Power Load Event Detection and Classification Based on Edge Symbol Analysis and Support Vector Machine

Nowadays, the load monitoring system is an important element in smart buildings to reduce energy consumption. Nonintrusive load monitoring (NILM) is utilized to determine the power consumption of each appliance in smart homes. The main problem of NILM is how to separate each appliance's power from the signal of aggregated consumption. In this regard, this paper presents a combination between particle swarm optimization (PSO) and artificial neural networks (ANNs) to identify electrical appliances for demand‐side management. ANN is applied in NILM as a load identification task, and PSO is used to train the ANN algorithm. This combination enhances the NILM technique's accuracy, which is further verified by experiments on different datasets like Reference Energy Disaggregation Dataset, UK Domestic Appliance‐Level ElectricityUK‐DALE, and Indian data for Ambient Water and electricity Sensing. The high accuracy of the proposed algorithm is verified by comparisons with state of the art methods. Compared with other approaches, the total mean absolute error has decreased from 39.3566 to 18.607. Also, the normalized root mean square error (NRMSE) method has been used to compare the measured and predicted results. The NRMSE is in the range of 1.719%–16.514%, which means perfect consistency. This demonstrates the effectiveness of the proposed approach for home energy management. Furthermore, customer behavior has been studied, considering energy costs during day hours.

Non-Intrusive Load Monitoring (NILM) aids in estimating the individual energy consumed by different appliances using aggregate signals measured at point of common connection. This paper explores various unexplored aspects concerning load classification in NILM. Rich feature sets are extracted from load signatures using auto-correlogram, Variational Mode Decomposition (VMD), and Wavelet Packet Tree (WPT) decomposition. Typically, previous works employ a single Feature Selection (FS) technique to earmark the relevant features for improved performance of NILM. However, each FS technique behaves uniquely, and the effects of using different FS techniques or their combinations have yet to be explored for NILM. Hence, Combinatorial Fusion Analysis (CFA), which surpasses the performance of a single FS technique by considering an optimal combination of multiple FS techniques, is used in this paper. The final selected features are fused and provided to a classifier. Rather than manually tuning or performing an exhaustive search for setting the classifier’s hyper-parameters, as prevalent in previous works, the present work utilizes Bayesian Optimization (BO) comprising surrogate and acquisition functions. The proposed work’s efficacy is validated on publicly available data-sets in a host computer and an embedded device, namely, R-Pi, via comparison with previous works.

Non-intrusive load monitoring (NILM) is to estimate individual appliance’s power consumption from aggregated smart meter data, which is useful for optimized energy management and provisioning of customized services. While deep learning (DL) has achieved state-of-the-art NILM performance, it is still constrained by the dependency on large amounts of data and intensive computations on training. In this paper, we propose a pre-training approach to address the generalization of DL models for NILM. We develop a meta-learning based approach and an ensemble learning based approach, which pre-train a base model and then fine-tune it with few-short learning when applied to an unknown dataset. The models are validated with two real-world datasets and shown to achieve a superior transferability performance compared with traditional DL and transfer learning methods.

Millions of smart meters have been deployed worldwide, collecting the total power consumed by individual households. Based on these data, electricity suppliers offer their clients energy monitoring solutions to provide feedback on the consumption of their individual appliances. Historically, such estimates have relied on statistical methods that use coarse-grained total monthly consumption and static customer data, such as appliance ownership. Non-Intrusive Load Monitoring (NILM) is the problem of disaggregating a household's collected total power consumption to retrieve the consumed power for individual appliances. Current state-of-the-art (SotA) solutions for NILM are based on deep-learning (DL) and operate on subsequences of an entire household consumption reading. However, the non-stationary nature of real-world smart meter data leads to a drift in the data distribution within each segmented window, which significantly affects model performance. This paper introduces NILMFormer, a Transformer-based architecture that incorporates a new subsequence stationarization/de-stationarization scheme to mitigate the distribution drift and that uses a novel positional encoding that relies only on the subsequence's timestamp information. Experiments with 4 real-world datasets show that NILMFormer significantly outperforms the SotA approaches. Our solution has been deployed as the backbone algorithm for EDF's (Electricité De France) consumption monitoring service, delivering detailed insights to millions of customers about their individual appliances' power consumption.

This paper presents a complete real-time implementation of a Non-Intrusive Appliance Load Monitoring (NIALM) system that, is robust under residential voltage level fluctuations. Existing NIALM techniques rely on multiple measurements taken at high sampling rates, but, only have been proven in simulated environments without even considering the effect of residential voltage level fluctuations — which is a severe problem in power systems of most developing countries like Sri Lanka. In contrast, through the NIALM method proposed in this paper, accurate load monitoring results were obtained in realtime using only smart meter measurements taken at a low sampling rate from a real appliance setup under residential voltage level fluctuations. In the proposed NIALM method, initially in the learning phase, a properly constructed MATLABTM Graphical User Interface (GUI) was used to acquire signals of each appliance active power consumption and voltage levels. Then, obtained active power measurements were separated into subspace components (SCs) via the Karhunen Loeve' Expansion (KLE) while also taking the voltage variations into account. Using those SCs, a unique information rich appliance level signature database was constructed and it was then used to obtain the signatures for all possible device combinations. Next, a separate GUI was designed to identify the turned ON appliance combination in the current time window using the pre-constructed signature databases, after reading the total residential active power consumption and the supply voltage. To validate the proposed real-time NIALM implementation, data from a laboratory arrangement consisting of ten household appliances was used. From the results, it was found that the proposed method is capable of accurately identifying the turned on appliances even under severe residential supply voltage level fluctuations.

In recent years the development and deployment of commercial Smart Meters in most households in developed countries have spread the appearance of certain applications and methods, mainly related to the fields of Smart Grids and Internet of Things, where Non-Intrusive Load Monitoring (NILM) is one of the most well-known. It takes advantage of the capability of Smart Meters to acquire the electrical signals of a household or building in real time, in order to implement a set of techniques oriented to disaggregate the power consumption, according to the different electrical loads plugged in the facility. Previous works are often based on a cloud-computing approach, where samples are transferred straightforwardly from the local meter to the cloud for further analysis. This implies that the sampling rates are low in order to keep the required bandwidth reduced, thus constraining the final performance achieved in the load identification. This work presents the design of a System-on-Chip (SoC) architecture based on a Field-Programmable Gate Array (FPGA) device that can be installed locally at the input of the electrical installation from a house or building. It is able to manage data rates at high sampling frequencies and to implement in real time those algorithms proposed for the electrical signal processing and load classification. Experimental results have preliminary validated the proposed architecture.

Smart meters are required to identify home appliances to fulfill various tasks in the smart grid environment. On the other hand, techniques using non-intrusive appliance load monitoring (NIALM) are yet to result in meaningful practical implementation. Our experimental setup, on the recommended specifications of the internal electrical wiring in Indian residences, used common household appliances' load signatures of active and reactive powers, harmonic components and their magnitudes. We have introduced a new approach of ‘multi point sensing’ and ‘group control’ rather than the ‘single point sensing’ and ‘individual control’, used so far in NIALM techniques. The disaggregation system based on Central Public Works Department of India (CPWD). One feature i.e. amplitude of first 8 odd harmonics of current signature of home appliances were selected for the classification. Further principle component analysis (PCA) is used. A comparison between these classification algorithms has been done and it is revealed that artificial neural network classifier and Bayes classifier provides 99.18% and 98.08% accuracy respectively for the experimental data.

Non-Intrusive Appliance Load Monitoring (NIALM) is a process for deducting what appliances are being used in a household by observing the total energy consumption over time. Such process makes it possible to provide energy management services to a large number of users without installation of per-appliance meters. This paper analyzes the performance of NIALM when used to provide real-time services. In addition, the paper studies how the performance of NIALM could be improved by dynamically selecting the disaggregation model on the basis of user feedback about the correctness of the disaggregation.

In this paper, a new method of non intrusive load monitoring (NILM) feature extraction is proposed.The method is based on the analysis and identification of the load transient state and steady state characteristics of the load in the power supply and power outages using the back propagation neural network (BP).The current signal through current sensor is detected in the main switchboard NILM, compared with detecting active power, reactive power and harmonic components of power signals and load the instantaneous change of the state traditional NILM, this new method is more convenient and reduces the amount of computation.The new NILM method integrates artificial intelligence identification technology and load current acquisition technolog.

In this paper, we present our preliminary results towards a novel framework for non intrusive monitoring of home appliances using wireless signals such as those of Wi-Fi. The framework relies on the fact that the state — ON or OFF — of some home appliances causes detectable changes in the characteristics of the wireless channel. For proof of concept demonstrations, we select a number of home appliances whose operation is either characterized by moving parts or by generation of radio frequency interference (RFI) – properties which we show can be detected by analysing reflected radio frequency energy in the wireless channel. Using software-defined radios with a Wi-Fi-like physical layer, we develop a prototype system for the detection of the following home appliances: (a) Ceiling Fan, (b) Pedestal Fan, (c) Washing Machine, and (d) Microwave Oven. We identify relevant features on the measured Channel State Information (CSI) that depict the environmental changes due to state of different home appliances. These features are used by a subsequent machine learning stage to classify the state and type of the home appliance. By achieving an average validation accuracy of 90.11% using a Support Vector Machine (SVM) classifier, our results indicate that the proposed framework has the potential for a cheap, easy to install, and an ubiquitous alternative to conventional non-intrusive load monitoring (NILM).

Knowing the power consumption of individual household appliances is useful for end-user as well as utilities. There are two ways for appliance load monitoring (ALM), namely intrusive load monitoring (ILM) and non-intrusive load monitoring (NILM). This paper focuses on the NILM approach, and discusses a simple yet effective method to improve its accuracy by constructing a better knowledge-base. The proposed methodology is initially verified with the simulation using the Reference Energy Disaggregation Data (REDD) dataset, and later tested on a lab-scale hardware setup as well. Test results reveal that careful construction of knowledge-base can increase the performance of NILM algorithms. MATLAB is used as the programming platform.

Although a diversity of approaches towards Non-Intrusive Load Monitoring (NILM) are now available, complementary studies must be carried out in order to improve load modeling and consequently increase load recognition accuracy. This paper presents a study on active power appliances' modeling when only low-frequency granularities are considered. The approach analyzes the distribution of power changes in finite-state loads using an effective feature transform to stabilize power variance. Subtractive clustering method is utilized for detection of power transition recurrences. It allows identifying most likely power changes presented in individual load profiles using a prior knowledge of power uncertainties. The principal aim of this paper is to create a probabilistic device-specific model of household resistive loads, which can be used in event-based load recognition. The results using real data prove the efficacy of the proposed method.

This paper presents a technical system, which uses the non-intrusive appliance load monitoring (NIALM) method. The solution enables the end user to observe the electricity consumption of the individual appliances. By dividing electricity consumption to individual appliances, it improves the users’ understanding of the overall energy use of the building. This way the owner of the building is able to intervene better with the energy consumption of the building. Observation of the electricity appliances is performed in a web application in a user interface calendar view.

Energy disaggregation algorithms disintegrate aggregate demand into appliance-level demands. Among various energy disaggregation approaches, non-intrusive load monitoring (NILM) algorithms requiring a single sensor have gained much attention in recent years. Various machine learning and optimization-based NILM approaches are available in the literature, but bulk training data and high computational time are their respective drawbacks. Considering these drawbacks, we devised an event matching energy disaggregation algorithm (EMEDA) for NILM of multistate household appliances using smart meter data. Having limited training data, K-means clustering was employed to estimate appliance power states. These power states were accumulated to generate an event database (EVD) containing all combinations of appliance operations in their various states. Prior to matching, the test samples of aggregate demand events were decreased by event-driven data compression for computational effectiveness. The compressed test events were matched in the sorted EVD to assess the contribution of each appliance in the aggregate demand. To counter the effects of transient spikes and/or dips that occurred during the state transition of appliances, a post-processing algorithm was also developed. The proposed approach was validated using the low-rate data of the Reference Energy Disaggregation Dataset (REDD). With better energy disaggregation performance, the proposed EMEDA exhibited reductions of 97.5 and 61.7% in computational time compared with the recent smart event-based optimization and optimization-based load disaggregation approaches, respectively.

Sequence to point learning based on bidirectional dilated residual network for non-intrusive load monitoring