Non-intrusive Load Monitoring Techniques Research Articles

Privacy-Aware Smart Metering: Progress and Challenges

The next-generation energy network, the so-called smart grid (SG), promises a tremendous increase in efficiency, safety and flexibility of managing the electricity grid as compared to the legacy energy network. This is needed today more than ever, as the global energy consumption is growing at an unprecedented rate, and renewable energy sources have to be seamlessly integrated into the grid to assure a sustainable human development. Smart meters (SMs) are among the crucial enablers of the SG concept; they supply accurate high-frequency information about users' household energy consumption to a utility provider, which is essential for time of use pricing, rapid fault detection, energy theft prevention, while also providing consumers with more flexibility and control over their consumption. However, highly accurate and granular SM data also poses a threat to consumer privacy as non-intrusive load monitoring techniques enable a malicious attacker to infer many details of a user's private life. This article focuses on privacy-enhancing energy management techniques that provide accurate energy consumption information to the grid operator, without sacrificing consumer privacy. In particular, we focus on techniques that shape and modify the actual user energy consumption by means of physical resources, such as rechargeable batteries, renewable energy sources or demand shaping. A rigorous mathematical analysis of privacy is presented under various physical constraints on the available physical resources. Finally, open questions and challenges that need to be addressed to pave the way to the effective protection of users' privacy in future SGs are presented.

Interactive visualization for NILM in large buildings using non-negative matrix factorization

Non-intrusive load monitoring (NILM) techniques have recently attracted much interest, since they allow to obtain latent patterns from power demand data in buildings, revealing useful information to the expert user. Unsupervised methods are specially attractive, since they do not require labeled datasets. Particularly, non-negative matrix factorization (NMF) methods decompose a single power demand measurement over a certain time period into a set of components or “parts” that are sparse, non-negative and sum up the original measured quantity. Such components reveal hidden temporal patterns which may be difficult to interpret in complex systems such as large buildings. We suggest to integrate the knowledge of the user into the analysis in order to recognize the real events inside the electric network behind the learnt patterns. In this paper, we integrate the available domain knowledge of the user by means of a visual analytics web application in which an expert user can interact in a fluid way with the NMF outcome through visual approaches such as barcharts, heatmaps or calendars. Our approach is tested with real electric power demand data from a hospital complex, showing how the interpretation of the decomposition is improved by means of interactive data cube visualizations, in which the user can insightfully relate the NMF components to characteristic demand patterns of the hospital such as those derived from human activity, as well as to inefficient behaviors of the largest systems in the hospital.

Residential Consumer-Centric Demand-Side Management Based on Energy Disaggregation-Piloting Constrained Swarm Intelligence: Towards Edge Computing.

The emergence of smart Internet of Things (IoT) devices has highly favored the realization of smart homes in a down-stream sector of a smart grid. The underlying objective of Demand Response (DR) schemes is to actively engage customers to modify their energy consumption on domestic appliances in response to pricing signals. Domestic appliance scheduling is widely accepted as an effective mechanism to manage domestic energy consumption intelligently. Besides, to residential customers for DR implementation, maintaining a balance between energy consumption cost and users’ comfort satisfaction is a challenge. Hence, in this paper, a constrained Particle Swarm Optimization (PSO)-based residential consumer-centric load-scheduling method is proposed. The method can be further featured with edge computing. In contrast with cloud computing, edge computing—a method of optimizing cloud computing technologies by driving computing capabilities at the IoT edge of the Internet as one of the emerging trends in engineering technology—addresses bandwidth-intensive contents and latency-sensitive applications required among sensors and central data centers through data analytics at or near the source of data. A non-intrusive load-monitoring technique proposed previously is utilized to automatic determination of physical characteristics of power-intensive home appliances from users’ life patterns. The swarm intelligence, constrained PSO, is used to minimize the energy consumption cost while considering users’ comfort satisfaction for DR implementation. The residential consumer-centric load-scheduling method proposed in this paper is evaluated under real-time pricing with inclining block rates and is demonstrated in a case study. The experimentation reported in this paper shows the proposed residential consumer-centric load-scheduling method can re-shape loads by home appliances in response to DR signals. Moreover, a phenomenal reduction in peak power consumption is achieved by 13.97%.

Comparative Analysis of Load-Shaping-Based Privacy Preservation Strategies in a Smart Grid

A key enabler for the smart grid is the fine-grained monitoring of power utilization. Although such a mechanism is helpful in the optimization of the whole electricity generation, distribution, and consumption cycle, it also creates opportunities for the potential adversaries in deducing the activities and habits of the subscribers. In fact, by utilizing the standard and readily available tools of nonintrusive load monitoring (NILM) techniques on the metered electricity data, many details of customers’ personal lives can be easily discovered. Therefore, prevention of such adversarial exploitations is of utmost importance for privacy protection. One strong privacy preservation approach is the modification of the metered data through the use of on-site storage units in conjunction with renewable energy resources. In this study, we introduce a novel mathematical programming framework to model eight privacy-enhanced power-scheduling strategies inspired and elicited from the literature. We employ all the relevant techniques for the modification of the actual electricity utilization (i.e., on-site battery, renewable energy resources, and appliance load moderation). Our evaluation framework is the first in the literature, to the best of our knowledge, for a comprehensive and fair comparison of the load-shaping techniques for privacy preservation. In addition to the privacy concerns, we consider monetary cost and disutility of the users in our objective functions. Evaluation results show that privacy preservation strategies in the literature differ significantly in terms of privacy, cost, and disutility metrics.

Wavelet-Based Multiresolution Smart Meter Privacy

The availability of individual load curves per household in the smart grid end-user domain combined with nonintrusive load monitoring (NILM) to infer personal data from these load curves has led to privacy concerns. Based on insights of the interrelation of load profile resolution and accuracy of NILM techniques, we propose the use of the wavelet transform to represent load data in multiple resolutions. Each resolution is encrypted with a different key using an appropriate cipher and a hierarchical keying scheme. End-to-end security ensures access control. To meet requirements of low computational complexity in low-cost smart meters, the lifting implementation of the wavelet transform is used to generate multiple resolutions. It is shown that the multiresolution approach is compatible with other privacy-enhancing technologies, such as secure signal processing. This allows adding new degrees of freedom to these methods by introducing the dimension of multiple resolutions. The proposed approach is evaluated based on the provided level of privacy and security, computational demands, and feasibility in an economic sense.

Privacy-Protecting Energy Management Unit Through Model-Distribution Predictive Control

The roll-out of smart meters in electricity networks introduces risks for consumer privacy due to increased measurement frequency and granularity. Through various Non-Intrusive Load Monitoring techniques, consumer behavior may be inferred from their metering data. In this paper, we propose an energy management method that reduces energy cost and protects privacy through the minimization of information leakage. The method is based on a Model Predictive Controller that utilizes energy storage and local generation, and that predicts the effects of its actions on the statistics of the actual energy consumption of a consumer and that seen by the grid. Computationally, the method requires solving a Mixed-Integer Quadratic Program of manageable size whenever new meter readings are available. We simulate the controller on generated residential load profiles with different privacy costs in a two-tier time-of-use energy pricing environment. Results show that information leakage is effectively reduced at the expense of increased energy cost. The results also show that with the proposed controller the consumer load profile seen by the grid resembles a mixture between that obtained with Non-Intrusive Load Leveling and Lazy Stepping.

Data mining of smart meters for load category based disaggregation of residential power consumption

Abstract Non-Intrusive Load Monitoring (NILM) techniques have been leveraged by new instrument and machine learning algorithms to provide customers the breakdown of their energy usage. The state-of-art indicates a large amount of high-frequency measurement ( > 1 Hz) can lead to accurate disaggregation. This paper, however, proposes a disaggregation algorithm relies on hourly smart meter readings, aiming to extend the application of the low-frequency data that is accessible by both utilities and customers. The output of the disaggregation includes the breakdown of energy into load-category-based components that have different average power factors. The disaggregated data will support small-scale planning, e.g., in microgrid, by revealing the variance and patterns in different load categories. Our approach is built on a top-down structure that requires no prior knowledge or general models of individual loads. Using clustering and optimization techniques, we infer the load signatures of each category based on the active and reactive power from smart meters. The signatures are updated periodically using the most recent smart meter data. The results show that our disaggregation approach could be applied to random houses in different seasons and to single house and small neighborhood in both offline and quasi-real-time context.

A Hybrid Signature-based Iterative Disaggregation algorithm for Non-Intrusive Load Monitoring

Information on residential power consumption patterns disaggregated at the single-appliance level is an essential requirement for energy utilities and managers to design customized energy demand management strategies. Non-Intrusive Load Monitoring (NILM) techniques provide this information by decomposing the aggregated electric load measured at the household level by a single-point smart meter into the individual contribution of each end-use. Despite being defined non-intrusive, NILM methods often require an intrusive data sampling process for training purpose. This calibration intrusiveness hampers NILM methods large-scale applications. Other NILM challenges are the limited accuracy in reproducing the end-use consumption patterns and their trajectories in time, which are key to characterize consumers’ behaviors and appliances efficiency, and the poor performance when multiple appliances are simultaneously operated. In this paper we contribute a hybrid, computationally efficient, algorithm for NILM, called Hybrid Signature-based Iterative Disaggregation (HSID), based on the combination of Factorial Hidden Markov Models, which provide an initial approximation of the end-use trajectories, and Iterative Subsequence Dynamic Time Warping, which processes the end-use trajectories in order to match the typical power consumption pattern of each appliance. In order to deal with the challenges posed by intrusive training, a supervised version of the algorithm, requiring appliance-level measurements for calibration, and a semi-supervised version, retrieving appliance-level information from the aggregate smart-metered signal, are proposed. Both versions are demonstrated onto a real-world power consumption dataset comprising five different appliances potentially operated simultaneously. Results show that HSID is able to accurately disaggregate the power consumption measured from a single-point smart meter, thus providing a detailed characterization of the consumers’ behavior in terms of power consumption. Numerical results also demonstrate that HSID is robust with respect to noisy signals and scalable to dataset including a large set of appliances. Finally, the algorithm can be successfully used in non-intrusive experiments without requiring appliance-level measurements, ultimately opening up new opportunities to foster the deployment of large-scale smart metering networks, as well as the design and practical implementation of personalized demand management strategies.

Residential Appliance Identification Based on Spectral Information of Low Frequency Smart Meter Measurements

A nonintrusive load monitoring (NILM) method for residential appliances based on uncorrelated spectral components of an active power consumption signal is presented. This method utilizes the Karhunen Loeve expansion to breakdown the active power signal into subspace components (SCs) so as to construct a unique information rich appliance signature. Unlike existing NILM techniques that rely on multiple measurements at high sampling rates, this method works effectively with a single active power measurement taken at a low sampling rate. After constructing the signature data base, SC level power conditions were introduced to reduce the number of possible appliance combinations prior to applying the maximum a posteriori estimation. Then, an appliances matching algorithm was presented to identify the turned-on appliance combination in a given time window. After identifying the turned-on appliance combination, an energy estimation algorithm was introduced to disaggregate the energy contribution of each individual appliance in that combination. The proposed NILM method was validated by using two public databases: 1) tracebase; and 2) reference energy disaggregation data set. The presented results demonstrate the ability of the proposed method to accurately identify and disaggregate individual energy contributions of turned-on appliance combinations in real households.

Applicability of using time series subsequences to study office plug load appliances

Energy management in offices requires efficient methods (e.g. non-intrusive load monitoring techniques, NILM) to monitor the large number of workstations and office appliances. The key purpose of this study is to ascertain the applicability of using time series subsequence data mining to study and classify the transient operations of typical appliances in an office. The approach involves discovering hidden subsequences (i.e. feature extraction) that are characteristic of individual appliance transient states, using an extension of Symbolic Aggregate approXimation (SAX). Such characteristic features are used to create a repository of rules to help supervised classification of aggregate time series measurements. It is one of the first studies to demonstrate the potential of classifying subsequence features into individual appliances and their states within large aggregate time series data using a “Bag of Rules” approach. The results indicate that distinct, characteristic patterns represent office appliances and their states, in the form of SAX grammar rules. These patterns can then be used for NILM with promising results. This ongoing study demonstrates SAX based time series subsequence mining as a proof-of-concept; not only to discover similarities presented by appliance events but also to demonstrate their applicability to disambiguate aggregate signatures in the context of office NILM.

ELECTRICITY CONSUMPTION PATTERN DISAGGREGATION USING NON-INTRUSIVE APPLIANCE LOAD MONITORING METHOD

In practice, a standard energy meter can only capture the overall electricity consumption and estimating electricity consumption pattern of various appliances from the overall consumption pattern is complicated. Therefore, the Non-Intrusive Appliance Load Monitoring (NIALM) technique can be applied to trace electricity consumption from each appliance in a monitored building. However, the method requires a detailed, second-by-second power consumption data which is commonly not available without the use of high specification energy meter. Hence, this paper analyzes the impact of different time sampling data in estimating the energy consumption pattern of various appliances through NIALM method. This is so that consumers will have an overview of time sampling data which is required in order to apply the NIALM technique. As for the analysis, air-conditioning systems and fluorescent lamps were used in the experimental setup. One minute sample rate was the minimum time interval required by NIALM carried out in this analysis. Through the study presented in this paper, it can be established that higher time sampling led to uncertain appliance detection and low accuracy.

Fine-grained appliance usage and energy monitoring through mobile and power-line sensing

To promote energy-efficient operations in residential and office buildings, non-intrusive load monitoring (NILM) techniques have been proposed to infer the fine-grained power consumption and usage patterns of appliances from power-line measurement data. Fine-grained monitoring of everyday appliances (such as toasters and coffee makers) can not only promote energy-efficient building operations, but also provide unique insights into the context and activities of individuals. Current building-level NILM techniques are unable to identify the consumption characteristics of relatively low-load appliances, whereas smart-plug based solutions incur significant deployment and maintenance costs. In this paper, we investigate an intermediate architecture, where smart circuit breakers provide measurements of aggregate power consumption at room (or section) level granularity. We then investigate techniques to identify the usage and energy consumption of individual appliances from such measurements. We first develop a novel correlation-based approach called CBPA to identify individual appliances based on both their unique transient and steady-state power signatures. While promising, CBPA fails when the set of candidate appliances is too large. To further improve the accuracy of appliance level usage estimation, we then propose a hybrid system called AARPA, which uses mobile sensing to first infer high-level activities of daily living (ADLs), and then uses knowledge of such ADLs to effectively reduce the set of candidate appliances that potentially contribute to the aggregate readings at any point. We evaluate two variants of this algorithm, and show, using real-life data traces gathered from 10 domestic users, that our fusion of mobile and power-line sensing is very promising: it identified all devices that were used in each data trace, and it identified the usage duration and energy consumption of low-load consumer appliances with ∼87% accuracy.

A Review of Approaches for Sensing, Understanding, and Improving Occupancy-Related Energy-Use Behaviors in Commercial Buildings

Buildings currently account for 30–40 percent of total global energy consumption. In particular, commercial buildings are responsible for about 12 percent of global energy use and 21 percent of the United States’ energy use, and the energy demand of this sector continues to grow faster than other sectors. This increasing rate therefore raises a critical concern about improving the energy performance of commercial buildings. Recently, researchers have investigated ways in which understanding and improving occupants’ energy-consuming behaviors could function as a cost-effective approach to decreasing commercial buildings’ energy demands. The objective of this paper is to present a detailed, up-to-date review of various algorithms, models, and techniques employed in the pursuit of understanding and improving occupants’ energy-use behaviors in commercial buildings. Previous related studies are introduced and three main approaches are identified: (1) monitoring occupant-specific energy consumption; (2) Simulating occupant energy consumption behavior; and (3) improving occupant energy consumption behavior. The first approach employs intrusive and non-intrusive load-monitoring techniques to estimate the energy use of individual occupants. The second approach models diverse characteristics related to occupants’ energy-consuming behaviors in order to assess and predict such characteristics’ impacts on the energy performance of commercial buildings; this approach mostly utilizes agent-based modeling techniques to simulate actions and interactions between occupants and their built environment. The third approach employs occupancy-focused interventions to change occupants’ energy-use characteristics. Based on the detailed review of each approach, critical issues and current gaps in knowledge in the existing literature are discussed, and directions for future research opportunities in this field are provided.

An Advanced Home Energy Management System Facilitated by Nonintrusive Load Monitoring With Automated Multiobjective Power Scheduling

Nowadays, electricity energy demands requested from down-stream sectors in a smart grid constantly increase. One way to meet those demands is use of home energy management systems (HEMS). By effectively scheduling major household appliances in response to demand response (DR) schemes, residents can save their electricity bills. In this paper, an advanced HEMS facilitated by a nonintrusive load monitoring (NILM) technique with an automated nondominated sorting genetic algorithm-II (NSGA-II)-based multiobjective in-home power scheduling mechanism is proposed. The NILM as an electricity audit is able to nonintrusively estimate power consumed by each of monitored major household appliances at a certain period of time. Data identified by the NILM are very useful for DR implementation. For DR implementation, the NSGA-II-based multiobjective in-home power scheduling mechanism autonomously and meta-heuristically schedules monitored and enrolled major household appliances without user intervention. It is based on an analysis of the NILM with historical data with past trends. The experimental results reported in this paper reveal that the proposed advanced HEMS with the NILM assessed in a real-house environment with uncertainties is workable and feasible.

Overview of non-intrusive load monitoring and identification techniques

Load monitoring and identification is a method of determining electrical energy consumption and operation condition of individual appliances based on the analysis of composite load measured from the main power meter in a building. They can supply information such as type of load, electricity consumption detail and the running conditions of the appliances to both the consumer and the utility. The information can be used to formulate load plan strategies for optimal energy utilization. Load monitoring techniques can generally be grouped into intrusive and non-intrusive load monitoring. Intrusive load monitoring provides accurate results and would allow each individual appliance's energy consumption to be communicated to a central hub. However, this method is costly because of the number of equipment to be manufactured and installed. This has prompted the introduction of non-intrusive load monitoring system. Non-intrusive load monitoring is cost effective and convenient means of load monitoring since it requires lower equipment due to fewer components to install and smaller space requirements. This paper is concerned with the overview of different load identification and monitoring techniques for energy management focusing on non-intrusive load monitoring.

A Monte Carlo Simulation Platform for Studying Low Voltage Residential Networks

The smart grid vision has resulted in many demand side innovations such as nonintrusive load monitoring techniques, residential micro-grids, and demand response programs. Many of these techniques need a detailed residential network model for their research, evaluation, and validation. In response to such a need, this paper presents a sequential Monte Carlo (SMC) simulation platform for modeling and simulating low voltage residential networks. This platform targets the simulation of the quasi-steady-state network condition over an extended period such as 24 h. It consists of two main components. The first is a multiphase network model with power flow, harmonic, and motor starting study capabilities. The second is a load/generation behavior model that establishes the operating characteristics of various loads and generators based on time-of-use probability curves. These two components are combined together through an SMC simulation scheme. Four case studies are presented to demonstrate the applications of the proposed platform.

The Integration of a Genetic Programming-Based Feature Optimizer With Fisher Criterion and Pattern Recognition Techniques to Non-Intrusive Load Monitoring for Load Identification

Identification of electricity energy consumption on individual household appliances used in a smart house is the first important step for making the use and conservation of electricity energy more efficient. In the past, Non-Intrusive Load Monitoring (NILM) techniques, which are part of smart grid techniques realized to improve electricity energy usage efficiency, have been developed to identify individual appliances with avoiding installing many smart meters for appliances in a field. In this paper, a new NILM technique that integrates an efficient Genetic Programming (GP)-based feature optimizer with pattern recognition techniques is proposed to identify which appliance is being turned on or off. The proposed GP-based feature optimizer with Fisher criterion is used to generate a more efficient feature than original potential transient features extracted from captured transient response of household appliances through analysis of NILM. The new feature generated by GP is used by pattern recognition techniques as load identifiers for load identification. The load identifiers used and compared in this paper include k-Nearest-Neighbor Rule, Back-Propagation Artificial Neural Network, and Learning Vector Quantization. Experiments are conducted under different single-load and multiple-load operation circumstances at different actual experimental environments with small disturbances. As shown from the experimental results, the proposed is confirmed to be feasible and usable.

Intelligent Electrical Appliance Event Recognition Using Multi-Load Decomposition

The management of electricity system in home environments plays an important role in generating energy consumption and improving efficiency of energy usage. At present, nonintrusive appliance load monitoring (NIALM) techniques are the most effective approach for estimating the electrical power consumption of individual appliances. This paper presents our contribution in intelligent electrical appliance decomposition in home environment. It is a modified power appliance disaggregation technique based on power harmonic features and support vector machine (SVM). It has higher recognition accuracy and faster computational speed. The experimental results of the power decomposition technique on real date are presented with promising results.

A New Measurement Method for Power Signatures of Nonintrusive Demand Monitoring and Load Identification

Based upon the analysis of load signatures, this paper presents a nonintrusive load monitoring (NILM) technique. With a characterizing response associated with a transient energy signature, a reliable and accurate recognition result can be obtained. In this paper, artificial neural networks, in combination with turn-on transient energy analysis, are used to improve recognition accuracy and computational speed of NILM results. To minimize the distortion phenomenon in current measurements from the hysteresis of traditional current transformer (CT) iron cores, a coreless Hall CT is adopted to accurately detect nonsinusoidal waves to improve NILM accuracy. The experimental results indicate that the incorporation of turn-on transient energy algorithm into NILM significantly improve the recognition accuracy and the computational speed.

Nonintrusive appliance load monitoring based on integer programming

AbstractThis paper presents a new nonintrusive appliance load monitoring technique based on integer programming. Nonintrusive appliance load monitoring is the problem of identifying the operating conditions of electric appliances in a house by observing only the overall load current and voltage. Since the overall load current is expressed as a superposition of the currents of the operating appliances, the monitoring problem can be formulated as an integer quadratic programming problem by expressing the operating conditions as integer variables. This problem is solvable with a sufficiently small computational burden thanks to the recent development of commercial software. The proposed method does not require relearning even when a new appliance is installed in the house. Furthermore, the proposed formulation is applicable to cases in which some appliance has multiple modes, and cases in which some appliances of the same type are operating simultaneously. The usefulness of the proposed technique is verified by experimental results. © 2010 Wiley Periodicals, Inc. Electr Eng Jpn, 174(2): 18–25, 2011; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/eej.21040