Sliding Window Approach for Online Energy Disaggregation Using Artificial Neural Networks

Krystalakos, Odysseas; Nalmpantis, Christoforos; Vrakas, Dimitris

doi:10.1145/3200947.3201011

Cited by 127 publications

(78 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The performance of NILM algorithms has usually been evaluated through four critical metrics (Krystalakos et al, 2018), which are accuracy, precision, F1 score, and recall. These four metrics are defined as follows.…”

Section: Experiments Data and Resultsmentioning

confidence: 99%

“…Liu et al (2019) developed a convolutional neural network (CNN)-based NILM algorithm. Kelly and Knottenbelt (2015), Zhou et al (2020), and Krystalakos et al (2018) selected the recurrent neural network (RNN) to perform one-one mapping instead of direct classification from the aggregated power data. However, the main disadvantage of these popular BP-ANN algorithms is that they are not suitable for low-cost NILM devices such as smart meters for the following reasons: 1) the training time, as well as space cost, is extremely expensive; 2) the convergence of the BP-ANNs relies on the selection of NN parameters such as the activation functions, learning rates, or NN’s structure; 3) it is difficult to detect the on/off events from the aggregated power data.…”

Section: Introductionmentioning

confidence: 99%

“…To demonstrate the effectiveness of the proposed algorithm, the numerical experiments were carried out on a benchmark REDD (Kolter and Johnson, 2011) dataset, and the performance of the proposed algorithm is compared with several well-known NILM algorithms such as FHMM (Kolter and Jaakkola, 2012) and combinatorial optimization (CO; Hart, 1992). In addition, the proposed algorithm has been compared with existing RNN-based NILM approaches (Kelly and Knottenbelt, 2015; Krystalakos et al, 2018). Moreover, a hardware testbed has been designed to further evaluate the PNN-based algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Self-organizing probability neural network-based intelligent non-intrusive load monitoring with applications to low-cost residential measuring devices

Zhou

Xiang

et al. 2020

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

Non-intrusive load monitoring (NILM) is a critical technique for advanced smart grid management due to the convenience of monitoring and analysing individual appliances’ power consumption in a non-intrusive fashion. Inspired by emerging machine learning technologies, many recent non-intrusive load monitoring studies have adopted artificial neural networks (ANN) to disaggregate appliances’ power from the non-intrusive sensors’ measurements. However, back-propagation ANNs have a very limit ability to disaggregate appliances caused by the great training time and uncertainty of convergence, which are critical flaws for low-cost devices. In this paper, a novel self-organizing probabilistic neural network (SPNN)-based non-intrusive load monitoring algorithm has been developed specifically for low-cost residential measuring devices. The proposed SPNN has been designed to estimate the probability density function classifying the different types of appliances. Compared to back-propagation ANNs, the SPNN requires less iterative synaptic weights update and provides guaranteed convergence. Meanwhile, the novel SPNN has less space complexity when compared with conventional PNNs by the self-organizing mechanism which automatically edits the neuron numbers. These advantages make the algorithm especially favourable to low-cost residential NILM devices. The effectiveness of the proposed algorithm is demonstrated through numerical simulation by using the public REDD dataset. Performance comparisons with well-known benchmark algorithms have also been provided in the experiment section.

show abstract

Section: Experiments Data and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-organizing probability neural network-based intelligent non-intrusive load monitoring with applications to low-cost residential measuring devices

Zhou

Xiang

et al. 2020

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

show abstract

“…• Recurrent network with GRU: The idea of using gate recurrent unit (GRU) instead of LSTM in recurrent network was proposed by D. Murray et al [4], Krystalakos et al [9] and [19]. Since the there is different models with different implementations, we will use the LSTM model from (b) but we replace the use of LSTM with GRU to medicate the poor performance of LSTM achieved by J.Kelly experiment.…”

Section: Experimental Designmentioning

confidence: 99%

“…Recently, deep learning techniques have been widely used in solving the low-frequency-based NILM problem, due to their capabilities of extracting features and patterns [4]- [9]. For example, three models were proposed in [5]: first model was based on denoising autoencoder (DAE) that is aiming to reconstruct a clean target from the noisy data input.…”

Section: Introductionmentioning

confidence: 99%

Investigation of Deep Learning-based Techniques for Load Disaggregation, Low-Frequency Approach

Alkhulaifi¹,

Aljohani²

2020

IJACSA

View full text Add to dashboard Cite

Unlike sub-metering, which requires individual appliances to be equipped with their own meters, non-intrusive load monitoring (NILM) use algorithms to discover appliance individual consumption from the aggregated overall energy reading. Approaches that uses low frequency sampled data are more applicable in a real world smart meters that has typical sampling capability of ≤ 1Hz. In this paper, a systematic literature review on deep-learning-based approaches for NILM problem is conducted, aiming to analyse the four key aspects pertaining to deep learning adoption. This includes deep learning model adoption, features selection that are used to train the model, used data set and model accuracy. In our study, analyses the performance of four different deep learning approaches, namely, denoising autoencoder (DAE), recurrent long short-term memory (LSTM) , Recurrent gate recurrent unit (GRU), and sequence to point. Our experiments will be conducted using the two data sets, namely, REDD and UK-DALE. According to our analysis, the sequence to point model has achieved the best results with an average mean absolute error (MAE) of 14.98 watt when compared to other counterpart algorithms.

show abstract

Non‐Intrusive Load Monitoring Using A Parallel Bidirectional Long Short‐Term Memory Model

Andrean

Lian

2022

Intelligent Data Mining and Analysis in Power and Energy Systems

View full text Add to dashboard Cite

Sliding Window Approach for Online Energy Disaggregation Using Artificial Neural Networks

Cited by 127 publications

References 10 publications

Self-organizing probability neural network-based intelligent non-intrusive load monitoring with applications to low-cost residential measuring devices

Self-organizing probability neural network-based intelligent non-intrusive load monitoring with applications to low-cost residential measuring devices

Investigation of Deep Learning-based Techniques for Load Disaggregation, Low-Frequency Approach

Non‐Intrusive Load Monitoring Using A Parallel Bidirectional Long Short‐Term Memory Model

Contact Info

Product

Resources

About