Search Results (214)

Most available smart meters sample at low rates and transmit the acquired measurements to a cloud server for further processing. This article presents a prototype smart meter operating at a high sampling frequency (15 kHz) and performing energy disaggregation locally, thus negating the need to transmit the acquired high-frequency measurements. The prototype’s architecture comprises a custom signal conditioning circuit and an embedded board that performs energy disaggregation using a deep learning model. The influence of the sampling frequency on the model’s accuracy and the edge device power consumption, throughput, and latency across different hardware platforms is evaluated. The architecture embeds NILM inference into the meter hardware while maintaining a compact and energy-efficient design. The presented smart meter is benchmarked across six embedded platforms, evaluating model accuracy, latency, power usage, and throughput. Furthermore, three novel hardware-aware performance metrics are introduced to quantify NILM efficiency per unit cost, throughput, and energy, offering a reproducible framework for future NILM-enabled edge meter designs. Full article

Existing non-intrusive load monitoring (NILM) methods predominantly rely on centralized models, which introduce privacy vulnerabilities and lack scalability in large industrial park scenarios equipped with distributed energy resources. To address this issue, a Federated Temporal Pattern-based NILM framework (FedTP-NILM) is proposed. It aims to ensure data privacy while enabling efficient load monitoring in distributed and heterogeneous environments, thereby extending the applicability of NILM technology in large-scale industrial park scenarios. First, a federated aggregation method is proposed, which integrates the FedYogi optimization algorithm with a secret sharing mechanism to enable the secure aggregation of local data. Second, a pyramid neural network architecture is presented to capture complex temporal dependencies in load identification tasks. It integrates temporal encoding, pooling, and decoding modules, along with an enhanced feature extractor, to better learn and distinguish multi-scale temporal patterns. In addition, a hybrid data augmentation strategy is proposed to expand the distribution range of samples by adding noise and linear mixing. Finally, experimental results validate the effectiveness of the proposed federated learning framework, demonstrating superior performance in both distributed energy device identification and privacy preservation. Full article

Advanced Non-Intrusive Load Monitoring (NILM) research is important to help reduce energy consumption. Very-low-frequency approaches have traditionally faced challenges in separating appliance uses due to low discriminative information. The richer signatures available in high-frequency electrical data include many harmonic orders that have the potential to advance disaggregation. This has been explored to some extent, but not comprehensively due to a lack of an appropriate public dataset. This paper presents the development of a cost-effective energy monitoring system scalable for multiple entries while producing detailed measurements. We will detail our approach to creating a NILM dataset comprising both aggregate loads and individual appliance measurements, all while ensuring that the dataset is reproducible and accessible. Ultimately, the dataset can be used to validate NILM, and we show through the use of machine learning techniques that high-frequency features improve disaggregation accuracy when compared with traditional methods. This work addresses a critical gap in NILM research by detailing the design and implementation of a data acquisition system capable of generating rich and structured datasets that support precise energy consumption analysis and prepare the essential materials for advanced, real-time energy disaggregation and smart energy management applications. Full article

Load disaggregation has emerged as an effective tool for enabling smarter energy management in residential and commercial buildings. By providing appliance-level energy consumption estimation from aggregate data, it supports energy efficiency initiatives, demand-side management, and user awareness. However, several challenges remain in improving the accuracy of energy disaggregation methods. For instance, the amount of noise in energy consumption datasets can heavily impact the accuracy of disaggregation algorithms, especially for low-power consumption appliances. While disaggregation performance depends on hyperparameter tuning, the influence of data characteristics, such as noise, on hyperparameter selection remains underexplored. This work investigates the hypothesis that appliance-specific noise information can guide the selection of algorithm hyperparameters, like the input sequence length, to maximize disaggregation accuracy. The appliance-to-noise ratio metric is used to quantify the noise level relative to each appliance’s energy consumption. Then, the selection of the input sequence length hyperparameter is investigated for each case by inspecting disaggregation performance. The results indicate that the noise metric provides valuable guidance for selecting the input sequence length, particularly for user-dependent appliances with more unpredictable usage patterns, such as washing machines and electric kettles. Full article

Machine learning (ML) has emerged as a transformative force in smart building management due to its ability to significantly enhance energy efficiency and promote sustainability within the built environment. This review examines the pivotal role of ML in optimizing building operations through the application of predictive analytics and sophisticated automated control systems. It explores the diverse applications of ML techniques in critical areas such as energy forecasting, non-intrusive load monitoring (NILM), and predictive maintenance. A thorough analysis then identifies key challenges that impede widespread adoption, including issues related to data quality, privacy concerns, system integration complexities, and scalability limitations. Conversely, the review highlights promising emerging opportunities in advanced analytics, the seamless integration of renewable energy sources, and the convergence with the Internet of Things (IoT). Illustrative case studies underscore the tangible benefits of ML implementation, demonstrating substantial energy savings ranging from 15% to 40%. Future trends indicate a clear trajectory towards the development of highly autonomous building management systems and the widespread adoption of occupant-centric designs. Full article

Non-active current in the time domain is considered for application to the diagnostics and classification of loads in power grids based on waveform-distortion characteristics, taking as a working example several recordings of the pantograph current in an AC railway system. Data are processed with a deep autoencoder for feature extraction and then clustered via k-means to allow identification of patterns in the latent space. Clustering enables the evaluation of the relationship between the physical meaning and operation of the system and the distortion phenomena emerging in the waveforms during operation. Euclidean distance (ED) is used to measure the diversity and pertinence of observations within pattern groups and to identify anomalies (abnormal distortion, transients, …). This approach allows the classification of new data by assigning data to clusters based on proximity to centroids. This unsupervised method exploiting non-active current is novel and has proven useful for providing data with labels for later supervised learning performed with the 1D-CNN, which achieved a balanced accuracy of 96.46% under normal conditions. ED and 1D-CNN methods were tested on an additional unlabeled dataset and achieved 89.56% agreement in identifying normal states. Additionally, Grad-CAM, when applied to the 1D-CNN, quantitatively identifies the waveform parts that influence the model predictions, significantly enhancing the interpretability of the classification results. This is particularly useful for obtaining a better understanding of load operation, including anomalies that affect grid stability and energy efficiency. Finally, the method has been also successfully further validated for general applicability with data from a different scenario (charging of electric vehicles). The method can be applied to load identification and classification for non-intrusive load monitoring, with the aim of implementing automatic and unsupervised assessment of load behavior, including transient detection, power-quality issues and improvement in energy efficiency. Full article

The increasing need for efficient energy consumption monitoring, driven by economic and environmental concerns, has made Non-Intrusive Load Monitoring (NILM) a cost-effective alternative to traditional measurement methods. Despite its progress since the 1980s, NILM still lacks standardized benchmarks, limiting objective performance comparisons. This study introduces several key contributions: (1) the development of five new converters with 13-digit timestamp support and harmonic inclusion, improving the data collection accuracy by up to 25%; (2) the implementation of an advanced disaggregation software, achieving a 10–15% increase in the F1-score for certain appliances; (3) a detailed analysis of harmonics’ impact on NILM, reducing the Mean Normalized Error in Assigned Power by up to 40%; and (4) the design of open-source measurement hardware to enhance reproducibility. This study also evaluates open hardware platforms and compares five common household appliances using NILM Toolkit metrics. Results demonstrate that open hardware and software foster reproducibility and accelerate innovation in NILM. The proposed approach contributes to a standardized and scalable NILM framework, facilitating real-world applications in energy management and smart grid optimization. Full article

Elevators are a vital part of urban infrastructure, playing a key role in smart cities where increasing population density has driven the rise in taller buildings. As an essential means of vertical transportation, elevators have become an integral part of daily life, making their design, construction, and maintenance crucial to ensuring safety and compliance with evolving industry standards. The safety of elevator systems depends on the continuous monitoring and fault-free operation of Permanent Magnet Synchronous Motor (PMSM) drives, which are critical to their performance. Furthermore, the fault-free operation of PMSM drives reduces operating costs, increases service life, and improves reliability. The PMSM drive components may be susceptible to electrical, mechanical, and thermal faults that, if undetected, can lead to operational disruptions or safety risks. The integration of artificial intelligence and Internet of Things (IoT) technologies can enhance fault prediction, reducing downtime and improving efficiency. Ongoing challenges such as managing machine thermal load and developing more durable materials for PMSMs require the development of suitable models that are adapted to existing drive systems. The proposed framework for fault prediction is validated on a real residential elevator equipped with a PMSM drive. Multimodal signal data is processed through a Generative Adversarial Network (GAN)-enhanced Positive Unlabeled (PU) classifier and a Reinforcement Learning (RL)-based adaptive decision engine, enabling robust and scalable fault prediction in a non-intrusive fashion. Full article

Non-Intrusive Load Monitoring (NILM) technology, enabled by high-precision electrical data acquisition sensors at household entry points, facilitates real-time monitoring of electricity consumption, enhancing user interaction with smart home systems and reducing electrical safety risks. However, the growing diversity of household appliances and limitations in NILM accuracy and robustness necessitate innovative solutions. Additionally, outdated public datasets fail to capture the rapid evolution of modern appliances. To address these challenges, we constructed a high-sampling-rate voltage–current dataset, measuring 15 common household appliances across diverse scenarios in a controlled laboratory environment tailored to regional grid standards (220 V/50 Hz). We propose an AI-driven NILM method that integrates power-mapped, color-coded voltage–current (V–I) trajectories with frequency-domain features to significantly improve load recognition accuracy and robustness. By leveraging deep learning frameworks, this approach enriches temporal feature representation through chromatic mapping of instantaneous power and incorporates frequency-domain spectrograms to capture dynamic load behaviors. A novel channel-wise attention mechanism optimizes multi-dimensional feature fusion, dynamically prioritizing critical information while suppressing noise. Comparative experiments on the custom dataset demonstrate superior performance, particularly in distinguishing appliances with similar load profiles, underscoring the method’s potential for advancing smart home energy management, user-centric energy feedback, and social informatics applications in complex electrical environments. Full article

The increasing energy intensity of the economy has led us to look for ways to reduce this negative trend. One method is non-intrusive load monitoring (NILM). This paper presents the use of artificial intelligence methods for the selection of information features and for the identification of operating electrical devices. A set of potential identification features was obtained from high-frequency measurements covering 12 types of electrical consumers and consisted of 218 features. From these, an identification vector was selected via the mRMR (minimum redundancy maximum relevance) method, which searches for features that are maximally correlated with the class and are as little correlated with each other as possible. Identification was realized by building a hybrid classifier using binary classifiers built from artificial neural networks and decision trees. The Accuracy, Precision, Recall, and F1 metrics were used to assess the quality of identification. The obtained values of the identification quality indicators confirm that it is possible to replace multiclass classification in NILM with binary classification without losing its quality. The use of binary classifiers allows for the identification of new devices without the need to change the classifier configuration. Full article

Non-intrusive load monitoring (NILM) enables the disaggregation of appliance-level energy consumption from aggregate electrical signals, offering a scalable solution for improving efficiency. This study compared the performance of traditional NILM algorithms (Mean, CO, Hart85, FHMM) and deep neural network-based approaches (DAE, RNN, Seq2Point, Seq2Seq, WindowGRU) under various experimental conditions. Factors such as sampling rate, harmonic content, and the application of power filters were analyzed. A key aspect of the evaluation was the difference in testing conditions: while traditional algorithms were evaluated under multiple experimental configurations, deep learning models, due to their extremely high computational cost, were analyzed exclusively under a specific configuration consisting of a 1-s sampling rate, with harmonic content present and without applying power filters. The results confirm that no universally superior algorithm exists, and performance varies depending on the type of appliance and signal conditions. Traditional algorithms are faster and more computationally efficient, making them more suitable for scenarios with limited resources or rapid response requirements. However, significantly more computationally expensive deep learning models showed higher average accuracy (MAE, RMSE, NDE) and event detection capability (F1-SCORE) in the specific configuration in which they were evaluated. These models excel in detailed signal reconstruction and handling harmonics without requiring filtering in this configuration. The selection of the optimal NILM algorithm for real-world applications must consider a balance between desired accuracy, load types, electrical signal characteristics, and crucially, the limitations of available computational resources. Full article

Non-Intrusive Load Monitoring (NILM), a technique that extracts appliance-level energy consumption information through analysis of aggregated electrical measurements, has become essential for smart grids and energy management applications. Given the increasing diversification of electrical appliances, real-time NILM systems require continuous integration of knowledge from new client-side appliance data to maintain monitoring effectiveness. However, current methods face challenges with inter-client knowledge conflicts and catastrophic forgetting in distributed multi-client continual learning scenarios. This study addresses these challenges by proposing a confidence-based collaborative distributed continual learning framework for NILM. A lightweight layer-wise dual-supervised autoencoder (LWDSAE) model is initially designed for smart meter deployment, supporting both load identification and confidence-based collaboration tasks. Clients with learning capabilities generate new models through one-time fine-tuning, facilitating collaboration among client models and enhancing individual client load identification performance via a confidence judgment method based on signal reconstruction deviations. Furthermore, an anomaly sample detection-driven model portfolios update method is developed to assist each client in maintaining optimal local performance under model quantity constraints. Comprehensive evaluations on two public datasets and real-world applications demonstrate that the framework achieves sustained performance improvements in distributed continual learning scenarios, consistently outperforming state-of-the-art methods. Full article

Non-intrusive load monitoring (NILM) provides a cost-effective solution for smart services across numerous appliances by inferring appliance-level information from mains electrical measurements. With the rapid growth in appliance diversity, continual learning that adapts to new appliances while retaining knowledge of previously learned appliances is of great interest. However, existing methods can handle only a few new appliance types and suffer from high computational complexity and data leakage risks. Therefore, an analytic continual learning-based (ACL) NILM method is proposed. The method employs a lightweight model that is constructed with dual output branches using depthwise separable convolution for load identification and novelty detection. Meanwhile, a supervised contrastive learning strategy is applied to enhance the distinctiveness among appliance types in the feature extraction module. When the novelty detection branch determines that new data need to be learned, the parameters of the dual branches are updated by recursively calculating the analytical solution using only the current data. Experiments on four public datasets demonstrate superior performance on pre-collected appliances with lower computational effort. It also significantly outperforms existing methods during the continual learning process, as the number of appliance types increases to 56. The practicality of the proposed method is validated through a real-world application on an STM32F407-based smart socket. Full article

Ensuring the safe, reliable, and energy-efficient provision of electricity is a complex task for smart grid (SG) management applications. Internet of Things (IoT) and edge computing-based SG applications have been proposed for time-responsive monitoring and controlling tasks related to power systems. Recent studies have provided valuable insights into the potential of machine learning algorithms in SGs, covering areas such as generation, distribution, microgrids, consumer energy market, and cyber security. Integrated IoT devices directly exchange data with the SG cloud, which increases the vulnerability and security threats to the energy system. The review aims to provide a comprehensive analysis of privacy-preserving machine learning (PPML) applications in IoT-Integrated SGs, focusing on non-intrusive load monitoring, fault detection, demand forecasting, generation forecasting, energy-management systems, anomaly detection, and energy trading. The study also highlights the importance of data privacy and security when integrating these applications to enable intelligent decision-making in smart grid domains. Furthermore, the review addresses performance issues (e.g., accuracy, latency, and resource constraints) associated with PPML techniques, which may impact the security and overall performance of IoT-integrated SGs. The insights of this study will provide essential guidelines for in-depth research in the field of IoT-integrated smart grid privacy and security in the future. Full article

With global efforts intensifying towards achieving carbon neutrality, accurately monitoring and managing energy consumption in industrial sectors has become critical. Non-Intrusive Load Monitoring (NILM) technology presents a cost-effective solution for industrial energy management by decomposing aggregate power data into individual device-level information without extensive hardware requirements. However, existing NILM methods primarily tailored for residential applications struggle to capture complex inter-device correlations and production-dependent load dynamics prevalent in industrial environments, such as cement plants. This paper proposes a novel sequence-to-sequence-based non-intrusive load disaggregation method that integrates Convolutional Neural Networks (CNN) and Transformer architectures, specifically addressing the challenges of multi-device load disaggregation in industrial settings. An innovative time–application attention mechanism was integrated to effectively model long-term temporal dependencies and the collaborative operational relationships between industrial devices. Additionally, global constraints—including consistency, smoothness, and sparsity—were introduced into the loss function to ensure power conservation, reduce noise, and achieve precise zero-power predictions for inactive equipment. The proposed method was validated on real-world power consumption data collected from a cement production facility. Experimental results indicate that the proposed method significantly outperforms traditional NILM approaches with average improvements of 4.98%, 3.70%, and 4.38% in terms of accuracy, recall, and F1-score, respectively. These findings underscore its superior robustness in noisy conditions and under device fault conditions, further affirming its applicability and potential for deployment in industrial settings. Full article