Edge-Based NILM System with MDMR Filter-Based Feature Selection

Leveraging sequence-to-sequence learning for online non-intrusive load monitoring in edge device

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.

What we measure, we can improve. In accordance to this approach, Indian Institute of Science (IISc), Bangalore has developed a Micro-grid Monitoring System in the campus through the installation of Smart Meters, covering almost 250 nodes including substations, centers, departments, administration, hostels and other utilities. This will help the institute in various ways such as capacity planning, substation loading, phase imbalance correction, over-voltage monitoring, billing and so on. Smart Meters measure the power consumption at a single point in the building giving a picture of the energy consumption of the building as a whole. It is necessary to also understand the scenario of the constituent loads at the point where the smart meter is installed so that ways could be found to reduce consumption. Personalised, concise and reliable feedback providing appliance level breakdown of energy consumption in the premises is the key in implementing energy efficiency programs. Taking this into consideration the area of Non Intrusive Load Monitoring (NILM) was explored. In NILM the aggregate smart meter data is separated into constituent loads by machine learning techniques. The NILM system is trained through previous data sets and then the algorithm will disaggregate the total power into individual appliances based on its experience. A benchmark NILM algorithm called Factorial Hidden Markov Model was used for proper load disaggregation. Finally an attempt was made to develop a Smartphone app to visualize results and bring the data to the people.

The performance of non-intrusive load monitoring (NILM) system is closely related to the uniqueness and comprehensiveness of the load features extracted from the equipment. However, existing feature extraction methods for NILM are difficult to extract interpretable intuitive features representing the uniqueness of load, and lack of comprehensive attention to the features on different time scales. Therefore, this paper proposes a multi-time-scale shapelet based feature extraction framework. First, shapelet, the most unique segment of a sequence, which can distinguish it from other sequences is introduced as a feature and multi-time-scale current shapelets are proposed to extract comprehensive characteristics of electric appliances and offer intuitive interpretability. Meanwhile, a shapelet transform is constructed, so that the essence of shapelet based NILM is transformed from sequence matching to a general classification problem. Next, an ensemble bagging classifier is proposed on multi-time scales to effectively balance the classification errors on each time scale and enhance the performance of NILM system. In addition, this framework can support small sample training to facilitate rapid deployment of NILM applications at the initial practical stage. The results show that this framework can effectively focus on the uniqueness of load on different time scales, provide interpretability for NILM, and achieve good classification effects.

Non-intrusive load monitoring (NILM) considers different approaches for disaggregating energy consumption in residential, tertiary, and industrial buildings to enable smart grid services. The main feature of NILM is that it can break down the bulk electricity demand, as recorded by conventional smart meters, into the consumption of individual appliances without the need for additional meters or sensors. Furthermore, NILM can identify when an appliance is in use and estimate its real-time consumption based on its unique consumption patterns. However, NILM is based on machine learning methods and its performance is dependent on the quality of the training data for each appliance. Therefore, a common problem with NILM systems is that they may not generalize well to new environments where the appliances are unknown, which hinders their widespread adoption and more significant contributions to emerging smart grid services. The main goal of the presented research is to apply a domain adversarial neural network (DANN) approach to improve the generalization of NILM systems. The proposed semi-supervised algorithm utilizes both labeled and unlabeled data and was tested on data from publicly available REDD and UK-DALE datasets. The results show a improvement in generalization performance on highly uncorrelated data, indicating the potential for real-world applications.

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.

Over more than 30 years development of Non-intrusive Load Monitoring (NILM), many technologies were developed from sampling frequency 1 Hz to hundreds kHz to extract from simple information such as difference power dP, dQ; shape of transient signatures to complex information such as harmonics or electromagnetic interference (EMI). There are now many real NILM systems in residential applications but there is lack of researches to apply NILM to commercial and industrial application. This site uses so much energy in business and production so that analyzing power consumption to optimize their operation is very important to produce competitive products on the market. Unfortunately, it is very difficult to recognize commercial and industrial machine that are composed of many electric elements. This paper provides a new NILM approach to monitor commercial and industrial machines based on basic electrical appliances inside architecture of machine. All power differences dP, dQ, dS are used to analyze and classify basic electrical appliances. Adaptive filter CUSUM is used to improve removing noise in preprocessing phase of the NILM system. Finally, Field Program Gate Array (FPGA) is discussed to implement our NILM system.

This paper brings the application of non-intrusive load monitoring (NILM) into demand response (DR). NILM is usually applied to identify the major loads in buildings, which is very promising in meeting the load monitoring requirements of demand response. Unlike the traditional approach of NILM in energy auditing, a new NILM system for DR is established based on a comprehensive analysis on the requirement of demand response. The new system is designed from both hardware and software aspects with a more practical load space and a more explicit measuring criteria. The ultimate goal of this paper is to pave the road for the future researchers to work in NILM for demand response.

Practical application of deep learning based non-intrusive load monitoring (NILM) system requires the deep neural network model to generalize on new unseen data. Existing NILM solutions are not suitable for real-world application due to their poor disaggregation accuracy on new unseen data. In order to address this problem, this paper presents a NILM algorithm that uses data augmentation to generate synthetic data for training deep convolutional neural network models for each target appliance. Proposed data augmentation technique works by combining on and off-durations of a target appliance from various datasets, and forms a unified and comprehensive synthetic aggregate and sub-meter profiles. Apart from proposed algorithm, this paper also proposes an evaluation approach that relies on total predicted energy and ground-truth energy of an appliance to provide detailed insights about total overlapping energy, missing energy and extra energy predicted by the algorithm. Comparison results on our proposed evaluation approach showed that proposed disaggregation algorithm was able to predict energy that was 60% overlapping with ground truth energy and 36% energy was extra. Overall results showed that overlapping energy was 2.5 times more, and extra-predicted energy was 60% less than state-of-the-art algorithms in unseen test cases.

BackgroundRecently, successful applications of the discrete wavelet transform have been reported in brain interface (BI) systems with one or two EEG channels. For a multi-channel BI system, however, the high dimensionality of the generated wavelet features space poses a challenging problem.MethodsIn this paper, a feature selection method that effectively reduces the dimensionality of the feature space of a multi-channel, self-paced BI system is proposed. The proposed method uses a two-stage feature selection scheme to select the most suitable movement-related potential features from the feature space. The first stage employs mutual information to filter out the least discriminant features, resulting in a reduced feature space. Then a genetic algorithm is applied to the reduced feature space to further reduce its dimensionality and select the best set of features.ResultsAn offline analysis of the EEG signals (18 bipolar EEG channels) of four able-bodied subjects showed that the proposed method acquires low false positive rates at a reasonably high true positive rate. The results also show that features selected from different channels varied considerably from one subject to another.ConclusionThe proposed hybrid method effectively reduces the high dimensionality of the feature space. The variability in features among subjects indicates that a user-customized BI system needs to be developed for individual users.

The rapid development of technology in the electrical energy sector within the last 20 years has led to growing electric power needs through the increased number of electrical appliances and automation of tasks. In parallel the global climate protection goals, energy conservation and efficient energy management arise interest for reduction of the overall energy consumption. These requirements have led to the recent adoption of smart-meters and smart-grids, as well as to the rise of Load Monitoring (LM) using energy disaggregation, also referred to as Non-Intrusive Load Monitoring (NILM), which enables appliance-specific energy monitoring by only observing the aggregated energy consumption of a household. The real-time information on appliance level can be used to get deeper insights in the origin of energy consumption and to make optimization, strategic load scheduling and demand management feasible. The three main contributions are as follows: First, a generalized up-to-date review of NILM approaches including a high-level taxonomy of NILM methodologies is provided. Second, previously published results are grouped based on the experimental setup which allows direct comparison. Third, the article is accompanied by a software implementation of the described NILM approaches.

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.

Recently, a growing interest has been dedicated towards developing and implementing low-cost energy efficiency solutions in buildings. Accordingly, non-intrusive load monitoring has been investigated in various academic and industrial projects for capturing device-specific consumption footprints without any additional hardware installation. However, its performance should be improved further to enable an accurate appliance identification from the aggregated load. This paper presents an efficient non-intrusive load monitoring framework that consists of the following main components: (i) a novel fusion of multiple time-domain features is proposed to extract appliance fingerprints; (ii) a dimensionality reduction scheme is introduced to be applied to the fused time-domain features, which relies on fuzzy-neighbors preserving analysis based QR-decomposition. The latter can not only reduce feature dimensionality, but it can also effectively decrease the intra-class distances and increase the extra-class distances of appliance features; and (iii) a powerful decision bagging tree classifier is implemented to accurately classify electrical devices using the reduced features. Empirical evaluations performed on three real datasets, namely ACS-F2, REDD and WHITED collected at different sampling rates have shown a promising performance, according to the accuracy and F1 score achieved using the proposed non-intrusive load monitoring system. Reported accuracy and F1 score have reached both 100% for the WHITED dataset, 99.79% and 99.76% for the REDD dataset, and up to 99.41% and 98.93% for the ACS-f2 dataset, respectively. The outstanding performance achieved using the proposed solution determines its effectiveness in collecting individual-appliance consumption data and in promoting energy saving behaviors.

Overview of non-intrusive load monitoring and identification techniques