PyTorchKR Papers

최신 논문

총 98편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2104.07809

A Novel Hybrid Deep Learning Approach for Non-Intrusive Load Monitoring of Residential Appliance Based on Long Short Term Memory and Convolutional Neural Networks

Energy disaggregation or nonintrusive load monitoring (NILM), is a single-input blind source discrimination problem, aims to interpret the mains user electricity consumption into appliance level measurement. This article presents a new approach for power disaggregation by using a deep recurrent long short term memory (LSTM) network combined with convolutional neural networks (CNN). Deep neural networks have been shown to be a significant way for these types of problems because of their complexity and huge number of trainable paramters. Hybrid method that proposed in the article could significantly increase the overall accuracy of NILM because it benefits from both network advantages. The proposed method used sequence-to-sequence learning, where the input is a window of the mains and the output is a window of the target appliance. The proposed deep neural network approach has been applied to real-world household energy dataset "REFIT". The REFIT electrical load measurements dataset described in this paper includes whole house aggregate loads and nine individual appliance measurements at 8-second intervals per house, collected continuously over a period of two years from 20 houses around the UK. The proposed method achieve significant performance, improving accuracy and F1-score measures by 95.93% and 80.93% ,respectively which demonstrates the effectiveness and superiority of the proposed approach for home energy monitoring. Comparison of proposed method and other recently published method has been presented and discussed based on accuracy, number of considered appliances and size of the deep neural network trainable parameters. The proposed method shows remarkable performance compare to other previous methods.

arXiv:2104.03120

Unsupervised Disaggregation of Water Heater Load from Smart Meter Data Processing

In the residential sector, electric water heaters are appliances with a relatively high power consumption and a significant thermal inertia, which is particularly suitable for Demand Response schemes. The success of efficient DR schemes via the control of water heaters presupposes an accurate estimate of their power demand at each instant. Although the load of water heaters is rarely directly measured, a large penetration of Smart Meters (SMs) in distribution grids enables to indirectly infer this information on a large scale via load disaggregation. For that purpose, a considerable number of Non-Intrusive Load Monitoring (NILM) approaches are suggested in the literature. However, they require data streams at a time resolution in the range of one second or higher, which is not realistic for standard SMs. Hence, this paper proposes an unsupervised approach to detect and disaggregate the load profile of water heaters from standard SM data with a time resolution in the minute range. Evaluated on multiple real loads with sub-metering, the proposed approach achieves a Normalized Mean Absolute Error (NMAE) lower than 2% and a precision generally higher than 92% with time resolutions between 5 and 15 minutes.

arXiv:2104.01618

A Federated Learning Framework for Non-Intrusive Load Monitoring

Non-intrusive load monitoring (NILM) aims at decomposing the total reading of the household power consumption into appliance-wise ones, which is beneficial for consumer behavior analysis as well as energy conservation. NILM based on deep learning has been a focus of research. To train a better neural network, it is necessary for the network to be fed with massive data containing various appliances and reflecting consumer behavior habits. Therefore, data cooperation among utilities and DNOs (distributed network operators) who own the NILM data has been increasingly significant. During the cooperation, however, risks of consumer privacy leakage and losses of data control rights arise. To deal with the problems above, a framework to improve the performance of NILM with federated learning (FL) has been set up. In the framework, model weights instead of the local data are shared among utilities. The global model is generated by weighted averaging the locally-trained model weights to gather the locally-trained model information. Optimal model selection help choose the model which adapts to the data from different domains best. Experiments show that this proposal improves the performance of local NILM runners. The performance of this framework is close to that of the centrally-trained model obtained by the convergent data without privacy protection.

arXiv:2103.12177공식 코드 · Papers with Code

Energy Disaggregation using Variational Autoencoders

Non-intrusive load monitoring (NILM) is a technique that uses a single sensor to measure the total power consumption of a building. Using an energy disaggregation method, the consumption of individual appliances can be estimated from the aggregate measurement. Recent disaggregation algorithms have significantly improved the performance of NILM systems. However, the generalization capability of these methods to different houses as well as the disaggregation of multi-state appliances are still major challenges. In this paper we address these issues and propose an energy disaggregation approach based on the variational autoencoders framework. The probabilistic encoder makes this approach an efficient model for encoding information relevant to the reconstruction of the target appliance consumption. In particular, the proposed model accurately generates more complex load profiles, thus improving the power signal reconstruction of multi-state appliances. Moreover, its regularized latent space improves the generalization capabilities of the model across different houses. The proposed model is compared to state-of-the-art NILM approaches on the UK-DALE and REFIT datasets, and yields competitive results. The mean absolute error reduces by 18% on average across all appliances compared to the state-of-the-art. The F1-Score increases by more than 11%, showing improvements for the detection of the target appliance in the aggregate measurement.

arXiv:2102.12578

A Comprehensive Review on the NILM Algorithms for Energy Disaggregation

The housing structures have changed with urbanization and the growth due to the construction of high-rise buildings all around the world requires end-use appliance energy conservation and management in real-time. This shift also came along with smart-meters which enabled the estimation of appliance-specific power consumption from the buildings aggregate power consumption reading. Non-intrusive load monitoring (NILM) or energy disaggregation is aimed at separating the household energy measured at the aggregate level into constituent appliances. Over the years, signal processing and machine learning algorithms have been combined to achieve this. Incredible research and publications have been conducted on energy disaggregation, non-intrusive load monitoring, home energy management and appliance classification. There exists an API, NILMTK, a reproducible benchmark algorithm for the same. Many other approaches to perform energy disaggregation has been adapted such as deep neural network architectures and big data approach for household energy disaggregation. This paper provides a survey of the effective NILM system frameworks and reviews the performance of the benchmark algorithms in a comprehensive manner. This paper also summarizes the wide application scope and the effectiveness of the algorithmic performance on three publicly available data sets.

arXiv:2101.07191

Quantification of Disaggregation Difficulty with Respect to the Number of Meters

A promising approach toward efficient energy management is non-intrusive load monitoring (NILM), that is to extract the consumption profiles of appliances within a residence by analyzing the aggregated consumption signal. Among efficient NILM methods are event-based algorithms in which events of the aggregated signal are detected and classified in accordance with the appliances causing them. The large number of appliances and the presence of appliances with close consumption values are known to limit the performance of event-based NILM methods. To tackle these challenges, one could enhance the feature space which in turn results in extra hardware costs, installation complexity, and concerns regarding the consumer's comfort and privacy. This has led to the emergence of an alternative approach, namely semi-intrusive load monitoring (SILM), where appliances are partitioned into blocks and the consumption of each block is monitored via separate power meters. While a greater number of meters can result in more accurate disaggregation, it increases the monetary cost of load monitoring, indicating a trade-off that represents an important gap in this field. In this paper, we take a comprehensive approach to close this gap by establishing a so-called notion of "disaggregation difficulty metric (DDM)," which quantifies how difficult it is to monitor the events of any given group of appliances based on both their power values and the consumer's usage behavior. Thus, DDM in essence quantifies how much is expected to be gained in terms of disaggregation accuracy of a generic event-based algorithm by installing meters on the blocks of any partition of the appliances. Experimental results based on the REDD dataset illustrate the practicality of the proposed approach in addressing the aforementioned trade-off.

arXiv:2101.07190

Incorporating Coincidental Water Data into Non-intrusive Load Monitoring

Non-intrusive load monitoring (NILM) as the process of extracting the usage pattern of appliances from the aggregated power signal is among successful approaches aiding residential energy management. In recent years, high volume datasets on power profiles have become available, which has helped make classification methods employed for the NILM purpose more effective and more accurate. However, the presence of multi-mode appliances and appliances with close power values have remained influential in worsening the computational complexity and diminishing the accuracy of these algorithms. To tackle these challenges, we propose an event-based classification process, in the first phase of which the $K$-nearest neighbors method, as a fast classification technique, is employed to extract power signals of appliances with exclusive non-overlapping power values. Then, two deep learning models, which consider the water consumption of some appliances as a novel signature in the network, are utilized to distinguish between appliances with overlapping power values. In addition to power disaggregation, the proposed process as well extracts the water consumption profiles of specific appliances. To illustrate the proposed process and validate its efficiency, seven appliances of the AMPds are considered, with the numerical classification results showing marked improvement with respect to the existing classification-based NILM techniques.

arXiv:2004.13905

End-to-end NILM System Using High Frequency Data and Neural Networks

Improving energy efficiency is a necessity in the fight against climate change. Non Intrusive Load Monitoring (NILM) systems give important information about the household consumption that can be used by the electric utility or the end users. In this work the implementation of an end-to-end NILM system is presented, which comprises a custom high frequency meter and neural-network based algorithms. The present article presents a novel way to include high frequency information as input of neural network models by means of multivariate time series that include carefully selected features. Furthermore, it provides a detailed assessment of the generalization error and shows that this class of models generalize well to new instances of seen-in-training appliances. An evaluation database formed of measurements in two Uruguayan homes is collected and discussion on general unsupervised approaches is provided.

arXiv:2002.05593

Augmenting an Assisted Living Lab with Non-Intrusive Load Monitoring

The need for reducing our energy consumption footprint and the increasing number of electric devices in today's homes is calling for new solutions that allow users to efficiently manage their energy consumption. Real-time feedback at device level would be of a significant benefit for this application. In addition, the aging population and their wish to be more autonomous have motivated the use of this same real-time data to indirectly monitor the household's occupants for their safety. By breaking down aggregate power consumption into its components, Non-Intrusive Load Monitoring provides information on individual appliances and their current state of operation. Since no additional metering equipment is required, residents are not confronted with intrusion into their familiar environment. Our work aims to depict an architecture supporting non-intrusive measurement with a smart electricity meter and the handling of these data using an open-source platform that allows to visualize and process real-time data about the total energy consumed. As a case study, we describe a series of measurements from common household devices and show how abnormal behavior can be detected.

arXiv:1903.09180

A Hybrid Event Detection Approach for Non-Intrusive Load Monitoring

Non-Intrusive Load Monitoring (NILM) is a practical method to provide appliance-level electricity consumption information. Event detection, as an important part of event-based NILM methods, has a direct impact on the accuracy of the ultimate load disaggregation results in the entire NILM framework. This paper presents a hybrid event detection approach for relatively complex household load datasets that include appliances with long transients, high fluctuations, and/or near-simultaneous actions. The proposed approach includes a base algorithm based on moving average change with time limit, and two auxiliary algorithms based on derivative analysis and filtering analysis. The structure, steps, and working principle of this approach are described in detail. The proposed approach does not require additional information about household appliances, nor does it require any training sets. Case studies on different datasets are conducted to evaluate the performance of the proposed approach in comparison with several existing approaches including log likelihood ratio detector with maxima (LLD-Max) approach, active window-based (AWB) approach, and generalized likelihood ratio (GLR) approach. Results show that the proposed approach works well in detecting events in complex household load datasets and performs better than the existing approaches.

arXiv:1809.08910

Functional Intrusive Load Monitor (FILM): A Model-based Platform for Non-Intrusive Load Monitoring System Development

Non-Intrusive Load Monitoring (NILM) is an important application to monitor household appliance activities and provide related information to house owner or/and utility company via a single sensor installed at the electrical entry of the house. It can be used for different purposes in residential and industrial sectors. Thus, an increasing number of new algorithms have been developed in recent years. In these algorithms, researchers either use existing public datasets or collect their own data which causes such problems as insufficiency of electrical parameters, missing of ground-truth data, absence of many appliances, and lack of appliance information. To solve these problems, this paper presents a model-based platform for NILM system development, namely Functional Intrusive Load Monitor (FILM). By using this platform, the state transitions and activities of all the involved appliances can be preset by researchers, and multiple electrical parameters such as harmonics and power factor can be monitored or calculated. This platform will help researchers save the time of collecting experimental data, utilize precise control of individual appliance activities, and develop load signatures of devices. This paper describes the steps, structure, and requirements of building this platform. Case study is presented to help understand this platform.

arXiv:1801.05363

Non Intrusive Load Monitoring in Chaotic Switching Networks

In this work, a non intrusive load disaggregation scheme is proposed. By using a kernel based nonlinear regression strategy, the switching dynamic of an electric network, simulated as a set of RLC circuits with chaotic switching, is approximated using a time series of the total power consumption. The results suggest that the employed methodology can be useful in the design of efficient load disaggregation schemes.

arXiv:2011.14870

Prior Flow Variational Autoencoder: A density estimation model for Non-Intrusive Load Monitoring

Non-Intrusive Load Monitoring (NILM) is a computational technique to estimate the power loads' appliance-by-appliance from the whole consumption measured by a single meter. In this paper, we propose a conditional density estimation model, based on deep neural networks, that joins a Conditional Variational Autoencoder with a Conditional Invertible Normalizing Flow model to estimate the individual appliance's power demand. The resulting model is called Prior Flow Variational Autoencoder or, for simplicity PFVAE. Thus, instead of having one model per appliance, the resulting model is responsible for estimating the power demand, appliance-by-appliance, at once. We train and evaluate our proposed model in a publicly available dataset composed of power demand measures from a poultry feed factory located in Brazil. The proposed model's quality is evaluated by comparing the obtained normalized disaggregation error (NDE) and signal aggregated error (SAE) with the previous work values on the same dataset. Our proposal achieves highly competitive results, and for six of the eight machines belonging to the dataset, we observe consistent improvements that go from 28% up to 81% in NDE and from 27% up to 86% in SAE.

arXiv:2011.06205

Privacy Preserving in Non-Intrusive Load Monitoring: A Differential Privacy Perspective

Smart meter devices enable a better understanding of the demand at the potential risk of private information leakage. One promising solution to mitigating such risk is to inject noises into the meter data to achieve a certain level of differential privacy. In this paper, we cast one-shot non-intrusive load monitoring (NILM) in the compressive sensing framework, and bridge the gap between theoretical accuracy of NILM inference and differential privacy's parameters. We then derive the valid theoretical bounds to offer insights on how the differential privacy parameters affect the NILM performance. Moreover, we generalize our conclusions by proposing the hierarchical framework to solve the multi-shot NILM problem. Numerical experiments verify our analytical results and offer better physical insights of differential privacy in various practical scenarios. This also demonstrates the significance of our work for the general privacy preserving mechanism design.

arXiv:2010.16050공식 코드 · Papers with Code

NILM as a regression versus classification problem: the importance of thresholding

Non-Intrusive Load Monitoring (NILM) aims to predict the status or consumption of domestic appliances in a household only by knowing the aggregated power load. NILM can be formulated as regression problem or most often as a classification problem. Most datasets gathered by smart meters allow to define naturally a regression problem, but the corresponding classification problem is a derived one, since it requires a conversion from the power signal to the status of each device by a thresholding method. We treat three different thresholding methods to perform this task, discussing their differences on various devices from the UK-DALE dataset. We analyze the performance of deep learning state-of-the-art architectures on both the regression and classification problems, introducing criteria to select the most convenient thresholding method.

arXiv:2009.12355

Sequence-to-Sequence Load Disaggregation Using Multi-Scale Residual Neural Network

With the increased demand on economy and efficiency of measurement technology, Non-Intrusive Load Monitoring (NILM) has received more and more attention as a cost-effective way to monitor electricity and provide feedback to users. Deep neural networks has been shown a great potential in the field of load disaggregation. In this paper, firstly, a new convolutional model based on residual blocks is proposed to avoid the degradation problem which traditional networks more or less suffer from when network layers are increased in order to learn more complex features. Secondly, we propose dilated convolution to curtail the excessive quantity of model parameters and obtain bigger receptive field, and multi-scale structure to learn mixed data features in a more targeted way. Thirdly, we give details about generating training and test set under certain rules. Finally, the algorithm is tested on real-house public dataset, UK-DALE, with three existing neural networks. The results are compared and analysed, the proposed model shows improvements on F1 score, MAE as well as model complexity across different appliances.

arXiv:2009.07756

Exploring Bayesian Surprise to Prevent Overfitting and to Predict Model Performance in Non-Intrusive Load Monitoring

Non-Intrusive Load Monitoring (NILM) is a field of research focused on segregating constituent electrical loads in a system based only on their aggregated signal. Significant computational resources and research time are spent training models, often using as much data as possible, perhaps driven by the preconception that more data equates to more accurate models and better performing algorithms. When has enough prior training been done? When has a NILM algorithm encountered new, unseen data? This work applies the notion of Bayesian surprise to answer these questions which are important for both supervised and unsupervised algorithms. We quantify the degree of surprise between the predictive distribution (termed postdictive surprise), as well as the transitional probabilities (termed transitional surprise), before and after a window of observations. We compare the performance of several benchmark NILM algorithms supported by NILMTK, in order to establish a useful threshold on the two combined measures of surprise. We validate the use of transitional surprise by exploring the performance of a popular Hidden Markov Model as a function of surprise threshold. Finally, we explore the use of a surprise threshold as a regularization technique to avoid overfitting in cross-dataset performance. Although the generality of the specific surprise threshold discussed herein may be suspect without further testing, this work provides clear evidence that a point of diminishing returns of model performance with respect to dataset size exists. This has implications for future model development, dataset acquisition, as well as aiding in model flexibility during deployment.

arXiv:2007.13645

PowerGAN: Synthesizing Appliance Power Signatures Using Generative Adversarial Networks

Non-intrusive load monitoring (NILM) allows users and energy providers to gain insight into home appliance electricity consumption using only the building's smart meter. Most current techniques for NILM are trained using significant amounts of labeled appliances power data. The collection of such data is challenging, making data a major bottleneck in creating well generalizing NILM solutions. To help mitigate the data limitations, we present the first truly synthetic appliance power signature generator. Our solution, PowerGAN, is based on conditional, progressively growing, 1-D Wasserstein generative adversarial network (GAN). Using PowerGAN, we are able to synthesise truly random and realistic appliance power data signatures. We evaluate the samples generated by PowerGAN in a qualitative way as well as numerically by using traditional GAN evaluation methods such as the Inception score.

arXiv:2007.11819

A Non-Intrusive Load Monitoring Approach for Very Short Term Power Predictions in Commercial Buildings

This paper presents a new algorithm to extract device profiles fully unsupervised from three phases reactive and active aggregate power measurements. The extracted device profiles are applied for the disaggregation of the aggregate power measurements using particle swarm optimization. Finally, this paper provides a new approach for short term power predictions using the disaggregation data. For this purpose, a state changes forecast for every device is carried out by an artificial neural network and converted into a power prediction afterwards by reconstructing the power regarding the state changes and the device profiles. The forecast horizon is 15 minutes. To demonstrate the developed approaches, three phase reactive and active aggregate power measurements of a multi-tenant commercial building are used. The granularity of data is 1 s. In this work, 52 device profiles are extracted from the aggregate power data. The disaggregation shows a very accurate reconstruction of the measured power with a percentage energy error of approximately 1 %. The developed indirect power prediction method applied to the measured power data outperforms two persistence forecasts and an artificial neural network, which is designed for 24h-day-ahead power predictions working in the power domain.

arXiv:2006.00250

Sequence to Point Learning Based on Bidirectional Dilated Residual Network for Non Intrusive Load Monitoring

Non Intrusive Load Monitoring (NILM) or Energy Disaggregation (ED), seeks to save energy by decomposing corresponding appliances power reading from an aggregate power reading of the whole house. It is a single channel blind source separation problem (SCBSS) and difficult prediction problem because it is unidentifiable. Recent research shows that deep learning has become a growing popularity for NILM problem. The ability of neural networks to extract load features is closely related to its depth. However, deep neural network is difficult to train because of exploding gradient, vanishing gradient and network degradation. To solve these problems, we propose a sequence to point learning framework based on bidirectional (non-casual) dilated convolution for NILM. To be more convincing, we compare our method with the state of art method, Seq2point (Zhang) directly and compare with existing algorithms indirectly via two same datasets and metrics. Experiments based on REDD and UK-DALE data sets show that our proposed approach is far superior to existing approaches in all appliances.