arXiv subjects

Elena Gryazina

Publications and source records attributed to Elena Gryazina.

10 recordsLinked to original sources

arXiv2025

Toward Explainable NILM: Real-Time Event-Based NILM Framework for High-Frequency Data

Non-Intrusive Load Monitoring (NILM) is an advanced, and cost-effective technique for monitoring appliance-level energy consumption. However, its adaptability is hindered by the lack of transparency and explainability. To address this challenge, this paper presents an explainable, real-time, event-based NILM framework specifically designed for high-frequency datasets. The proposed framework ensures transparency at every stage by integrating a z-score-based event detector, appliance signature estimation, Fourier-based feature extraction, an XG-Boost classifier, and post hoc SHAP analysis. The SHAP analysis further quantifies the contribution of individual features, such as cosine of specific harmonic phases, to appliance classification. The framework is trained and evaluated on the PLAID dataset, and achieved a classification accuracy of 90% while maintaining low computational requirements and a latency of less than one second.

eess.SY↗

arXiv2025

COLD: Concurrent Loads Disaggregator for Non-Intrusive Load Monitoring

The global effort toward renewable energy and the electrification of energy-intensive sectors have significantly increased the demand for electricity, making energy efficiency a critical focus. Non-intrusive load monitoring (NILM) enables detailed analyses of household electricity usage by disaggregating the total power consumption into individual appliance-level data. In this paper, we propose COLD (Concurrent Loads Disaggregator), a transformer-based model specifically designed to address the challenges of disaggregating high-frequency data with multiple simultaneously working devices. COLD supports up to 42 devices and accurately handles scenarios with up to 11 concurrent loads, achieving 95% load identification accuracy and 82% disaggregation performance on the test data. In addition, we introduce a new fully labeled high-frequency NILM dataset for load disaggregation derived from the UK-DALE 16 kHz dataset. Finally, we analyze the decline in NILM model performance as the number of concurrent loads increases.

eess.SP↗

arXiv2022

Power System Anomaly Detection and Classification Utilizing WLS-EKF State Estimation and Machine Learning

Power system state estimation is being faced with different types of anomalies. These might include bad data caused by gross measurement errors or communication system failures. Sudden changes in load or generation can be considered as anomaly depending on the implemented state estimation method. Additionally, considering power grid as a cyber physical system, state estimation becomes vulnerable to false data injection attacks. The existing methods for anomaly classification cannot accurately classify (discriminate between) the above mentioned three types of anomalies, especially when it comes to discrimination between sudden load changes and false data injection attacks. This paper presents a new algorithm for detecting anomaly presence, classifying the anomaly type and identifying the origin of the anomaly, i.e., measurements that contain gross errors in case of bad data, or buses associated with loads experiencing a sudden change, or state variables targeted by false data injection attack. The algorithm combines analytical and machine learning (ML) approaches. The first stage exploits an analytical approach to detect anomaly presence by combining $χ^2$-test and anomaly detection index. The second stage utilizes ML for classification of anomaly type and identification of its origin, with particular reference to discrimination between sudden load changes and false data injection attacks. The proposed ML based method is trained to be independent of the network configuration which eliminates retraining of the algorithm after network topology changes. The results obtained by implementing the proposed algorithm on IEEE 14 bus test system demonstrate the accuracy and effectiveness of the proposed algorithm.

eess.SY↗

arXiv2021

Application of blockchain for secure data transmission in distributed state estimation

The application of renewable energy sources in the power grid increases the necessity of tracking the system's state, especially in smart grids, where there is a bidirectional transfer of data and power. The complexity of coupling between communication and the electrical infrastructure in a smart grid will create a higher chance for security breach. Increasing the state estimation accuracy will help the smart grid operator efficiently manage the system. The paper proposes an integration of distributed state estimation with a blockchain designed communication platform. Additionally, the asynchronous manner for data transmission, which is more likely to happen in the real world, has been considered as the second task of this research. Finally, a detailed analysis of the blockchain-based application in distributed state estimation is provided. The numerical analysis shows that the proposed method meets real-world performance requirements and brings high security and reliability to the distributed state estimation process.

eess.SY↗

arXiv2021

Optimal partitioning in distributed state estimation considering a modified convergence criterion

Distributed state estimation (DSE) is considered as a more robust and reliable alternative for centralized state estimation (CSE) in power system. Especially, taking into account the future power grid, so called smart grid in which bi-directional transfer of energy and information happens, and renewable energy sources with huge indeterminacy are applied more than before. Combining the mentioned features and complexity of the power network, there is a high probability that CSE face problems such as communication bottleneck or security/reliability issues. So, DSE has the potential to be considered as a solution to solve the mentioned issues. In this paper, first, a modified convergence criterion is proposed and has been tested for different approaches of DSE problem, considering the most important factors such as iteration number, convergence rate, and data needed to be transferred to/from each area. Then, an optimal partitioning technique has been implemented for clustering the system into different areas. Besides the detailed analysis and comparison of recent DSE methods, the proposed partitioning method's effectiveness has been shown in this paper.

eess.SY↗

arXiv2021

Voltage Feasibility Boundaries for Power System Security Assessment

Modern power systems face a grand challenge in grid management due to increased electricity demand, imminent disturbances, and uncertainties associated with renewable generation, which can compromise grid security. The security assessment is directly connected to the robustness of the operating condition and is evaluated by analyzing proximity to the power flow solution space's boundary. Calculating location of such a boundary is a computationally challenging task, linked to the power flow equations' non-linear nature, presence of technological constraints, and complicated network topology. In this paper we introduce a general framework to characterize points on the power flow solution space boundary in terms of auxiliary variables subject to algebraic constraints. Then we develop an adaptive continuation algorithm to trace 1-dimensional sections of boundary curves which exhibits robust performance and computational tractability. Implementation of the algorithm is described in detail, and its performance is validated on different test networks.

math.NA↗

arXiv2021

Distributed state estimation: a novel stopping criterion

Power System State Estimation (PSSE) has been a research area of interest for power engineers for a long period of time. Due to the intermittent nature of renewable energy sources, which are applied in the power network more than before, the importance of state estimation has been increased as well. Centralized state estimation due to the complexity of new networks and growing size of power network will face problems such as communication bottleneck in real-time analyzing of the system or reliability issues. Distributed state estimation is a solution for the mentioned issues. There are different implementation methods introduced for it. The results of the paper are twofold. First, we examined different approaches to distributed PSSE (DPSSE) problem, according to most important factors like iteration number, convergence rate, data needed to be transferred to/from each area and so on. Next, we proposed and discussed a new distributed stopping criterion for the methods and above-mentioned factors are obtained as well. Finally, a comparison between the total efficiency of all applied methods is done.

eess.SY↗

arXiv2020

ADMM-based Distributed State Estimation for Power Systems: Evaluation of Performance

Recently, distributed algorithms for power system state estimation have attracted significant attention. Along with such advantages as decomposition, parallelization of the original problem and absence of a central computation unit, distributed state estimation may also serve for local information privacy reasons since the only information to be transferred is the boundary states of neighboring areas. In this paper, we propose some novel approaches for speeding up the ADMM-based distributed state estimation algorithms by utilizing some recent results in optimization theory. We also thoroughly analyze the theoretical and practical performance, concluding that accelerated approach outperforms the existing ones. The theoretical considerations are verified through the experiments on a scalable example.

math.OC↗

arXiv2018

Geometry of quadratic maps via convex relaxation

We consider several basic questions pertaining to the geometry of image of a general quadratic map. In general the image of a quadratic map is non-convex, although there are several known classes of quadratic maps when the image is convex. Remarkably, even when the image is not convex it often exhibits hidden convexity: a surprising efficiency of convex relaxation to address various geometric questions by reformulating them in terms of convex optimization problems. In this paper we employ this strategy and put forward several algorithms that solve the following problems pertaining to the image: verify if a given point does not belong to the image; find the boundary point of the image lying in a particular direction; stochastically check if the image is convex, and if it is not, find a maximal convex subset of the image. Proposed algorithms are implemented in the form of an open-source MATLAB library CAQM, which accompanies the paper. Our results can be used for various problems of discrete optimization, uncertainty analysis, physical applications, and study of power flow equations.

math.OC↗

arXiv2014

Random sampling: Billiard Walk algorithm

Hit-and-Run is known to be one of the best random sampling algorithms, its mixing time is polynomial in dimension. Nevertheless, in practice the number of steps required to achieve uniformly distributed samples is rather high. We propose new random walk algorithm based on billiard trajectories. Numerical experiments demonstrate much faster convergence to uniform distribution.

math.OC↗