiple devices from aggregated measurement data for monitoring. A sequencing method has been proposed to reduce the training process of neural networks [20].…”

“…Nevertheless, the classification accuracy of the basic deep backpropagation networks cannot meet the need for non-intrusive load monitoring. Convolutional networks [19] extracts features of the image through the action of the convolutional layer and pooling layer. The convolutional networks can accurately classify image features.…”