Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Concept of aggregate load profile and NILM. The task of NILM is to disaggregate the energy of each device and then identify it as shown in the colored plots.
Source publication
With widely deployed smart meters, non-intrusive energy measurements have become feasible, which may benefit people by furnishing a better understanding of appliance-level energy consumption. This work is a step forward in using graph signal processing for non-intrusive load monitoring (NILM) by proposing two novel techniques: the spectral cluster...
Contexts in source publication
Context 1
... energy profile of each device is of extreme importance in the overall operation of smart grids with renewable energy resources. NILM plays a vital role in efficiently extracting energy consumption data down to the appliance level, as demonstrated in Figure 1, helping demand prediction. This energydemand information may be used to manage and conserve energy at the consumer and grid levels. ...
Context 2
... this process for each data sample leads to a complete load identification or disaggregation at the individual device level. Hart [8] initially coined the concept of disaggregating the total energy and demonstrated that each appliance or device could be recognized using an appropriate LS feature, as shown in Figure 1. He also defined the following three types of device models: Machine learning approaches can be divided into supervised and unsupervised methods. ...
Context 3
... SC-EV method outperforms the SC-M method generally, except in one case, i.e., Device 4, in which both perform equally. Figure 10 represents this comparison for the REFIT dataset. In this analysis, it is also evident that the SC-EV method is performing well. ...
Context 4
... the SC-EV algorithm performs better in most cases. Figure 10 shows a comparison of mean accuracy and f-measure scores, illustrating that event threshold 'k' affects the detection accuracies. Setting k = 0.1 provides better performance as compared to k = 0.01. ...
Context 5
... research work by Zhao et al. [56] provides a detailed comparison of different NILM techniques' disaggregation accuracies. The results (accuracies) provided by Zhao et al. have been compared with the current study results in Figures 11 and 12 for the REFIT dataset. The benchmark studies are factorial hidden Markov model (FHMM), discriminative disaggregation sparse coding (DDSC), graph signal processing (GSP), unsupervised optimization (OPT), and convolutional neural network (CNN). ...
Context 6
... of mean f-measure between proposed and state-of-the-art for refit data. A comparison of current approaches with two studies employing different approaches of spectral clustering technique may be of interest here, shown in Figure 13. In [50], the EMBED dataset was used to test three different clustering approaches. ...
Citations
... In intrusive load monitoring (ILM) [8,9], as shown in Figure 1a, each electric load is monitored by a separate sensor, and the information acquired from all sensors can be centrally processed at the cloud end. And in non-intrusive load monitoring (NILM) [6,7,10], as shown in Figure 1b, only one monitor is required for each family or cell. It captures electric signals (such as voltage, current, and so on) at the commercial power input and transmits them to the cloud server in which the workload information of all loads is interpreted with algorithms. ...
State-of-the-art smart cities have been calling for economic but efficient energy management over a large-scale network, especially for the electric power system. It is a critical issue to monitor, analyze, and control electric loads of all users in the system. In this study, a non-intrusive load monitoring method was designed for smart power management using computer vision techniques popular in artificial intelligence. First of all, one-dimensional current signals are mapped onto two-dimensional color feature images using signal transforms (including the wavelet transform and discrete Fourier transform) and Gramian Angular Field (GAF) methods. Second, a deep neural network with multi-scale feature extraction and attention mechanism is proposed to recognize all electrical loads from the color feature images. Third, a cloud-based approach was designed for the non-intrusive monitoring of all users, thereby saving energy costs during power system control. Experimental results on both public and private datasets demonstrate that the method achieves superior performances compared to its peers, and thus supports efficient energy management over a large-scale Internet of Things network.
... In Invasive Load Monitoring (ILM), each electric load is monitored by a separate sensor and the information acquired from all sensors can be centrally processed by cloud-end. While in Non-Invasive Load Monitoring (NILM) [6]- [8], only one monitor is required for each family or cell. It captures electric signals (such as voltage, current, and so on) at the commercial power input and transimits them to cloud server in which workload information of all loads are interpreted with algorithms. ...
The state-of-the-art smart city has been calling for an economic but efficient energy management over large-scale network, especially for the electric power system. It is a critical issue to monitor, analyze and control electric loads of all users in system. In this paper, we employ the popular computer vision techniques of AI to design a non-invasive load monitoring method for smart electric energy management. First of all, we utilize both signal transforms (including wavelet transform and discrete Fourier transform) and Gramian Angular Field (GAF) methods to map one-dimensional current signals onto two-dimensional color feature images. Second, we propose to recognize all electric loads from color feature images using a U-shape deep neural network with multi-scale feature extraction and attention mechanism. Third, we design our method as a cloud-based, non-invasive monitoring of all users, thereby saving energy cost during electric power system control. Experimental results on both public and our private datasets have demonstrated our method achieves superior performances than its peers, and thus supports efficient energy management over large-scale Internet of Things (IoT).
... Ghaffar et al. analyzed frequency spectrum of power consumption data to detect individual appliances using spectral clustering [27]. The technique is evaluated on real-world datasets and is found to be effective in identifying appliance-level usage accurately. ...
Non-intrusive load monitoring (NILM) has become an emerging technology in the energy sector for its effectiveness in the energy disaggregation of individual loads from the measured aggregated energy in main power supply of building. NILM has also evolved gradually over the past few decades, due to the significant advancements in artificial intelligence (AI), embedded/edge devices, and internet of things (IoT). From the review of literature, we observed that most of the NILM systems were only capable of monitoring different loads and it fails to detect and disaggregate the energy consumption of similar loads effectively. Further, most of works in the literature were focused on improving the performance of energy disaggregation of different loads in residential buildings and very limited works have been carried out for the similar loads in NILM system. Therefore, there is a necessity to study and evaluate the state of the art NILM algorithms for similar loads in real case scenarios for effective implementation in the commercial and industrial buildings. In this paper, we present a case study of the developed DeepEdge-NILM device which has been installed in a commercial building (office environment), where multiple similar and identical air conditioners (AC's) are used in the monitoring environment. A deep learning framework, Long Short-Term Memory (LSTM) has been implemented on the new set of features which comprises of electrical features and intrinsic features derived from the basic electric features using geometric mean for capturing the signature of similar loads effectively. From our case study, we observed that the performance of the deployed NILM system outperforms the baseline systems that have been developed using basic electrical features significantly. Finally, the limitations and future scope of the NILM edge device in the commercial buildings are also discussed.
... These machine learning techniques are divided in supervised and unsupervised techniques [10]. In a previous study [11], authors proposed two unsupervised techniques for NILM applications; Spectral Cluster-Mean (SC-M) and Spectral Cluster-Eigen Vector (SC-EV). The aggregate active power of the whole house is denoted by p(ti), measured at time ti. ...
... A graph = ( , ) is defined with vertices at each data sample and having connection and weight information in matrix [13]. Spectral Cluster-Mean (SC-M) method clusters data on the basis of the mean value of device power signature [11]. A linear similarity graph is defined with consecutive nodes connected and others unconnected with weights defined according to the adjacency matrix; ...
... Data in each cluster is replaced with the mean of that cluster for better device identification and error reduction. In Spectral Cluster -Eigen Vector (SC-EV) method [11], a resultant eigen vector is calculated after adding all the eigen vectors. A meaningful change in these resultant attributes to an event. ...
Widespread inculcation of smart meter data in modern grid is motivating stakeholders to utilize it for demand response management and achieving energy sustainability goals. One of the methods being used in regard is Non-Intrusive Load Monitoring (NILM), for disaggregating individual devices from a combined load signature. This study combines two spectral clustering strategies using voting based spectral clustering technique in such a way as to achieve the benefits of both parent strategies. The voters in the consensus are taken to be the accuracies achieved using Spectral Cluster-Mean (SC-M) and Spectral Cluster-Eigen Vector (SC-EV) algorithms with different window sizes to achieve diversity. Currently, Spectral Clustering for NILM has been used by few research works and so far, no one technique has achieved higher accuracy in detecting various kinds of devices. The proposed strategy was evaluated on real world data set (REFIT). The results have shown enhanced overall performance by up to 6%. An in-depth analysis of various tuning parameters of SC-M and SC-EV is also presented. These novel contributions increase the feasibility of spectral clustering and voting based consensus clustering for NILM and may open further avenues of research in this direction.
... However, in other research works, voltage distortion [9] and current signal [16], [17] are used as the primary inputs. Studies have considered high-power appliances [17] and given very little attention to low-power appliances [18], and therefore, existing event detection algorithms cannot be directly applied in NILM-based solutions developed for residential purposes. Thus, there is a need to develop novel event detection methodology for residential NILM solutions, which we intend to fulfill through our work proposed in this paper. ...
... For example, Roy et al. (2006) compare the accuracy 780 results of Nash H-learning and simple H-learning game algorithms for overlapping location estimation. A similar approach is used by Barbato et al. (2009) Ghaffar et al. (2022) REFIT Determining the energy consumption of individual appliances from the building's overall energy profile Disaggregation accuracy and F-measure Table 11: Utilization of energy consumption datasets in various studies the performance of the inhabitant behavior prediction algorithm. The percentage of the correctly predicted profiles is used as an evaluation measure. ...
Smart homes are equipped with easy-to-interact interfaces, providing a more comfortable living environment and less energy consumption. There are currently satisfactory approaches proposed to deliver adequate comfort and ease to smart home inhabitants through infrared sensors, motion sensors, and other similar technologies. However, the goal of reducing energy consumption is always a significant concern for smart home stakeholders. A detailed discussion about energy management techniques might open new leads for advanced research and even introduce more ways to improve existing methods since a summary of effective energy conservation techniques are helpful to get a quick overview of the state-of-the-art techniques. This review study aims to provide an overview of previously proposed techniques for energy conservation and energy-saving recommendations. We identify various critical features in energy conservation techniques, i.e., user energy profiling, appliance energy profiling, and off-peak load scheduling to perform a comparative analysis among different techniques. Then, we explain various energy conservation techniques, describe common and rare evaluation metrics, identify several techniques for realizing synthetic smart home energy consumption datasets, and provide a statistical analysis of the existing literature. The survey finally points out possible research directions which might lead to new inquiries in energy conservation research.
... It has been successfully proposed by Ghaffar et al. In [8], it is shown that the robust eigenvalue evaluation algorithm allows the indirect determination of the weight of each load in the measured energy. ...
... Problem Scale Machine Learning Algorithmic Solution [1] AMPds [12], UK-DALE [13], REDD [14], Refi [15] Small X [2] COMBED [16] Large X [3] UK-DALE [13], REDD [14] Medium X [4] AMPds [12] Medium X [5] REDD [14] Small X [6] UK-DALE [13], REDD [14], Refi [15] Small X [7] UK-DALE [13], REDD [14], Refi [15] Small X [8] Refi [15] Small X [9] UK-DALE [13] Small X [10] GeLaP [17] Small X Indeed, in the last years, the problem of NILM system has been approached by using methods and algorithms covering several advanced systems and control theory results of the last 30 years. This shows how the research in this area covers a wide spectrum from an algorithmic point of view. ...
Non-Intrusive load monitoring (NILM) represents an emerging strategy based on the application of sevaral multidisciplinary topics [...]
Non-intrusive load monitoring (NILM) is a promising technique for energy consumption monitoring that can recognize load states and appliance types without relying on excessive sensing meters. With the development of the Internet of Things in intelligent buildings, the NILM technique will have broad application prospects. According to the different characteristics of load electrical signals, this work constructs 2D load signatures, including building the weighted voltage–current (WVI ) trajectory image, Markov Transition Field (MTF) image, and current spectral sequence-based GAF (I-GAF) image. Furthermore, a deep learning model named Residual Convolutional Neural Network with Energy-normalization and Squeeze-and-excitation blocks (EN-SE-RECNN) is proposed to mine information on the constructed load signatures and realize the appliance identification task. The accuracy of the proposed method on PLAID, WHITED, and HRAD datasets reached 97.43%, 95.99%, and 98.14%, respectively. And it shows that the proposed method significantly improves the recognition performance compared to existing methods.
