New phasor‐based approach for online and fast prediction of generators grouping using decision tree

An eigensystem realization algorithm based data-driven approach for extracting electromechanical oscillation dynamic patterns from synchrophasor measurements in bulk power grids

Technical analyses of several recent power blackouts revealed that a group of generators going out-of-step with the rest of the power system is often a precursor of a complete system collapse. Out-of-step protection is designed to assess the stability of the evolving swing after a disturbance and take control action accordingly. However, the settings of out-of-step relays are found to be unsatisfactory due to the fact that the electromechanical swings that occurred during relay commissioning are different in practice. These concerns motivated the development of a novel approach to recalculate the out-of-step protection settings to suit the prevalent operating condition. With phasor measurement unit (PMU) technology, it is possible to adjust the setting of out-of-step relay in real-time. The setting of out-of-step relay is primarily determined by three dynamic parameters: direct axis transient reactance, quadrature axis speed voltage and generator inertia. In a complex power network, these parameters are the dynamic parameters of an equivalent model of a coherent group of generators. Hence, it is essential to identify the coherent group of generators and estimate the dynamic model parameters of each generator in the system first in order to form the dynamic model equivalent in the system. The work presented in this thesis develops a measurement-based technique to identify the coherent areas of power system network by analysing the measured data obtained from the system. The method is based on multivariate analysis of the signals, using independent component analysis (ICA). Also, a technique for estimating the dynamic model parameters of the generators in the system has been developed. The dynamic model parameters of synchronous generators are estimated by processing the PMU measurements using unscented Kalman filter (UKF).

A dynamic neural network (NN) based multi-class classifier is proposed for improving online prediction of coherent generator groups (CGGs), following the occurrences of various contingencies in the power grid. This is motivated by the increasing availability of the measurements from phasor measurement units (PMUs) and the number of grouping schemes is limited. The proposed method consists of three steps. First, by performing offline simulations, a library of system dynamic responses characterized by post-contingency rotor angles and speeds of individual generators is obtained. To generate sufficient data, up to N-2 contingencies and the uncertain parameters associated with the power grid including type and location of disturbance and fault clearing times are modeled. Secondly, the training data-set is produced by generating labels for individual contingencies using a hierarchical clustering method based on rotor angle and speed data. Finally, the dynamic NN models are trained for online applications such as emergency controls and controlled islanding. The proposed method is tested on the standard 16-generator 68-bus system to demonstrate its performance. Furthermore, the impact of the sample data lengths on the CGG numbers is evaluated. It is interesting to observe that the time domain stability behaviors can be determined by examining the changes in the CGG numbers.

The widespread deployment of phasor measurement unit (PMU) across the U.S. together with the burgeoning machine learning technology made it possible to develop data-driven PMU data analytics to improve grid security and reliability in a more insightful and effective manner. Although PMU applications have been explored for over a decade, the representative PMU usage is limited to the bulk power system monitoring mainly due to the data integrity issues associated with PMUs (typically missing, fragmented, and wrongly amplified data). To forge a breakthrough on this stalemate and embrace PMUs for power system control and protection as well, we applied various advanced machine learning and big data analysis technology to the power system event detection and classification as the first step toward the power system control and protection pertaining to grid security enhancement. In contrast to other related work, we capitalized on active power, reactive power, voltage magnitude, and frequency inspired by the system operator's generally monitored measurements and the input of the in-use disturbance recorders, which drastically raised the event detection and classification performance, highlighted in the following five contributions. First, the root of the PMU data integrity issue was addressed, developing an event-participation decomposition model with a novel online SPIKE-P (Stochastic Proximal Implicit Krasulina Event-Participation Decomposition) algorithm, which enables the prompt replacement of missing data with realistic data with the significantly low error between the two data. The same technical challenge was tackled, developing short-term forecasting of PMU data by an advanced attentional sequence to sequence (seq2seq) long term short memory forecast model, which enables us to replace missing data with realistic data even if all PMUs are out-of-service (i.e., all PMU data are missing). Next, three event detection algorithms were individually developed, which enables us to perform 1) the unrivaled search refinement with the spatiotemporal correlation encoding technique, 2) superb (voltage) event signature extraction with the newly invented separation extraction technique from the noise matrix, and 3) event-type-free non-event/event discrimination with no event label, based on the cutting-edge bidirectional generative adversarial network model. All three event detection algorithms can quickly detect the targeted event, which enables us to turn them into an online control and protection. Third, a groundbreaking classifier was produced with an innovative graph signal processing-based PMU sorting algorithm and information loading-based regularization technique, which enables us to 1) differentiate four event types (voltage event, frequency event, oscillation event, and non-event) with a comprehensive visualization, and 2) achieve sufficiently fast event classification (no longer than 2 seconds following events). Additionally, three representative data injection methods (fast gradient sign method, basic iterative method, DeepFool method) are employed to scrutinize the resilience of the aforementioned classifier against a typical cyberattack (i.e., false data injection attack or adversarial attack), which clarifies that subtle noisy signal injection (5-7% amplitude of the attack signal with relative to the original signal) would potentially deteriorate the classifier's performance (i.e., event type classification accuracy) by half. Furthermore, the classifier model trained with the Eastern Interconnection (EI) grid event data was reused to train another classifier model that classifies western electricity coordinating council (WECC) grid events. Another classifier successfully showed enough classification performance for the power system events in the WECC with no training in WECC grid event data, which enables the decrease in the model development task for other bulk power grids. Fourth, a dynamic behavior-based event signature library was designed using a deep neural network-based classifier with an empirical clustering and Shannon entropy, which enables us to 1) facilitate a reliable event signature database with more granular categorization than just voltage, frequency, and oscillation events, 2) effectively showcase how a generic event signature looks like for each categorization in education, and 3) efficiently discover a new type of event signature. Finally, the simulation-free PMU-oriented synthetic data for voltage and frequency events were generated with advanced probabilistic programming methods and deep cascaded convolutional generative models, differentiating between everpresent event signatures and remaining signatures, which enabled us to create highly realistic but artificially fabricated event data that may be used to augment training and testing datasets of supervised learning work such as an event classification. Other than the above, power system dynamic parameters were estimated using a physics-informed neural network, called neural ordinary differential equation, assuming that 1) the grid topology is disclosed, and 2) PMUs are deployed at all substations, which enables us to embed power system dynamic models (e.g., power swing equation) directly into the aforementioned neural network, and to identify unobservable/uncertain parameters, e.g., the grid inertia.

A major objective of this project was to apply GE’s commercial machine learning and data analytics toolsets to large-scale, real-world, anonymized Phasor Measurement Unit (PMU) datasets in order to extract signatures, correlated and/or causal factors, and precursor patterns associated with significant power system phenomena. The project had a particular emphasis on extraction of insights relevant to asset health monitoring, real-time load modeling and cybersecurity monitoring. Additionally, the team was directed to undertake a comprehensive data quality analysis for the provided datasets and encouraged to estimate the ‘machine-learning readiness’ of the datasets by documenting any major obstacles to the application of commercial machine learning algorithms. To accomplish the aforementioned objectives, the project team’s work centered around the identification of key event signatures and application of the identified event signatures for event detection and event classification. The industry-validated, semi-supervised machine learning strategy employed for event signature identification involved several major tasks, including data-preprocessing, generation of an overabundance of features, normal data identification, normality modeling, and event signature identification through a methodical, quantitative ranking of features in order of relevance to each studied event type. Throughout the project, data quality issues and mitigation techniques were investigated. In this report, insights are provided regarding the readiness of the provided synchrophasor datasets for application of machine learning and data analytics. The methodologies employed for this technical strategy are summarized in this report. With regards to data preprocessing and feature generation, the provided Training and Test Datasets were ingested into GE’s big data environment. Subsequently, the team applied bad data cleansing and data imputation scripts, event detection scripts, and application programming interfaces (APIs) to the datasets for convenient data access. The project team completed development and validation of dozens of physics-based, statistics-based and transformation-based feature functions used for the extraction of over 60 synchrophasor features. Using a new parallel feature generation technology developed on this project, over 60 features have been rapidly generated for the full two years’ worth of Training and Test Dataset data associated with both the Eastern and Western interconnects. Even accommodating for temporal down-sampling inherent to the feature extraction procedure, this parallel feature generation activity resulted in a massive feature set with a storage requirement approximately equal to that of the raw training dataset itself. With regards to normal data identification and normality modeling, a normality model was built using the feature data extracted from the Training Dataset and iteratively refined subsequent to incremental adjustments and expansions of the Training Dataset feature data. With respect to event characterization and signature identification, an event signature identification pipeline was developed and used in conjunction with the normality model to identify over 15 event signatures for key event categories within the Training Dataset. The identified event signatures were used to characterize hundreds of key events in terms of relative severity, duration, and location of the event. An investigation was undertaken to identify correlated and causal factors involved in transformer events. A separate investigation into temporal trends in ring-down analysis results was undertaken to determine possible associations between system dynamics and various other factors such as loading, season or year. To validate the identified event signatures, additional work was undertaken to develop signature-based anomaly detection and classification tools suitable for convenient application to the synchrophasor datasets. The anomaly detection and classification tools, suitable for online application, were then applied to the entirety of the Eastern Interconnect Training and Test Datasets. Performance of the event detection and classification tools was evaluated upon receipt of the Test Dataset event logs (i.e., the labels for events contained in the Test Dataset), and promising results were obtained despite several challenges (documented herein) associated with application of supervised or semi-supervised machine learning methods to large-scale, anonymized datasets. Finally, the detection and classification tools were used to detect, classify, and characterize thousands of new events not included in the original event logs provided by the DOE within both the Training and Test Datasets.

This paper addresses the challenge of achieving fast and accurate transient stability analysis and emergency control in power systems, which are crucial for reliable grid operation under disturbances. To this end, we propose a spatio-temporal graph deep learning approach leveraging Diffusion Convolutional Gated Recurrent Units (DCGRUs) for transient stability assessment and coherent generator group prediction. Unlike traditional methods, our approach explicitly represents transient responses as spatio-temporal graph data, capturing both topological and dynamic dependencies. The DCGRU model effectively extracts these features, and the predicted coherent generator groups are incorporated into the single-machine infinite-bus equivalence method to design an emergency generator tripping scheme. Simulation analysis results on both benchmark and real-world power grids validate the proposed method’s feasibility and effectiveness in enhancing transient stability analysis and emergency control.

Modern interconnected power grid requires comprehensive and efficient on-line monitoring system to ensure the reliability and stability of the whole power system. This paper firstly introduces the structure and deficiency of traditional monitoring system. Then, relying on high precision operating parameters collected by Phase Measurement Unit (PMU), an improved on-line monitoring method is proposed, which overcomes the obstacle of existing Wide Area Monitoring System (WAMS) in global analysis of low-frequency oscillation when processing multiple PMU data. This novel method improves the traditional info-exchange and accident-reaction structure between regional and central monitoring station, which assists in the synchronization of oscillation information and coordinated recognition of an accident. Besides, the real-time global identification of inter-area oscillation and coherency grouping are as well ameliorated on considering the geographical location and distance of PMU monitoring stations. This proposed method was applied in the analysis of the Turkish blackout happened on March 2015 which resulted in serious successive degradation of frequency in European power grid. Signals measured in representative monitoring stations with PMU equipment locating Continental Europe (CE) were used to establish detailed and global analysis of the accident, including the warning of oscillation, the propagation trend and the identification of the inter-area oscillations. Based on this practical application in on-line monitoring case, the effectiveness and sensitivity of the proposed method are discussed at the end of the paper.

Banking is an important industry, where financial transactions are performed to meet our needs in our everyday lives. Today, banks are frequently used to meet all kinds of financial transactions. In line with the increasing competition, the banks are aiming at acquiring new customers through customer satisfaction. At this point, studies on acquiring new customers by analyzing the customer data have gained importance recently. As a result, data analysis units have been established in the banks. In addition to the banks, these units have also been established for data analysis in customer focused industries such as insurance and telecommunication. In this study, models are established by using classification algorithms to estimate potential bank customers on the bank dataset obtained by telemarketing method in UCI Machine Learning Repository, and the results are compared. Using this comparison result, it is aimed to perform a more detailed and effective data analysis. Various models have been established with various classification algorithms for the estimation of customer acquisition. The classification algorithms used in this study include the C4.5 Decision Tree, Navie Bayes (NB) algorithm, K nearest neighbors algorithm (k-nn), Logistic Regression algorithm (LogReg), Random Forest algorithm (RanFor), and Adaptive Boosting algorithm (AdaBoostM1-Ada). While establishing the classification models, it is aimed to achieve consistency in the performance of the classification models by dividing the test and training data set by two different methods. K-fold Cross Validation and Holdout methods are used for this purpose. In the K-fold cross validation, training and test da-ta sets are separated with 5- and 10-fold cross validation. In the holdout method, the dataset was divided into training and test datasets with the 60–40%, 75–25% and 80–20% training and test separation ratios, respectively. These separations are evaluated for Accuracy (ACC), Precision (PPV), Sensitivity (TPR), and F-measure (F) performance. The performance results are similar in both separation results. According to the Accuracy and F-measure criteria, the classification model established by Random Forest algorithm highest results the other models, whereas the Naive Bayes algorithm gave highest results according to the precision criterion, and the AdaBoostM1 classification algorithm yielded better according to the sensitivity criterion.

Since phasor measurement units (PMU) were invented, there has been growing interest in developing methodologies for improving monitoring, protection and control of power systems in real time. In this study, the authors propose a new methodology, based on graph modelling, to identify coherent groups of generators in a real‐time fashion. The coherent groups are identified with instantaneous values measured from the system through PMUs, and the methodology needs neither setting the number of desired groups nor defining a threshold value since it is based on coupling factors between generators. Moreover, it is proposed a new method for the online definition of areas for islanding when this action is required as the latest emergency control method. The methodology assigns the non‐generation buses to the previously found generators coherent groups considering three criteria: electrical distance to the group of generators, topology, and operational constraints, which are verified by mean of an optimal power flow. The methodology is tested on the IEEE 39‐bus and IEEE 118‐bus test systems. Results show that the real‐time identification of coherent groups and the definition of areas allow the development of islanding strategies with promising results.

A new approach for online coherency identification in power systems based on correlation characteristics of generators rotor oscillations

Since the aspect of instability phenomena during midterm is complicated, the stability analysis is significant in order to keep the power system stable. Synchronized phasor angles obtained by the PMU (phasor measurement unit) provide the effective information for evaluating the stability of a bulk power system. This paper proposes a midterm stability evaluation method of the wide-area power system by using the synchronized phasor measurements. Clustering and aggregating the power system to some coherent generator groups, the stability margin of each coherent group is quantitatively evaluated on the basis of the one machine and infinite bus system. The midterm stability of a longitudinal power system model of Japanese 60 Hz systems constructed by the PSA (Power System Analyzer), which is a hybrid-type power system simulator, is practically evaluated using the proposed method.

Multichannel continuous wavelet transform approach to estimate electromechanical oscillation modes, mode shapes and coherent groups from synchrophasors in bulk power grids

This paper presented a reduced-order method for swing mode eigenvalue calculating based on fuzzy coherency recognition. First, we recognize the coherent generator groups using the fuzzy clustering method. Then we aggregated the generators in a coherent group into a single equivalent generator that the dimension of the state equation reduced evidently. Using QR algorithm to the reduced-order state equation we calculated the eigenvalues of the inter-area mode. The eigenvalues of local mode calculated by using QR algorithm to the sub-state matrices corresponding to the coherent groups separately. Thus, all eigenvalues of swing mode can be calculated. We have given detailed results of both the coherent generator groups recognition and the eigenvalues calculating of the 10-machine New England power system. The results shows that the method for eigenvalue calculation is simple and practical.

The coherent generator groups identified method was proposed via Empirical Mode Decomposition (EMD) and Stochastic Subspace Identification (SSI) method in this paper. Only the generator rotor speed gathered from the Wide Area Measurement System (WAMS) is used in the proposed method, and the detailed model and parameters of power system components are not needed. And the phase diagram obtained by using the SSI was employed in the proposed method to identify the coherent generator groups. At the end, the simulation was tested on the CEPRI system with 8-generator. The results of test system testify the efficiency of the proposed method.

Situational awareness of coherency behavior of synchronous generators in a power system with utility-scale photovoltaics