Load Signatures Research Articles

Smart Non-Intrusive Appliance Load-Monitoring System Based on Phase Diagram Analysis

Much of today’s power grid was designed and built using technologies and organizational principles developed decades ago. The lack of energy resources and classic power networks are the main causes of the development of the smart grid to efficiently use energy resources, with stable and safe operation. In such a network, one of the fundamental priorities is provided by non-intrusive appliance load monitoring (NIALM) in order to analyze, recognize and determine the electricity consumption of each consumer. In this paper, we propose a new smart system approach for the characterization of the appliance load signature based on a data-driven method, namely the phase diagram. Our aim is to use the non-intrusive load monitoring of appliances in order to recognize different types of consumers that can exist within a smart building.

Energy Consumption Management of Residential Appliances Based on Load Signatures Decomposition

Nowadays, energy consumption management techniques in the residential side have gained significant importance due to their considerable influence on the control of power flow in distribution networks and especially the possibility of managing a huge part of domestic electrical demand during peak-load hours. Since the customer’s data are recorded in an aggregated form, therefore, in order to apply control approaches, it is necessary to use load pattern evaluation techniques (load signature). These methods capable to decomposition effective features that help control approaches to implement with more accuracy. In this article, features of residential loads have been extracted by using the signature of the aggregated consumer’s demand. Then these features have been evaluated by methods such as logistic regression, k-nearest neighborhood, and decision tree. By assessing the results, it was determined that among the extracted features, the first two features (consumed power and injected harmonics) covered more than 89% of the variance of the entire set, and with the help of using the principal component analysis method, it was determined that by reducing the number of features to 2, a considerable amount of computation is reduced and only about 4% of the accuracy is reduced. Also, the convolutional neural network approach was used to estimate the type of load, and by identifying controllable loads and applying remote home energy management methods, it was found that by increasing participation up to 80%, more than 41% of peak-load consumption could be shifted to off-peak hours.

TIMP-1 is an activator of MHC-I expression in myeloid dendritic cells with implications for tumor immunogenicity

Immune checkpoint therapies (ICT) for advanced solid tumors mark a new milestone in cancer therapy. Yet their efficacy is often limited by poor immunogenicity, attributed to inadequate priming and generation of antitumor T cells by dendritic cells (DCs). Identifying biomarkers to enhance DC functions in such tumors is thus crucial. Tissue Inhibitor of Metalloproteinases-1 (TIMP-1), recognized for its influence on immune cells, has an underexplored relationship with DCs. Our research reveals a correlation between high TIMP1 levels in metastatic melanoma and increased CD8 + T cell infiltration and survival. Network studies indicate a functional connection with HLA genes. Spatial transcriptomic analysis of a national melanoma cohort revealed that TIMP1 expression in immune compartments associates with an HLA-A/MHC-I peptide loading signature in lymph nodes. Primary human and bone-marrow-derived DCs secrete TIMP-1, which notably increases MHC-I expression in classical type 1 dendritic cells (cDC1), especially under melanoma antigen exposure. TIMP-1 affects the immunoproteasome/TAP complex, as seen by upregulated PSMB8 and TAP-1 levels of myeloid DCs. This study uncovers the role of TIMP-1 in DC-mediated immunogenicity with insights into CD8 + T cell activation, providing a foundation for mechanistic exploration and highlighting its potential as a new target for combinatorial immunotherapy to enhance ICT effectiveness.

Appliance Identification via Combinatorial Fusion Analysis-Assisted Bayesian-Optimized Classifier

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 by Load Trajectory and Multi-Feature Based on DCNN

This study proposes a non-intrusive load monitoring (NILM) framework based on a deep convolutional neural network (DCNN) to profile each household appliance on/off status and the residential power consumption. It uses only load trajectory, which can overcome the limitations of existing voltage-current (V-I) trajectory NILM techniques. The DCNN architecture with a load trajectory as the input enables the NILM to directly analyze the electricity consumption at the appliance-level. Meanwhile, the temporal feature transferring procedure improves load monitoring performance and extends its application range include monitoring appliances based on multiple and combined characteristics. Furthermore, the power variation augmentation technique enhances the load signature uniqueness. The fusion of temporal and power variation features provides rich identification information for NILM and improves the accuracy of appliance identification. Experimental results demonstrate that the proposed NILM framework is effective and superior for enhancing demand side management and energy efficiency.

A Learnable Image-Based Load Signature Construction Approach in NILM for Appliances Identification

One of the tasks of Non-Intrusive Load Monitoring (NILM) is load identification, which aims to extract and classify altered electrical signals after switching events are detected. In this subtask, representative and distinguishable load signatures are es-sential. At present, the literature approach to characterize electri-cal appliances is mainly based on manual feature engineering. However, the performance of signatures obtained by this way is limited. In this paper, we propose a novel load signature construc-tion method utilizing deep learning techniques. Specifically, three learnable load signatures are presented such as Learnable Recur-rent Graph (LRG), Learnable Gramian Matrix (LGM) and Gen-erative Graph (GG). Furthermore, we test different frameworks for learning these signatures and conclude that Temporal Convo-lutional Networks (TCN) based on residual learning are more suit-able for this work than the other schemes mentioned. The results of experiment on the PLAID datasets with submetered and aggre-gated, WHITED dataset and LILAC dataset confirm that our method outperforms the voltage-current trajectory, Recursive Graph and Gramian Angular Field methods in multiple evalua-tion metrics.

Enhanced NILM load pattern extraction via variable-length motif discovery

Due to the diversity of appliances and users’ power consumption behaviors, it is challenging to accurately extract load signature samples for non-intrusive load monitoring (NILM) in unseen scenarios. To this end, this paper proposes an enhanced NILM load pattern extraction method via variable-length motif discovery. Firstly, the variable-length motif discovery method is used for the first time to discover similar subsequences from the aggregated power time series to extract power waveform signature (PWS) samples for appliances and obtain the power waveform motifs (PWMs). Furthermore, the appliance PWM sequence pattern mining method is proposed to detect complete power consumption patterns of appliance working cycles, and eventually construct the load signature library. Finally, the similarity between the original PWS samples and the templates in the signature library is measured to realize load identification. In practice, the proposed method is intended to integrate into the incremental learning framework, so that the unknown appliances can be identified gradually by continuous iterative learning. The comparison testing results on the public and private datasets demonstrate that the proposed method can effectively discover various PWMs of different appliances, and accurately model their power consumption patterns, thus exhibiting better performance on the unsupervised load identification compared with the existing methods, especially for the complex appliances.

Unsupervised learning of load signatures to estimate energy-related building features using surrogate modelling techniques

Unsupervised learning of load signatures to estimate energy-related building features using surrogate modelling techniques

DiffNILM: A Novel Framework for Non-Intrusive Load Monitoring Based on the Conditional Diffusion Model.

Non-intrusive Load Monitoring (NILM) is a critical technology that enables detailed analysis of household energy consumption without requiring individual metering of every appliance, and has the capability to provide valuable insights into energy usage behavior, facilitate energy conservation, and optimize load management. Currently, deep learning models have been widely adopted as state-of-the-art approaches for NILM. In this study, we introduce DiffNILM, a novel energy disaggregation framework that utilizes diffusion probabilistic models to distinguish power consumption patterns of individual appliances from aggregated power. Starting from a random Gaussian noise, the target waveform is iteratively reconstructed via a sampler conditioned on the total active power and encoded temporal features. The proposed method is evaluated on two public datasets, REDD and UKDALE. The results demonstrated that DiffNILM outperforms baseline models on several key metrics on both datasets and shows a remarkable ability to effectively recreate complex load signatures. The study highlights the potential of diffusion models to advance the field of NILM and presents a promising approach for future energy disaggregation research.

A residual convolutional neural network with multi-block for appliance recognition in non-intrusive load identification

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.

Evaluation of the impact of the electric network's quality on the appliance's signatures

The continuous increase in the demand for electrical energy has led to the design of highly complex electrical systems, which can even extend to entire countries. In this context, active residential customer participation in the smart grid can benefit from having control over a number of data points related to the behaviour of the grid and the devices connected to it. The load signatures are the basis for practical energy's consumption monitoring technologies, which involve identifying an electrical device and determining their operating status. Although several load identification techniques are under development in research laboratories, it is important to note that studies on the impact of power system quality on the signatures underlying these developments are not yet clear. Knowing that load profiles depend on environmental factors, user habits, and other non-deterministic factors, it is important to assess the impact that grid quality can have on load signatures in order to take it into account in the development of identification systems to be integrated into the smart grid. This research focuses on the two central components of these approaches: (1) Presenting an assessment of the different network faults that can impact the signatures of connected loads, (2) Analysing and quantifying the impact of each fault through load behavioural models and virtual simulation. The study considers the two types of loads generally encountered in homes (linear and non-linear). It then analyses the characteristic quantities such as waveforms, effective current and voltage values, active and reactive power (harmonics) and non-deforming power (fundamentals). The results of the simulations performed on Simulink/Simscape show that some network faults such as flicker have a significant and permanent impact on the signatures while others (Voltage Sag) have a temporary and sometimes insignificant effect.

Feature Extraction of V–I Trajectory Using 2-D Fourier Series for Electrical Load Classification

Nonintrusive load monitoring (NILM) techniques allow the individual consumption of devices in an installation to be reported to the user, collaborating in the awareness and managing consumers’ energy use. One of the most critical steps in NILM procedures is feature extraction, which involves the quantitative description of the load signature. Most state-of-the-art methods, particularly those involving voltage–current ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">V–I</i> ) trajectories, are based on features that specialists design when manually analyzing signals—the so-called hand-crafted features. On the other hand, this work presents a mathematical method that describes the transient and steady-state (SS) load signature using a 2-D Fourier series, avoiding hand-crafted descriptors. The proposed approach evaluates load identification results with different classifiers and publicly available datasets. In addition to the evaluation of the proposed method’s computational resources, such as execution time and memory footprint in an embedded system, their robustness to noise insertion is also assessed. The results of the proposed approach indicate an average per-class accuracy higher than 90%, equivalent or superior to hand-crafted <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">V–I</i> trajectory-based methods in most cases and even deep learning approaches recently presented in the literature. Such results reinforce the main contributions of this work: 1) a mathematical method to extract interpretable features; 2) results comparable or superior to other state-of-the-art methods; and 3) promising results in computational resources in an embedded system.

Non-Intrusive Load Monitoring Based on the Graph Least Squares Reconstruction Method

Monitoring the operating conditions of residential appliances by collecting the total power consumption data of households has a great significance for smart power utilization. In this study, a graph least squares reconstruction approach is proposed. First, the graph signal is constructed using the collected active power consumption data, providing unique appliance signature information. The signal smoothness of the graph and an iterative least squares reconstruction algorithm are utilized for classification. The proposed graph reconstruction method relies on only low-sampling data from installed smart meters. It aims to address some existing problems of event-based NILM methods like measurement noise, indistinguishable load signatures, and inaccurate power reconstruction. Also, extensive training and associated calculations are not required. Simulation results on the REDD benchmark dataset demonstrate that the proposed method outperforms some of the current state-of-the-art techniques.

Non‐intrusive Load Monitoring Using Gramian Angular Field Color Encoding in Edge Computing

Non-intrusive load monitoring (NILM) can infer the status of the appliances in operation and their energy consumption by analyzing the energy data collected from monitoring devices. With the rapid increase of electric loads in amount and type, the traditional way of uploading all energy data to cloud is facing enormous challenges. It becomes increasingly significant to construct distinguishable load signatures and build robust classification models for NILM. In this paper, we propose a load signature construction method for load recognition task in home scenarios. The load signature is based on the Gramian angular field encoding theory, which is convenient to construct and significantly reduces the data transmission volume of the network. Moreover, edge computing architecture can reasonably utilize computing resources and relieve the pressure of the server. The experimental results on NILM datasets demonstrate that the proposed method obtains superior performance in the recognition of household appliances under insufficient resources.

A New Method of Extracting RGB V-I Trajectory for Non-intrusive Load Monitoring

Existing methods of extracting V-I trajectory in RGB space used as load signatures for non-intrusive load monitoring (NILM) are complex and not suitable for edge computed devices. To solve this problem, we propose a new method to obtain the RGB V-I trajectory. The new method is simple and efficient by using the time derivatives of instantaneous reactive current and voltage to map the grayscale V-I trajectory to RGB space. Then, a lightweight CNN model, ShuffleNetV2, is selected to carry out a transfer learning study for NILM problem. Using RGB V-I trajectory obtained by using the method in this paper as load signature achieves a 5.1% improvement in F1-score than using grayscale V-I trajectory. A V-I trajectory of larger resolution avails the improvement of transfer learning performance, and the model trained on RGB V-I trajectory seems to be less affected by input resolutions for a smaller variance in F1-score among various input resolutions.

A Non-Intrusive Residential Electric Bicycle Load Monitoring Method Based on Hybrid Feature Bitmap and DeiT

Taking into account energy management and fire safety, electric bicycles are one of the most significant household loads that require real-time sensing for nonintrusive load monitoring. V–I trajectories, power quantities, and harmonic characteristics are the basic selection in feature space for appliance identification. Based on the study of the charging mode of electric bicycles, this study expands the V–I trajectory into V-△I trajectory for gaining the load signature with multi appliances working simultaneously. We perform linear interpolation and pixelation to obtain a bitmap of the V-△I trajectory. Meanwhile, active and harmonic features are encoded and combined to form a hybrid feature bitmap, which is unique to compensate for the high harmonic feature loss caused by the pixelation of the V-△I trajectory. Furthermore, we trained the DeiT model on the self-built dataset and UK-DALE dataset and performed two experiments under single and superposition working conditions for electric bicycles. Our case results indicate that the DeiT model using hybrid feature bitmap offers better overall precision in the prediction of electric bicycles, against other deep convolutional neural networks.

Abstract 2198: The impact of carcinogens, obesity, and chronic inflammatory processes on mutational signatures and cancer risk in mouse tumor models

Abstract An estimated 40% of all human cancers are suspected to be a result of modifiable risk factors such as obesity, high fat diet and chronic inflammation. Whole genome sequencing (WGS) of thousands of human tumors have revealed “mutational signatures” that provide a molecular footprint of cancer origins. Whether such signatures exist for modifiable cancer risk factors remains unclear. We studied the impact of lifestyle risk factors using a compendium of 107 mouse tumors that model obesity, high fat diet, wounding, chronic inflammation, or chemotherapy. We used a well-established 2-step skin carcinogenesis model composed of exposure to mutagen DMBA followed by tumor promoter TPA, generating squamous carcinomas that were analysed by WGS for identification of mutational signatures. In addition to recapitulating many COSMIC human signatures, we identified a novel SNV signature induced by a single treatment with DMBA (SBS.DMBA) which explains the majority of all detected mutations. While a single exposure of normal skin to DMBA induces a highly variable number of carcinogen-specific mutations, a very high mutation burden is insufficient for tumorigenesis. SNVs attributable to reactive oxygen species (ROS) are broadly found in about 25% of all mouse tumors, but are most prominent in tumors from mice that are exposed to DMBA in utero, suggesting that the developmental age of mutagen exposure may impact the repair of ROS generated mutations and that the timing of exposure is a poorly understudied component of carcinogenesis. In mouse tumor models of genetic and dietary obesity, the total mutational load and mutational signatures in tumors from obese mice were indistinguishable from those of lean mice despite dramatic differences in tumor latency and progression as well transcriptomic differences in immune activation. We found an enrichment in deleterious Tgfrb2 mutations in tumors from mice with low compared to high body mass index (BMI) (p&amp;lt;0.016). Using a conditionally activated RAS mouse model, we also show that a non-mutagenic inflammatory signal such as a chronic wound can act as the rate-limiting step for full tumor development. Surprisingly these tumors can be evoked even in somatic genomes with very few mutations apart from the initiating Ras driver. Finally, together with the Riva et al study, these chemically induced mouse tumors recapitulate &amp;gt;50% of established human cancer driver genes. DMBA caused 91% of all Hras/Kras mutations, but only a minority of other recurrent driver mutations in genes such as Trp53 and Tert, suggesting that these occur later during the process of carcinogenesis. Taken together, we have analyzed the largest compendium of WGS data from nearly 300 mouse tumors, showing that while exogenous promotional factors do not increase mutation burden or induce novel mutational patterns, they have a major rate-limiting role in determining cancer risk. Citation Format: Yun Rose Li, Kyle Halliwill, Eve Kandyba, Reyno Delrosario, Quan Tran, Nora Bayani, Di Wu, Olga Mirzoeva, Melissa McCreery Reeves, Mishu Islam, Laura Riva, Eric Bergstrom, John Digiovanni, Ludmil Alexandrov, Allan Balmain. The impact of carcinogens, obesity, and chronic inflammatory processes on mutational signatures and cancer risk in mouse tumor models [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 2198.

128: DECIPHERING THE IMMUNOLOGICAL DETERMINANTS OF RESPONSE TO NEOADJUVANT CHEMO-RADIATION IN ESOPHAGEAL ADENOCARCINOMA

Abstract Background and aim The standard therapy for esophageal adenocarcinoma (EAC) is pre-operative neoadjuvant chemo-radiation (NACR) and surgery. Less that 30% of patients achieve a pathological complete response (pCR) and increased 5-year survival after NACR. Understanding the mechanisms of response to NACR is pivotal to better stratify patients and inform the design of more efficacious therapies. Cancer progression partly depends on defective immune surveillance, and the presence of tumor infiltrating T lymphocytes (TILs) is associated with better prognosis of several malignancies. We hypothesize that NACR induces immunogenic cell death that stimulates immune responses against tumor neoantigens (TNAs), derived from cancer somatic mutations, in the responders. We thus compared responders and non-responders for tumor immune contexture, immune molecular pathways, circulating immune markers and TNAs-specific T cells responses. Methods Pre-NACR tumor biopsies prospectively collected from consecutive EAC patients were subjected to DNA whole exome and RNA sequencing, high dimensional (HD) multiparametric flow cytometry and immune contexture analysis by histology and by proteome digital spatial profiling (n = 53 targets), while their peripheral blood mononuclear cells and plasma collected pre- and post- NACR were analyzed by HD flow cytometry and cytokine multiplexing assay respectively. Results Treatment-naïve EACs of NACR responders showed higher TNA load and enriched immune signatures compared to non-responders. Moreover, pre-treatment EACs of responders demonstrate augmented effector T cell infiltration and reduced Treg cells and M2-like pro-tumoral macrophages. High M2-like macrophages score associated with lower overall survival. Increased frequencies of circulating myeloid suppressor populations were detected both at baseline and after NACR in non-responder patients. These observations were associated with circulating levels of n = 30 cytokines/chemokines and with spatial expression of immune markers in tumor biopsies. Conclusion Collectively, these results support pre-existing immune-mediated mechanisms of anti-tumor response stimulated by NACR in the fraction of responder EAC patients, suggesting possible ways to stratify patients and direct them to more tailored neoadjuvant and/or adjuvant treatments, possibly in combination with personalized immunotherapy approaches.

Spectral Kurtosis Based Methodology for the Identification of Stationary Load Signatures in Electrical Signals from a Sustainable Building

The increasing use of nonlinear loads in the power grid introduces some unwanted effects, such as harmonic and interharmonic contamination. Since the existence of spectral contamination causes waveform distortion that may be harmful to the loads that are connected to the grid, it is important to identify the frequency components that are related to specific loads in order to determine how relevant their contribution is to the waveform distortion levels. Due to the diversity of frequency components that are merged in an electrical signal, it is a challenging task to discriminate the relevant frequencies from those that are not. Therefore, it is necessary to develop techniques that allow performing this selection in an efficient way. This paper proposes the use of spectral kurtosis for the identification of stationary frequency components in electrical signals along the day in a sustainable building. Then, the behavior of the identified frequencies is analyzed to determine which of the loads connected to the grid are introducing them. Experimentation is performed in a sustainable building where, besides the loads associated with the normal operation of the building, there are several power electronics equipment that is used for the electric generation process from renewable sources. Results prove that using the proposed methodology it is possible to detect the behavior of specific loads, such as office equipment and air conditioning.

A robust non-intrusive load disaggregation method with roof-top photovoltaics

As a promising technology dealing with electric behavior analysis and energy characteristic mining, non-intrusive load monitoring is popular with these people with energy conservation awareness. Coincidentally, these residents are with strong motivation to install roof-top photovoltaics. Therefore, it is a real challenge to implement non-intrusive load disaggregation considering PV integrations, which is rarely researched. In this paper, this problem is thoroughly investigated with an achievement of a corresponding robust load disaggregation approach. At the first stage, the problem formulation is established based on the evolved dictionary learning scheme, where the special features of PV, e.g., no switching pattern and continuous power variation, are addressed. Secondly, aiming at robustness of monitoring, the steady state disaggregation is enhanced by integrating with event-based detection, forming a hybrid validation strategy. Then, the whole problem is solved following the sparse coding principle. The proposed study is verified by both simulation tests and field measurements, and the results show that the proposed method is accurate and robust in non-intrusive load monitoring with PV consideration. Besides, it is compatible with various load signature utilization, leading to a practical disaggregation solution.