Non-intrusive Load Monitoring Method Research Articles

A Novel Transfer Learning-Based Intelligent Nonintrusive Load-Monitoring With Limited Measurements

In this article, the real-time nonintrusive load-monitoring (NILM) problem with limited measurements, i.e., low sampling rate data, is investigated. NILM is a technique to identify the various types of appliances by analyzing the voltage and current features collected by sensors, such as smart outlets. It is one of the most important topics in smart grid management and optimization. Although recent NILM methods developed several general models that can be used for various scenarios, these algorithms either require high-frequency measurement devices or have been limited to use for some specific appliances. A real-time intelligent NILM algorithm that is able to be transferred among different appliances with low-frequency data is still lacking and desperately needed. In this article, a novel online learning-based intelligent NILM algorithm has been developed that can, online, infer a variety of appliances using a transferred model with limited measurements. Especially, the developed algorithm integrates the emerging transfer learning technique along with deep neural networks. Two neural networks are used in two different stages: 1) the long short-term memory (LSTM) neural network to extract the lower level spatial and temporal features from the gray-scale image generated by the measurements and 2) the probabilistic neural network (PNN) to classify the appliance type as well as transfer between appliances. Finally, the algorithm is implemented into practical smart outlet hardware to demonstrate its effectiveness.

Automatic Implementation of a Self-Adaption Non-Intrusive Load Monitoring Method Based on the Convolutional Neural Network

Non-intrusive load monitoring (NILM) is an effective way to achieve demand-side measurement and energy efficiency optimization. This paper studies a method of non-intrusive on-line load monitoring under a high-frequency mode of electric data acquisition, which enables the NILM to be automated and in real-time, including the short-term construction of a dynamic signature library and continuous on-line load identification. Firstly, in the short initial operation phase, load separation and category determination are carried out to construct the load waveform library of the monitoring user. Then, the continuous load monitoring phase begins. Based on the data of each user’s signature library, the decomposition waveforms are classified by convolutional neural network models that are constructed to be suitable for each signature library in order to realize load identification. The real-time power consumption status of the load can be obtained continuously. In this paper, the electricity data of actual users are collected and used to perform the experiments, which show that the proposed method can construct the load signature library adaptively for different users. Meanwhile, the classification of the convolutional neural network model based on a library constructed in actual operation ensures the real-time and accuracy of load monitoring.

Non-Intrusive Load Monitoring based on Deep Neural Network and Differential Current

In daily life, it is easy to obtain the power consumption information of a house by installing an energy meter at the entrance. The non-intrusive load monitoring method can decompose the power consumption and the working state of a specific load according to the aggregated information of the power inlet, and then help people to save electricity. Here, we present a novel and complete non-intrusive load identification algorithm based on deep neural network and differential current. The algorithm includes several modules for data preparation, event detection, feature extraction and load identification, and uses the BLUED dataset to test the feasibility of the proposed algorithm.

An Event-Driven Convolutional Neural Architecture for Non-Intrusive Load Monitoring of Residential Appliance

Nowadays, the advancement of non-intrusive load monitoring (NILM) is hastened by the everincreasing requirements for smart power utilization and demand side management. Thus, 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. The deep convolutional neural architecture improves the performance of load monitoring procedure, and extends its application range to monitoring process in terms of various and combined characteristics. Meanwhile, the event-driven procedure is conducted to find the start-stop time and state change of the appliance accurately, including zero-cross detection, current similarity detection, threshold evaluation, and event current acquisition. Subsequently, the current-to-image conversion is carried out to represent the characteristics of residential appliance as the input of CNN. And the convolutional neural architecture is proposed to identify the power consumption load and its working condition. Selected experimental results are performed that the average recognition accuracy is over 93%, which demonstrates the effectiveness and superiority of the proposed methodology for home energy management.

Nonintrusive on-site load-monitoring method with self-adaption

Nonintrusive load monitoring (NILM) is an effective way to measure the demand side of electricity consumption. An on-site NILM method in high-frequency acquisition mode was explored, which makes the entire process, including the construction of load-waveform decomposition and a short-term dynamic signature database, as well as continuous on-site load identification, automatic and executable in real time. First, a load decomposition model was established based on the additivity principle of load current to obtain the independent load waveform. According to the operational signatures of the load, there was no need to obtain prior data by conducting a preliminary experiment. The load type was judged by Bayesian classification model, and a dynamic load signature database was adaptively built for independent users. Based on the dynamic signature database, load identification was realized by optimization model, obtaining the electricity consumption of load in real time. The effectiveness of the method was verified by measuring electricity-consumption data. According to the experiment, the method can be automatically executed on-site to adapt to different users, and the dynamic signature database established improves the weak universality caused by establishing the database in advance. The fast optimization based on the signature database ensures the identification is efficient and accurate.

Non-intrusive load monitoring and decomposition method based on decision tree

In order to realize the problems of non-intrusive load monitoring and decomposition (NILMD) from two aspects of load identification and load decomposition, based on the load characteristics of the database, this paper firstly analyzes and identifies the equipment composition of mixed electrical equipment group by using the load decision tree algorithm. Then, a 0–1 programming model for the equipment status identification is established, and the Particle Swarm Optimization (PSO) is used to solve the model for equipment state recognition, and the equipment operating state in the equipment group is identified. Finally, a simulation experiment is carried out for the partial data of Question A in the 6th “teddy cup” data mining challenge competition.

An improved non-intrusive load disaggregation algorithm and its application

The non-intrusive load monitoring (NILM) method is proposed to acquire the energy consumption of appliances in a building. Steady-state current decomposition is one of the most effective and applicable methods in NILM. Although many load features and decomposing models have been developed in the previous work, the harmonic vectors have been rarely discussed. In this study, weighted current harmonic vectors are proposed to increase the weight of the useful harmonic. The harmonic vectors are calculated geometrically so that all the information in features can be retained. A multi-objective particle swarm optimization based model is built to carry out the disaggregation task, where both summation and standard deviation of the errors are considered as objective functions. Moreover, to make the public datasets available in current decomposition, a current superimposing method is proposed. It generates aggregated currents from the currents of appliances running independently. Finally, the proposed model and two contrast models are performed on the WHITED dataset. The experimental results indicate that the proposed method is more robust and has higher current disaggregation precision than the involved comparing methods.

A new approach of electrical appliance identification in residential buildings

This paper proposes a simple algorithm about non-intrusive appliance load monitoring (NIALM) method. The main objective is to analyze the overall power consumption of a given building and to identify the different operating appliances. This approach aims to reduce the overall energy expense of maintaining a specified level of comfort. In our approach, we firstly replace the main signal by a shorter form in order to reduce computing time. This criterion is important to guarantee real-time operation mode. Furthermore, we can classify the operating devices through their type and the mean electrical power consumed. Finally, for identification, we use the template’s waveform matching to identify the individual energy consumption with an optimized manner. To validate the proposed algorithm, satisfactory simulation results showing the reliability of the proposed NIALM method are found.

Non-Intrusive Load Disaggregation by Linear Classifier Group Considering Multi-Feature Integration

Non-intrusive load monitoring (NILM) is a core technology for demand response (DR) and energy conservation services. Traditional NILM methods are rarely combined with practical applications, and most studies aim to disaggregate the whole loads in a household, which leads to low identification accuracy. In this method, the event detection method is used to obtain the switching event sets of all loads, and the power consumption curves of independent unknown electrical appliances in a period are disaggregated by utilizing comprehensive features. A linear discriminant classifier group based on multi-feature global similarity is used for load identification. The uniqueness of our algorithm is that it designs an event detector based on steady-state segmentation and a linear discriminant classifier group based on multi-feature global similarity. The simulation is carried out on an open source data set. The results demonstrate the effectiveness and high accuracy of the multi-feature integrated classification (MFIC) algorithm by using the state-of-the-art NILM methods as benchmarks.

Unsupervised algorithm for disaggregating low-sampling-rate electricity consumption of households

Non-intrusive load monitoring (NILM) has been extensively researched over the last decade. The objective of NILM is to identify the power consumption of individual appliances and to detect when particular devices are on or off from measuring the power consumption of an entire house. This information allows households to receive customized advice on how to better manage their electrical consumption. In this paper, we present an alternative NILM method that breaks down the aggregated power signal into categories of appliances. The ultimate goal is to use this approach for demand-side management to estimate potential flexibility within the electricity consumption of households. Our method is implemented as an algorithm combining NILM and load profile simulation. This algorithm, based on a Markov model, allocates an activity chain to each inhabitant of the household, deduces from the whole-house power measurement and statistical data the appliance usage, generate the power profile accordingly and finally returns the share of energy consumed by each appliance category over time. To analyze its performance, the algorithm was benchmarked against several state-of-the-art NILM algorithms and tested on three public datasets. The proposed algorithm is unsupervised; hence it does not require any labeled data, which are expensive to acquire. Although better performance is shown for the supervised algorithms, our proposed unsupervised algorithm achieves a similar range of uncertainty while saving on the cost of acquiring labeled data. Additionally, our method requires lower computational power compared to most of the tested NILM algorithms. It was designed for low-sampling-rate power measurement (every 15 min), which corresponds to the frequency range of most common smart meters.

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.

A nonintrusive power load monitoring method using coupled allocation mechanism

A nonintrusive power load monitoring method using coupled allocation mechanism

NILM Techniques for Intelligent Home Energy Management and Ambient Assisted Living: A Review

The ongoing deployment of smart meters and different commercial devices has made electricity disaggregation feasible in buildings and households, based on a single measure of the current and, sometimes, of the voltage. Energy disaggregation is intended to separate the total power consumption into specific appliance loads, which can be achieved by applying Non-Intrusive Load Monitoring (NILM) techniques with a minimum invasion of privacy. NILM techniques are becoming more and more widespread in recent years, as a consequence of the interest companies and consumers have in efficient energy consumption and management. This work presents a detailed review of NILM methods, focusing particularly on recent proposals and their applications, particularly in the areas of Home Energy Management Systems (HEMS) and Ambient Assisted Living (AAL), where the ability to determine the on/off status of certain devices can provide key information for making further decisions. As well as complementing previous reviews on the NILM field and providing a discussion of the applications of NILM in HEMS and AAL, this paper provides guidelines for future research in these topics.

An online non-intrusive load monitoring method based on Hidden Markov model

Non-intrusive load monitoring (NILM) can decompose the total power consumption measured by the smart meter into the power consumed by the individual appliances, so as to achieve the purpose of saving energy. In this paper, an improved method of Daubechies9 (DB9) which is a discrete wavelet is proposed, which can effectively remove the noise of the low-frequency components. On this basis, an online NILM method based on Hidden Markov model (HMM) is proposed. The model of load switching can be built using apparent power of transient-state with this method. Besides, the improved forward algorithm which effectively suppressing the data underflow in load classification is proposed. The proposed methods are embedded in the smart meter and can increase the overall recognition rate of the load over 90% in the experiments which prove that they have good applicability.

Neural Network with Extended Input for Estimating Electricity Consumption Using Background-based Data Generation

Non-intrusive load monitoring (NILM) can infer the electricity consumption of individual target appliances by only collecting and analyzing the aggregate power data at the single power entrance point. This detailed information obtained is of great significance to smart grid operation and energy saving. For solving the problems of feature loss and training data acquisition in current deep neural network-based NILM methods, this paper presents an extended input neural network method using background-based data generation for estimating electricity consumption. First, the extended input method is proposed, which ensures a complete working cycle to be fed into the neural network each time. Then, a synthetic method based on the power use background is used to generate abundant and desirable training data. Finally, the proposed methods are validated through comparison tests.

Incorporating Appliance Usage Patterns for Non-Intrusive Load Monitoring and Load Forecasting

This paper proposes a novel non-intrusive load monitoring (NILM) method which incorporates appliance usage patterns (AUPs) to improve performance of active load identification and forecasting. In the first stage, the AUPs of a given residence were learned using a spectral decomposition based standard NILM algorithm. Then, learnt AUPs were utilized to bias the priori probabilities of the appliances through a specifically constructed fuzzy system. The AUPs contain likelihood measures for each appliance to be active at the present instant based on the recent activity/inactivity of appliances and the time of day. Hence, the priori probabilities determined through the AUPs increase the active load identification accuracy of the NILM algorithm. The proposed method was successfully tested for two standard databases containing real household measurements in USA and Germany. The proposed method demonstrates an improvement in active load estimation when applied to the aforementioned databases as the proposed method augments the smart meter readings with the behavioral trends obtained from AUPs. Furthermore, a residential power consumption forecasting mechanism, which can predict the total active power demand of an aggregated set of houses, 5 min ahead of real time, was successfully formulated and implemented utilizing the proposed AUP based technique.

A NILM method for cooling load disaggregation based on artificial neural network

The demand of building energy management has increased due to high energy saving potentials. Load monitor and disaggregation can provide useful information for building energy management systems with detailed and individual loads of the building, so corresponding energy efficient measures can be taken to reduce the energy consumption of buildings. The technique is investigated widely in residential buildings known as Non-Intrusive Load Monitoring (NILM). However, relevant studies are not sufficient for non-residential buildings, especially for the cooling loads. This paper proposes a NILM method for cooling load disaggregation using artificial neural network. The cooling load is disaggregated into four categories: building envelope load, occupant load, equipment load and fresh air load. Two approaches are used to realize the load disaggregation: one is based on the Fourier transfer of the cooling loads, the other takes the cooling load, dry-bulb temperature and humidity of outdoor air, and time as inputs. By implementing the methods in a metro station, the performance of the proposed method can be obtained. Results show that both approaches can realize the load disaggregation accurately, with a RMSE less than 11.2. The second approach is recommended with a higher accuracy.

Uma revisão bibliométrica sobre a identificação de cargas similares em Smart Grid

Diante da necessidade de uso consciente dos recursos energéticos para o crescimento sustentável, o conceito Smart Grid tem servido de referência para o uso eficiente de tais recursos, sobretudo o elétrico. Entretanto, a aplicação de tal conceito nas instalações elétricas requer o desenvolvimento de dispositivos que permitam o monitoramento autônomo de aparelhos eletroeletrônicos em tais instalações. Este artigo tem como objetivo realizar uma revisão bibliométrica sobre os métodos não-intrusivo de monitoramento de cargas, a fim de mostrar o estado da arte dessa temática, isto é, os principais avanços e entraves para o desenvolvimento dessa tecnologia. É realizada uma análise quantitativa e qualitativa dos trabalhos referentes ao tema buscados via base de dados Web of Science. Como resultado de tal investigação, observa-se a relevância dos estudos nessa área, que está em pleno crescimento. Cita-se ainda o fato de o tema estar sendo investigado tanto em países desenvolvidos, como Canadá e Estados Unidos, quanto em países em desenvolvimento, como Malásia e Índia, o que mostra que existe uma preocupação mundial em se avançar em tal problema que independe da situação econômica da nação.

Detection of unidentified appliances in non-intrusive load monitoring using siamese neural networks

Non-intrusive load monitoring methods aim to disaggregate the total power consumption of a household into individual appliances by analyzing changes in the voltage and current measured at the grid connection point of the household. The goal is to identify the active appliances, based on their unique fingerprint. Most state-of-the-art classification algorithms rely on the assumption that all events in the data stream are triggered by known appliances, which is often not the case. This paper proposes a method capable of detecting previously unidentified appliances in an automated way. For this, appliances represented by their VI trajectory are mapped to a newly learned feature space created by a siamese neural network such that samples of the same appliance form tight clusters. Then, clustering is performed by DBSCAN allowing the method to assign appliance samples to clusters or label them as ‘unidentified’. Benchmarking on PLAID and WHITED shows that an F1,macro-measure of respectively 0.90 and 0.85 can be obtained for classifying the unidentified appliances as ‘unidentified’.

Accurate Energy Use Estimation for Nonintrusive Load Monitoring in Systems of Known Devices

This paper presents a method of nonintrusive load monitoring (NILM) for electrical systems consisting of a fixed and known set of devices. This constraint is inherently met by embedded and mobile power systems, and is also commonly satisfied in industrial settings. The proposed NILM method provides time-accurate profiles of device behavior using only probabilistic device models and system-level measurements. The full method consists of model training, construction of a system-level model, and prediction of device-level energy use. Energy use estimations are determined by maximizing the probability of the predicted behavior given the system-level measurements, and are calculated online at each sampling instant. The method is validated using test data from public databases, and its performance is assessed using standard NILM accuracy metrics. The intended application of the proposed method is to support system status assessments and to provide early indications of potential equipment damage through identification of atypical device behavior.