Energy Disaggregation Research Articles

Transferable Tree-Based Ensemble Model for Non-Intrusive Load Monitoring

Sustainable energy management systems have been increasingly studied in recent years. Non-intrusive load monitoring (NILM), as a key component, estimates the power consumption of individual appliances from the main readings only. However, most NILM approaches are computationally expensive, and their generality is negatively affected by the data drift occurred when the models are used across domains. Besides, the threats of privacy violation will rise in the model transfer due to the possible leakage of the personal information of the users from the source domain. To address all these challenges, we designed a cost-efficient learning method using LightGBM for energy disaggregation. We also proposed a model-based transfer learning algorithm using feature importance analysis, which enhances the generalisation capability of tree-based ensemble models applied in different domains while protecting privacy. We conducted experiments with real-world data sets. The performance of our approach is superior to the state-of-the-art solutions.

A comparative study on pretreatment methods and dimensionality reduction techniques for energy data disaggregation in home appliances

Energy meters provide valuable information that can be used to determine important features such as energy consumption of electrical devices and consumption habits in corporate, residential or public institutions. This information is crucial to establish energy saving strategies. With this aim, different approaches have been proposed in the literature, including non-intrusive load monitoring techniques, which enable the energy disaggregation of appliances and devices through a centralized measurement taken at panel level using a metering infrastructure. Generally, the accuracy of these techniques increases as more information is available on the analyzed signals or through subsequent post-computed values. Active power, reactive power, or even current harmonics measurements can be used for this task. However, the use of these and other recently proposed power and current features increases the dimensionality and, therefore, the complexity of the algorithms involved in the disaggregation process. Therefore, it is necessary to apply advanced techniques to reduce the dimensionality of the data, as well as the possible linear dependence between variables. This paper compares the performance of 8 data pretreatment methods and 6 dimensionality reduction techniques to data retrieved by an advanced metering infrastructure in a real environment consisting of 10 different home appliances. Results obtained from the comparative analysis show that the information provided by raw data can be enhanced by using pretreatment techniques and dimensionality reduction methods, especially when a custom combination of active power and current harmonics measures is considered.

A hybrid data-driven online solar energy disaggregation system from the grid supply point

AbstractThe integration of small-scale Photovoltaics (PV) systems (such as rooftop PVs) decreases the visibility of power systems, since the real demand load is masked. Most rooftop systems are behind the metre and cannot be measured by household smart meters. To overcome the challenges mentioned above, this paper proposes an online solar energy disaggregation system to decouple the solar energy generated by rooftop PV systems and the ground truth demand load from net measurements. A 1D Convolutional Neural Network (CNN) Bidirectional Long Short-Term Memory (BiLSTM) deep learning method is used as the core algorithm of the proposed system. The system takes a wide range of online information (Advanced Metering Infrastructure (AMI) data, meteorological data, satellite-driven irradiance, and temporal information) as inputs to evaluate PV generation, and the system also enables online and offline modes. The effectiveness of the proposed algorithm is evaluated by comparing it to baselines. The results show that the proposed method achieves good performance under different penetration rates and different feeder levels. Finally, a transfer learning process is introduced to verify that the proposed system has good robustness and can be applied to other feeders.

2D Transformations of Energy Signals for Energy Disaggregation.

The aim of Non-Intrusive Load Monitoring is to estimate the energy consumption of individual electrical appliances by disaggregating the overall power consumption that has been sampled from a smart meter at a house or commercial/industrial building. Last decade’s developments in deep learning and the utilization of Convolutional Neural Networks have improved disaggregation accuracy significantly, especially when utilizing two-dimensional signal representations. However, converting time series’ to two-dimensional representations is still an open challenge, and it is not clear how it influences the performance of the energy disaggregation. Therefore, in this article, six different two-dimensional representation techniques are compared in terms of performance, runtime, influence on sampling frequency, and robustness towards Gaussian white noise. The evaluation results show an advantage of two-dimensional imaging techniques over univariate and multivariate features. In detail, the evaluation results show that: first, the active and reactive power-based signatures double Fourier based signatures, as well as outperforming most of the other approaches for low levels of noise. Second, while current and voltage signatures are outperformed at low levels of noise, they perform best under high noise conditions and show the smallest decrease in performance with increasing noise levels. Third, the effect of the sampling frequency on the energy disaggregation performance for time series imaging is most prominent up to 1.2 kHz, while, above 1.2 kHz, no significant improvements in terms of performance could be observed.

Real-time recommendations for energy-efficient appliance usage in households.

According to several studies, the most influencing factor in a household's energy consumption is user behavior. Changing user behavior to improve energy usage leads to efficient energy consumption, saving money for the consumer and being more friendly for the environment. In this work we propose a framework that aims at assisting households in improving their energy usage by providing real-time recommendations for efficient appliance use. The framework allows for the creation of household-specific and appliance-specific energy consumption profiles by analyzing appliance usage patterns. Based on the household profile and the actual electricity use, real-time recommendations notify users on the appliances that can be switched off in order to reduce consumption. For instance, if a consumer forgets their A/C on at a time that it is usually off (e.g., when there is no one at home), the system will detect this as an outlier and notify the consumer. In the ideal scenario, a household has a smart meter monitoring system installed, that records energy consumption at the appliance level. This is also reflected in the datasets available for evaluating such systems. However, in the general case, the household may only have one main meter reading. In this case, non-intrusive load monitoring (NILM) techniques, which monitor a house's energy consumption using only one meter, and data mining algorithms that disaggregate the consumption into appliance level, can be employed. In this paper, we propose an end-to-end solution to this problem, starting with the energy disaggregation process, and the creation of user profiles that are then fed to the pattern mining and recommendation process, that through an intuitive UI allows users to further refine their energy consumption preferences and set goals. We employ the UK-DALE (UK Domestic Appliance-Level Electricity) dataset for our experimental evaluations and the proof-of-concept implementation. The results show that the proposed framework accurately captures the energy consumption profiles of each household and thus the generated recommendations are matching the actual household energy habits and can help reduce their energy consumption by 2–17%.

Intelligent home energy management using Internet of Things platform based on NILM technique

Due to the continuous increase in the global energy demand, it is essential to find solutions to improve energy efficiency. Non-intrusive load monitoring (NILM) is one of the most prominent energy management techniques, and it allows consumers and companies to manage their energy consumption efficiently. The energy footprint of residential buildings is monitored, and the total electrical consumption is disaggregated into appliance related signals through NILM. The NILM applications are working based on the “energy awareness” concept where the consumer receives some itemized information from the application to reduce its consumption and thus improves energy efficiency. This paper presents an Internet of Things (IoT) based criterion by using NILM to transform modern buildings and homes into energy-efficient and smart ones. The Factorial Hidden Markov Model (FHMM) is used as a NILM technique to disaggregate all appliances’ total power consumption into individual appliance load consumption by giving the power as an input. The FHMM is applied on reference energy disaggregation dataset (REDD) datasets, and a comparison is made between the measured and predicted values of appliances’ power consumption. Instant visualization of live data is then created using the ThingSpeak platform, which sends alerts through Twitter social media application to the consumer to control his consumption. The consumption behavior is assessed according to the time of use to make an energy saving based on the cost of electricity.

Towards Trustworthy Energy Disaggregation: A Review of Challenges, Methods, and Perspectives for Non-Intrusive Load Monitoring.

Non-intrusive load monitoring (NILM) is the task of disaggregating the total power consumption into its individual sub-components. Over the years, signal processing and machine learning algorithms have been combined to achieve this. Many publications and extensive research works are performed on energy disaggregation or NILM for the state-of-the-art methods to reach the desired performance. The initial interest of the scientific community to formulate and describe mathematically the NILM problem using machine learning tools has now shifted into a more practical NILM. Currently, we are in the mature NILM period where there is an attempt for NILM to be applied in real-life application scenarios. Thus, the complexity of the algorithms, transferability, reliability, practicality, and, in general, trustworthiness are the main issues of interest. This review narrows the gap between the early immature NILM era and the mature one. In particular, the paper provides a comprehensive literature review of the NILM methods for residential appliances only. The paper analyzes, summarizes, and presents the outcomes of a large number of recently published scholarly articles. Furthermore, the paper discusses the highlights of these methods and introduces the research dilemmas that should be taken into consideration by researchers to apply NILM methods. Finally, we show the need for transferring the traditional disaggregation models into a practical and trustworthy framework.

Energy consumption feature adaptive non-intrusive energy disaggregation via weighted sparse coding

Toward the future smart energy consumption, non-intrusive load monitoring is a technology with great potential by realizing the energy disaggregation in a user-friendly way. However, as smart energy users, the individual energy use patterns are customized, leading to the challenges and opportunities in implementations of non-intrusive energy monitoring. In this paper, a comprehensive study focusing on handling and utilizing the customized consumption features of diverse energy users is investigated from the view of temporal characteristics. At the first stage, the temporal energy use patterns are modeled in a probabilistic way, i.e. time of use probability. Then the individual features are adaptively evolved following the unsupervised probability density evolution method, to avoid the inaccurate model descriptions for the personalized characteristics. Furthermore, the probabilistic temporal feature model is embedded in dictionary learning formulation via weighted sparse coding scheme, achieving the direct load disaggregation with temporal characteristics into consideration. By verifications on both the low voltage network simulator platform and public field measurement dataset, the proposed study is demonstrated to be effective in handling and utilizing the customized energy features. In addition to the enhanced accuracy, the proposed approach provides a feasible solution to distinguish the appliances with similar electrical signatures, which is a contribution to the smart energy consumption.

Efficient Supervised Machine Learning Network for Non-Intrusive Load Monitoring

From a single meter that measures the entire home’s electrical demand, energy disaggregation calculates appliance-by-appliance electricity consumption. Non-intrusive load monitoring (NILM), also known as energy disaggregation, tries to decompose aggregated energy consumption data and estimate each appliance’s contribution. Recently, methodologies based on Artificial Intelligence (AI) have been proposed commonly used in these models, which can be expensive to run on a server or prohibitive when the target device has limited capabilities. AI-based models are typically computationally expensive and require a lot of storage. It is not easy to reduce the computing cost and size of a neural network without sacrificing performance. This study proposed an efficient non-parametric supervised machine learning network (ENSML) architecture with a smaller size, and a quick inference time without sacrificing performance. The proposed architecture can maximise energy disaggregation performance and predict new observations based on past ones. The results showed that employing the ENSML model considerably increased the accuracy of energy prediction in 99 percent of cases.

Mixed-Integer Nonlinear Programming for State-Based Non-Intrusive Load Monitoring

Energy disaggregation, known in the literature as Non-Intrusive Load Monitoring (NILM), is the task of inferring the energy consumption of each appliance given the aggregate signal recorded by a single smart meter. In this paper, we propose a novel two-stage optimization-based approach for energy disaggregation. In the first phase, a small training set consisting of disaggregated power profiles is used to estimate the parameters and the power states by solving a mixed integer programming problem. Once the model parameters are estimated, the energy disaggregation problem is formulated as a constrained binary quadratic optimization problem. We incorporate penalty terms that exploit prior knowledge on how the disaggregated traces are generated, and appliance-specific constraints characterizing the signature of different types of appliances operating simultaneously. Our approach is compared with existing optimization-based algorithms both on a synthetic dataset and on three real-world datasets. The proposed formulation is computationally efficient, able to disambiguate loads with similar consumption patterns, and successfully reconstruct the signatures of known appliances despite the presence of unmetered devices, thus overcoming the main drawbacks of the optimization-based methods available in the literature.

Double Fourier Integral Analysis Based Convolutional Neural Network Regression for High-Frequency Energy Disaggregation

Non-Intrusive Load Monitoring aims to extract the energy consumption of individual electrical appliances through disaggregation of the total power load measured by a single smart-meter. In this article we introduce Double Fourier Integral Analysis in the Non-Intrusive Load Monitoring task in order to provide more distinct feature descriptions compared to current or voltage spectrograms. Specifically, the high-frequency aggregated current and voltage signals are transformed into two-dimensional unit cells as calculated by Double Fourier Integral Analysis and used as input to a Convolutional Neural Network for regression. The performance of the proposed methodology was evaluated in the publicly available U.K.-DALE dataset. The proposed approach improves the estimation accuracy by 7.2% when compared to the baseline energy disaggregation setup using current and voltage spectrograms.

SAMNet: Toward Latency-Free Non-Intrusive Load Monitoring via Multi-Task Deep Learning

Non-intrusive load monitoring (NILM), including state detection and energy disaggregation, aims to identify the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">on/off</i> state and energy consumption from the aggregate load of a building. By monitoring the electrical behavior of consumers, smart grid applications such as demand response and recommendation services can also be realized for saving energy bills, environmental effectiveness, assisted living, and fault diagnosis. To achieve latency-free monitoring, this paper presents a <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b> cale- and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</b> ttention-experts based <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</b> ulti-task neural network (SAMNet) with a large enough context of the view to make full use of the correlation between the tasks of the NILM. A shared expert learner is designed to learn a good summary of the features. Self-attention mechanism is creatively adopted to realize the weighted fusion of different experts. To address the problem of manually setting different threshold values for different appliances to decide the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">on/off</i> states, we designed the network automatically labeling the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">on/off</i> states. Extensive experimental results with the public datasets demonstrate the effectiveness and superiority of our proposed model.

Deep attention and generative neural networks for nonintrusive load monitoring

In recent years, Nonintrusive Load Monitoring (NILM) has been considered a crucial problem for energy monitoring and management, especially in the residential sector. In this area, deep learning has shown state-of-the-art performance due to its many tunable parameters that help its generalization power extract highly nonlinear patterns from the residential load. This paper reviews the recent discriminative deep neural networks proposed for NILM and develops attention-based deep neural architectures to improve the accuracy of current studies. In this context, we present a novel attention-based variational autoencoder and sparse coding model which uses the long short-term memory (LSTM) network and a dictionary learning module for generative disaggregation of residential loads. We show how the attention mechanisms can help deep learning better understand the correlations between NILM features and how generative pattern recognition can help capture the underlying probability densities of the features thereby improving the NILM accuracy for cutting-edge deep learning solutions. Our numerical results on the real-world Reference Energy Disaggregation Dataset (REDD) show remarkable improvements compared to the state-of-the-art using disaggregation accuracy and F-score metrics.

Data Compressive Dictionary Matching Based Optimization Approach for Non-Intrusive Load Monitoring

Non-Intrusive Load Monitoring (NILM) supports energy management by characterizing the energy usage patterns of individual appliances from aggregate demand measurements. Machine learning algorithms for NILM require bulk training data while optimization techniques involve high computation time. Addressing these issues, this paper presents an intelligent dictionary matching-based optimization approach for NILM of finite-state residential appliances. The operating states of the target appliances are determined by K-means clustering using limited training data. Employing these power states, a consumer-specific dictionary containing all the possible combinations of aggregate demand is constructed in sorted form. To reduce the computational burden, the number of aggregate demand samples is reduced by event-driven data compression. These compressed samples are then matched in the sorted dictionary to estimate the share of individual appliances in aggregate demand. Furthermore, a post-processing algorithm is proposed to eliminate the effect of sudden spikes/dips during state transitions of appliances. The proposed algorithm is evaluated using the low-frequency Reference Energy Disaggregation Dataset and its results are compared with recent approaches. The comparison results show that the proposed approach gives better results as compared to recent techniques with low computational effort. The proposed approach can support energy managers in managing demand side resources of residential microgrids.

Torch-NILM: An Effective Deep Learning Toolkit for Non-Intrusive Load Monitoring in Pytorch

Non-intrusive load monitoring is a blind source separation task that has been attracting significant interest from researchers working in the field of energy informatics. However, despite the considerable progress, there are a very limited number of tools and libraries dedicated to the problem of energy disaggregation. Herein, we report the development of a novel open-source framework named Torch-NILM in order to help researchers and engineers take advantage of the benefits of Pytorch. The aim of this research is to tackle the comparability and reproducibility issues often reported in NILM research by standardising the experimental setup, while providing solid baseline models by writing only a few lines of code. Torch-NILM offers a suite of tools particularly useful for training deep neural networks in the task of energy disaggregation. The basic features include: (i) easy-to-use APIs for running new experiments, (ii) a benchmark framework for evaluation, (iii) the implementation of popular architectures, (iv) custom data loaders for efficient training and (v) automated generation of reports.

A Novel Denoising Auto-Encoder-Based Approach for Non-Intrusive Residential Load Monitoring

Mounting concerns pertaining to energy efficiency have led to the research of load monitoring. By Non-Intrusive Load Monitoring (NILM), detailed information regarding the electric energy consumed by each appliance per day or per hour can be formed. The accuracy of the previous residential load monitoring approach relies heavily on the data acquisition frequency of the energy meters. It brings high overall cost issues, and furthermore, the differentiating algorithm becomes much more complicated. Based on this, we proposed a novel non-Intrusive residential load disaggregation method that only depends on the regular data acquisition speed of active power measurements. Additionally, this approach brings some novelties to the traditionally used denoising Auto-Encoder (dAE), i.e., the reconfiguration of the overlapping parts of the sliding windows. The median filter is used for the data processing of the overlapping window. Two datasets, i.e., the Reference Energy Disaggregation Dataset (REDD) and TraceBase, are used for test and validation. By numerical testing of the real residential data, it proves that the proposed method is superior to the traditional Factorial Hidden Markov Model (FHMM)-based approach. Furthermore, the proposed method can be used for energy data, disaggregation disregarding the brand and model of each appliance.

Low frequency residential non-intrusive load monitoring based on a hybrid feature extraction tree-learning approach

ABSTRACT Non-intrusive load monitoring (NILM), or else energy disaggregation, aims at decomposing the aggregated energy consumption data, estimating the contribution of each appliance to the total building energy consumption. The current paper introduces a supervised algorithm for the accurate estimation of both power consumption and operational state of the appliances. A hybrid feature set consisting of electrical, temporal, and statistical features is utilized, focusing on steady state information, due to the low sampling rate (1 minute). The contribution of each feature category is experimentally validated. A predictive model is built for each appliance, utilizing Light Gradient Boosting Machine (LGBM) regression algorithm, which is a tree-based technique with accelerated training time and low computational cost. The results obtained, exploiting both private and public datasets, indicate that the proposed algorithm is able to disaggregate most of the appliances with high accuracy. The average f-score across all the disaggregated appliances is calculated at 0.77 and 0.86 for the private and the public dataset, respectively. The proposed models have also been benchmarked against other top state-of-the-art approaches, achieving high performance with high rank.

Joint Energy Disaggregation of Behind-the-Meter PV and Battery Storage: A Contextually Supervised Source Separation Approach

An increasing number of residential customers have installed hybrid rooftop solar battery systems (HRSBSs). Currently, most HRSBSs are installed behind-the-meter (BTM), where only customers’ net load is measured by smart meters. This invisibility poses significant challenges to the system operation. Disaggregating BTM PV generation and battery charging/discharging profile of customers can enhance the grid-edge observability. This article proposes an energy disaggregation method to jointly separate the PV generation and battery charging/discharging power from the net load. First, a Home Smart Battery Management model is built to simulate the battery charging/discharging profile. Second, an optimal disaggregation model is established based on a contextually supervised source separation method. Furthermore, the feature vectors of PV, load, and battery are extracted as the input of the disaggregation model. Case studies on two datasets from Australia and China show that the proposed method has a promising disaggregation performance.

An innovative edge-based Internet of Energy solution for promoting energy saving in buildings

Due to the ubiquity and maturity of Artificial Intelligence (AI), it became an essential tool in the development real-time Internet of energy (IoE) solutions. Also, since cloud platforms are not being the first implementation choice due to their bandwidth and latency issues that limit data transmission capacity, Edge Computing is becoming a popular alternative in both IoE and IoT applications. To that end, a novel Edge IoE system is proposed, namely M2SP-EdgeIoE, which enables various potential IoE use scenarios for domestic energy efficiency applications. Specifically, it incorporates (i) the sensing unit used as input stage for collecting data; (ii) the energy disaggregation unit, in which non-intrusive load monitoring algorithms are implemented to identify appliances using their disaggregated power traces; (iii) the anomaly detection platform in which energy consumption abnormalities are detected using multimodal data and AI algorithms; and (iv) the recommender system unit that helps in generating tailored recommendations for improving energy consumption behavior. Promising performance has been obtained under a number of scenarios, for example, an accuracy of 98.49% and 95% have been reached for appliance identification and anomaly detection, respectively. In conclusion, the M2SP-EdgeIoE provides a blueprint for the future of Edge IoE solutions for improved global energy efficiency.

Selection of features from power theories to compose NILM datasets

The load disaggregation concept is gaining attention due to the increasing need for optimized energy utilization and detailed characterization of electricity consumption profiles, especially through Nonintrusive Load Monitoring (NILM) approaches. This occurs since knowledge about individualized consumption per appliance allows to create strategies striving for energy savings, improvement of energy efficiency, and creating energy awareness to consumers. Moreover, by using feature extraction to devise energy disaggregation, one can achieve accurate identification of electric appliances. However, even though several literature works propose distinct features to be utilized, no consensus exists in the literature about the most appropriate set of features that ensure high accuracy on load disaggregation. Thus, beyond presenting a critical analysis of some significant features often selected in the literature, this paper proposes identifying the most relevant ones considering collinearity and machine learning algorithms. The results show that high-performance metrics can be achieved with fewer features than usually adopted in the literature. Moreover, it is demonstrated that the Conservative Power Theory can offer the most representative features for appliance identification, leading to efficient power consumption disaggregation.