Home Appliance Identification for Nilm Systems Based on Deep Neural Networks

@article{Penha2018HomeAI,
  title={Home Appliance Identification for Nilm Systems Based on Deep Neural Networks},
  author={Deyvison de Paiva Penha and Adriana Rosa Garcez Castro},
  journal={International Journal of Artificial Intelligence \& Applications},
  year={2018},
  volume={9},
  pages={69-80}
}
  • D. Penha, A. Castro
  • Published 30 March 2018
  • Engineering
  • International Journal of Artificial Intelligence & Applications
This paper presents the proposal for the identification of residential equipment in non-intrusive load monitoring systems. [] Key Method The methodology was developed using data from a public database (REED) that presents data collected at a low frequency (1 Hz). The results obtained in the test database indicate that the proposed system is able to carry out the identification task, and presented satisfactory results when compared with the results already presented in the literature for the problem in…

Figures and Tables from this paper

A Machine-Learning Based Nonintrusive Smart Home Appliance Status Recognition
TLDR
This paper proposes a deep learning approach that dispenses with the complex transient event detection and hand crafting of signal features to provide high performance recognition of close tolerance appliances and explores individually three deep learning disaggregation algorithms based on the multiple parallel structure convolutional neural networks.
Comparative Evaluation of Non-Intrusive Load Monitoring Methods Using Relevant Features and Transfer Learning
TLDR
This paper introduces a new publicly available annotated dataset of individual HEAs described by a large set of electrical features computed from current and voltage measurements in steady-state conditions and investigates a large number of new methods resulting from the combination of different feature selection techniques with several classification algorithms.
An Event-Driven Convolutional Neural Architecture for Non-Intrusive Load Monitoring of Residential Appliance
TLDR
An intelligent event-driven non-intrusive load monitoring method based on convolutional neural network (CNN) is proposed in this article to profile residential consumer behavior, which focused on limited applicability and low recognition accuracy of existing NILM techniques.
A Deep Learning Technique using Low Sampling rate for residential Non Intrusive Load Monitoring
TLDR
A novel deep neural network-based approach for performing load disaggregation on low frequency power data obtained from residential households using a series of one-dimensional Convolutional Neural Networks and Long Short Term Memory to extract features that can identify active appliances and retrieve their power consumption given the aggregated household power value.
A Scalable Real-Time Non-Intrusive Load Monitoring System for the Estimation of Household Appliance Power Consumption
TLDR
Experimental results reveal that the proposed NILM system can achieve promising results in real-time, presenting high computational and memory efficiency.
Image ‐ based mains signal disaggregation and load recognition
  • Sun
  • Computer Science, Engineering
  • 2020
TLDR
This paper uses convolutional neural networks that very well adapted to vision recognition to transform the power series into a reduced image dataset that contains a rich set of localized signal features and proposes an image-based mains load recognition system with high performance.
Review on Deep Neural Networks Applied to Low-Frequency NILM
TLDR
This paper reviews non-intrusive load monitoring approaches that employ deep neural networks to disaggregate appliances from low frequency data, i.e., data with sampling rates lower than the AC base frequency and does a performance comparison with respect to reported mean absolute error (MAE) and F1-scores.
Non-Intrusive Load Disaggregation Based on a Multi-Scale Attention Residual Network
TLDR
The experimental results show that the proposed non-intrusive sequential energy disaggregation method based on a multi-scale attention residual network has more advantages than the existing algorithms in terms of load disag segregation accuracy and judgments of the on/off state, and the attention mechanism can further improve the disaggregation accuracy of low-frequency electrical appliances.
Modelling the disaggregated demand for electricity at the level of residential buildings with the use of artificial neural networks (deep learning approach)
TLDR
The research confirmed the possibility of using ANN in modelling the disaggregation of electricity consumption and indicated the way of building a highly optimized model.
...
...

References

SHOWING 1-10 OF 27 REFERENCES
Convolutional Neural Network Applied to the Identification of Residential Equipment in Nonintrusive Load Monitoring Systems
TLDR
The results obtained in the test database indicate that the proposed system is able to carry out the identification task, and presented satisfactory results when compared with the results already presented in the literature for the problem in question.
Appliance classification using VI trajectories and convolutional neural networks
An Empirical Study on Energy Disaggregation via Deep Learning
TLDR
This paper introduces the feature extraction method that uses multiple parallel convolutional layers of varying filter sizes and presents an LSTM (Long Short Term Memory) based recurrent network model as well as an auto-encoder model for energy disaggregation.
On a Training-Less Solution for Non-Intrusive Appliance Load Monitoring Using Graph Signal Processing
TLDR
The main idea is to build upon the emerging field of graph signal processing to perform adaptive thresholding, signal clustering, and pattern matching in NALM and demonstrate the effectiveness of the proposed method for typical smart meter sampling rate.
Appliance Recognition from Electric Current Signals for Information-Energy Integrated Network in Home Environments
TLDR
An electric appliance recognition method using power-sensing data measured by CECU which is an intelligent outlet with voltage and current sensors to integrate legacy appliances (which are incompatible with a communications network) with the home network is described.
An Experimental Study on Electrical Signature Identification of Non-Intrusive Load Monitoring (NILM) Systems
TLDR
This work presents the development of an algorithm for electrical feature extraction and pattern recognition, capable of determining the individual consumption of each device from the aggregate electric signal of the home.
Neural NILM: Deep Neural Networks Applied to Energy Disaggregation
TLDR
Three deep neural network architectures are adapted to energy disaggregation and it is found that all three neural nets achieve better F1 scores than either combinatorial optimisation or factorial hidden Markov models and that the neural net algorithms generalise well to an unseen house.
Recent approaches to non-intrusive load monitoring techniques in residential settings
TLDR
A review of recent research efforts on state-of-the-art NILM algorithms is provided before concluding with a baseline and overall vision for the future research direction.
Unsupervised training methods for non-intrusive appliance load monitoring from smart meter data
TLDR
An unsupervised training method for NIALM which combines general appliance knowledge with just aggregate smart meter data from the household to perform disaggregation and outperforms the current state of the art, which uses a factorial hidden Markov model to tune the general appliance models.
State of art on load monitoring methods
This paper deals with a state of art about the most non-intrusive load monitoring (NILM) methods. These methods allow identifying consumption of the electrical loads. In the context of sustainable
...
...