Transient Stability Evaluation Research Articles

A probabilistic distributed digital twins approach for short-term stability and islanding of smart grid

The simultaneous evaluation of voltage, frequency, and transient stability enhances the reliability of the power systems, due to the transient effect of stability aspects on each other. However, different quantitative and qualitative parameters in the aspect and nonlinear structural analysis of the system make simultaneous and accurate predictions difficult. For this reason, the simultaneous probabilistic prediction of the stability state of three aspects with high certainty can be considered the most accurate method. This study presents a simultaneous prediction method for the stability aspect states by means of the decision theory and the game theory matrix on the basis of distributed digital twins (DDTs). The decision matrix weighs the aspect states in each bus using the distributed structure measurement and prioritizes the weak buses. In addition, the stability of different bus aspects is predicted using the game matrix. Furthermore, the changes in the system stability are predicted with high probability and certainty in the digital twins (DTs) graph, and if required, islanding is performed on the basis of the weak buses' priorities. The effects of the three aspects on each other, and the use of real-time data of the DDTs, have contributed to the high accuracy and speed of the proposed method. Simulations were performed on IEEE 14-bus, 39-bus, and 118-bus systems by means of MATLAB and DIgSILENT. The results show the advantages of the proposed method over other methods.

Integrated algorithm evaluation of a scalable digital power management innovation model

Maintaining contemporary society’s steady progress depends on the reliable functioning of the electrical grid. The complexity and nonlinearity of today’s power networks make it difficult to manage them using conventional mathematical modeling approaches. To get around these problems, researchers have started using machine learning methods, such transient stability evaluation that is based on machine learning. This research suggests a way to evaluate the transient stability of power systems by making use of the complex feature extraction capabilities of multi-layer perceptron (MLP) networks. Another approach is to suggest an ensemble learning model that uses the easy-ensemble undersampling technique to deal with power system transient stability data that is unbalanced. This method preserves unstable power system samples, performs multiple undersampling on stable samples and combines unstable and undersampling samples into multiple new balanced training sets for MLP model training. The final ensemble model is obtained through voting integration strategy. Through conducting a comparative evaluation of individual models and ensemble models, this paper discovers that the ensemble learning models exhibit superior sensitivity and accuracy in effectively addressing system instability.

Data-Driven Transient Stability Evaluation of Electric Distribution Networks Dominated by EV Supercharging Stations

Data-Driven Transient Stability Evaluation of Electric Distribution Networks Dominated by EV Supercharging Stations

Transient Stability-Constrained Unit Commitment Using Input Convex Neural Network.

This article proposes a transient stability-constrained unit commitment (TSC-UC) model using input convex neural networks (ICNNs). An ICNN is trained to learn the transient function that maps prefault operation conditions (e.g., generator power output) to the transient stability index (TSI), which can be further utilized to identify the transient status (e.g., stable or unstable). Transient stability evaluation is conducted using the learned ICNN, without discretizing differential-algebraic equations (DAEs) or interacting with the time-domain simulation tools. Based on the convexity of ICNNs, the trained ICNN is exactly encoded as a linear programming (LP) model and integrated into conventional UC models to form a TSC-UC model. To impose transient stability constraints and expedite the solution process, the proposed TSC-UC model is decomposed into a UC master problem and two subproblems (i.e., network feasibility check subproblems and transient stability check subproblems). The decomposed problem is then iteratively solved using the Benders decomposition. Simulation tests are conducted in the New England 39-bus test system and IEEE 118-bus test system to verify the validity of the proposed approach.

A robust transient energy function‐based controller for enhancing transient stability of virtual power system

AbstractThis paper offers non‐linear control for enhancing the transient stability in power systems containing a photovoltaic (PV) and doubly fed induction generator (DFIG) by transient energy function (TEF) method and finite‐time observers. At first, the TEF method is utilized to enhance the transient stability in a power system containing a PV, DFIG, and synchronous generator (SG) by constructing a hybrid Lyapunov function. Then, the derivative terms in control are estimated with finite‐time observers. The main contribution of the research is the application of the TEF technique in the transient stability evaluation of a power system consisting of PV, SG, and DFIG. Another innovation of the research is the simultaneous control of DFIG and PV, whose uncertain parameters are estimated with the use of finite‐time observer. The proposed non‐linear control scheme is robust against changes in the configuration of the power system. In order to show the capability of this control scheme, time domain simulations are performed on the IEEE 9‐bus, and the NEW ENGLAND Standard 39‐Bus power system. Using the obtained result, some comparisons are made with the back‐stepping control scheme to clarify the superiority of the proposed method. The comparisons show that the proposed non‐linear control scheme can properly provide extra damping to reduce the first‐swing fluctuations in less time.

Multi-task transient stability assessment of power system based on graph neural network with interpretable attribution analysis

Transient power angle stability analysis and voltage stability analysis are the key basis of power system security and stability control. The diversified operation modes of power system put forward higher requirements for real-time and topology generalization of transient stability assessment. Based on Convolution Neural Network (CNN) and Graph Attention Networks (GAT), this paper uses the wide-area transient response features to evaluate the transient angle stability and voltage stability of power system. Firstly, CNN is used to encode the temporal variation characteristics of transient features of electrical components in hidden layer space. Secondly, the encoded hidden layer features are mapped into graph data samples according to the spatial topological correlation of electrical components, so as to train and build a multi-task transient stability assessment model based on GAT. The model can adaptively capture the interaction relationship between encoded hidden layer features of topologically correlated components, and realizes real-time evaluation of transient angle stability and transient voltage stability by perceiving the temporal–spatial correlation of transient features. Finally, Shapley additive explanation (SHAP) method is used to explain the decision-making mechanism of the model and extract the key features that affect the transient stability, so as to enhance the ability of power grid operators to perceive the transient stability situation. The results of IEEE-39 system show that the transient stability assessment model has good accuracy and topology generalization, and the results of interpretable analysis are in line with the conclusions of traditional mechanism cognition, which helps to improve the credibility of the model results.

Research on Fault Diagnosis and Transient Stability Evaluation of Power System Based on Machine Learning

Research on Fault Diagnosis and Transient Stability Evaluation of Power System Based on Machine Learning

SVM based imbalanced correction method for Power Systems Transient stability evaluation

Due to the requirement of safety and reliability in power systems, unstable samples in the real system are rarely appeared. The evaluation results of the model trained by these imbalance samples have a certain preference. Generally, the imbalance in quantity is taken into account, while the imbalance in quality is ignored. Faced with such a problem, an imbalanced correction method based on support vector machine (SVM) is proposed. Firstly, the classification hyperplane trained by SVM and the normalized Euclidean distance between each sample and the classification hyperplane are calculated so as to obtain their fault severity. Based on this, training samples can be grouped to multilevel sets. Then, the original stacked sparse auto-encoder (SSAE) are pretrained to quantify the imbalance between two classes of samples in multilevel sets. Subsequently, in order to improve the imbalance of training samples, a cost-sensitive correction matrix is generated according to the imbalanced information of multilevel sets. Finally, the loss function of SSAE is modified by cost-sensitive correction matrix to establish the final classifier. Simulation results in IEEE 39-bus system and the realistic regional power system of Eastern China show the high performance of the proposed imbalanced correction method.

Transient voltage stability assessment of renewable energy grid based on residual SDE-Net

For the purpose of assessing the transient voltage stability of renewable energy grid more effectively and to measure the epistemic uncertainty of the evaluation results, a power system transient voltage stability assessment method based on residual stochastic differential equation network (SDE-Net) is proposed in this paper. Considering the transient stability characteristics is chronological, the proposed network takes the time series of the basic physical quantity measurement data of the power system as the input. The internal features of time series data are extracted by residual convolution block based stochastic differential equation network in this paper. Meanwhile, the proposed method introduces the focal loss function to eliminate the imbalance of the samples and improve the accuracy of transient stability assessment. In particular, the drift network for learning prediction of stability and the diffusion network for learning uncertainty measurement in residual SDE-Net are trained respectively. As a result, case study on modified IEEE 30- bus system demonstrate the residual SDE-Net’s superior performances on both transient voltage stability assessment and stability evaluation result confidence estimation.

A risk-based machine learning approach for probabilistic transient stability enhancement incorporating wind generation

ABSTRACT Power systems are becoming more complex than ever and are consequently operating close to their limit of stability. Considering its significance in power system security, it is important to propose a novel approach for enhancing the transient stability, considering uncertainties. Current deterministic industry practices of transient stability assessment ignore the probabilistic nature of variables. Moreover, the time-domain simulation approach for transient stability evaluation can be very computationally intensive, especially for a large-scale system. The impact of wind penetration on transient stability is critical to investigate, as it does not possess the inherent inertia of synchronous generators. Thus, this paper proposes a risk-based, machine learning decision-making approach, for probabilistic transient stability enhancement, by replacing circuit breakers, including the impact of wind generation. The IEEE 14-bus test system was used to test and validate the effectiveness of the proposed approach. DIgSILENT PowerFactory and MATLAB were utilised for transient stability simulations (for obtaining training data for machine learning), and applying machine learning algorithms, respectively.

Prediction of probabilistic transient stability using support vector regression

ABSTRACT The increasing uncertainty in power systems has brought various challenges, including transient stability assessment. The conventional approaches, such as, time-domain simulation approach and direct method (based on Lyapunov function and transient energy function), to estimate the transient stability are not appropriate for online application, as they suffer from various drawbacks of large computation time (time-domain simulation) and delivering approximate results (direct method). The field of machine learning and soft computing provides a good alternative to the conventional approaches, for transient stability evaluation. Thus, this paper aims to discuss the application of support vector machine (SVM) for predicting the probabilistic transient stability. DIgSILENT PowerFactory was utilised for conducting time-domain simulations (to obtain the training data), and MATLAB was used for support vector regression (SVR) training. For the SVR model, fault type, fault location, fault clearing time, and system load were chosen as the predictors and the transient stability index (TSI) was used as the response. Various regression metrics were computed, for the IEEE 14-bus system, to validate the effectiveness of the proposed approach. The results obtained verify the efficiency of the proposed approach and provide a great potential to be applied for online dynamic security assessment (DSA).

Application of supervised machine learning for prediction of probabilistic transient stability

ABSTRACT Evaluation of transient stability is integral to dynamic security assessment of power systems. It deals with the assessment of the ability of the system to remain in equilibrium for large disturbances, such as faults. Deterministic approaches for transient stability assessment are becoming unsuitable, considering the rising uncertainties. Moreover, due to its intensive computation effort, the conventional time-domain approach for transient stability assessment is not appropriate for online application, thereby motivating the requirement to apply a soft computing technique. Thus, this paper investigates artificial neural network-based supervised machine learning, for predicting the transient stability of a power system, considering uncertainties of load, faulted line, fault type, fault location, and fault clearing time. The training of the neural network was accomplished using suitable system features as inputs, and probabilistic transient stability status indicator as the output. Results obtained for the IEEE 14-bus test system demonstrated that the proposed method offers a fast technique for probabilistic transient stability prediction with a superior accuracy, and thereby, signifying a strong possibility for neural network application in dynamic security assessment. DIgSILENT PowerFactory and MATLAB was utilised for transient stability time-domain simulations (for obtaining training data for the neural network), and for applying supervised machine learning, respectively.

Power system transient stability assessment based on rough set and deep residual neural network

Machine learning algorithms have been widely used in power system transient stability evaluation. The combined application of data analysis and evaluation and neural network provides a new direction for power system transient stability analysis. After the actual power grid is running, there is obviously an imbalance between stable samples and unstable samples. The current deep learning network realizes the power system transient stability assessment method with too many redundant attributes, and the characteristics will inevitably be lost during the data transmission process. This leads to serious problems with the tendency of the training of the data-driven transient stability assessment model. The rough set theory algorithm is introduced to reduce the redundant attributes of power system transient data sets, which simplifies the difficulty of data training. At the same time, as the neural network deepens, the deep residual neural network model has a higher accuracy rate and effectively avoids the “gradient explosion” and “gradient dispersion” problems. Compared with the traditional neural network, it has better Evaluate performance.

Power Grid Safety Assessment Based on an Improved Generative Adversarial Network

Critical clearing time (CCT) is one of the important indices for transient stability evaluation. From the data-driven perspective, the research on CCT prediction is troubled by changing models and insufficient samples, that is, the small sample characteristics of the target system may be submerged by the large sample characteristics of the source system. In this paper, a prediction method of CCT based on improved generative adversarial network (WGAN) is put forward to solve this problem, and the network structure of WGAN is redesigned. This method is suitable for the transition phase of power grid when the operation mode changes. Through the unsupervised training of WGAN, the neural network will automatically learn the complex relationship between the small sample data of the target system, so that the generator can produce small sample data with high precision. Then the CCT prediction model was built on the expanded balanced dataset. Results validate that the method can effectively learn the distribution law of samples, improve the CCT prediction ability, and has the advantage of precision in the transition phase of power grid with insufficient samples.

Renewable energy power system transient stability analysis and assessment

In this paper, in-depth analysis, and evaluation of the transient stability of a renewable energy power system are carried out, and a transient stability evaluation method based on stacked autoencoders is proposed. The method breaks through the traditional two-stage evaluation mode. The method proposes a deep network model with a multi-branch structure for different physical natures of different measured data. With the help of different sparse denoising coding networks (branches), features are extracted from each measurement separately and fused on top of the model to finally complete the transient stability assessment. The simulation results show that the method can effectively handle the simultaneous input of multiple measurements, and has the advantages of high accuracy and robustness in noisy environments. To effectively determine the model hyperparameters, the orthogonal test is used for model selection, which can significantly reduce the hyperparameter seeking space and save computational resources. The simulation results show that the method can effectively use multiple measurements to improve the accuracy of wind power prediction. Also, the input variable selection index based on mutual information can provide a good guide for further improvement of model performance.

Transmission Hosting Capacity of Distributed Energy Resources

Distributed energy resources (DERs) are transforming the operation and planning of both distribution and transmission grids. Stability impacts from the increasing generation contribution of DERs have been widely recognized in distribution systems and are emerging in transmission systems. There is a need for the development of transmission hosting capacity studies of DERs so utilities will be able to predict and prevent instabilities, reductions in reliability on the electrical grid, and create planning methodologies that enable the continued growth of DERs. This paper evaluates the impact of different modeling considerations for assessing hosting capacity of DERs in transmission systems through analysis on a 2,000-bus synthetic grid test system. The modeling considerations include transient and steady state contingencies, use of dynamic load and DER models with voltage support control, dynamic load composition, and seasonal and loading scenarios. The results demonstrate that transient stability evaluations are more limiting than steady state analysis, the use of voltage support control in DERs can increase hosting capacity in the system, and large variations in hosting capacity can be found when assessing between seasonal variations. From comparing system factors the amount of wind generation in the system was a critical factor for hosting capacity in this study.

Transient stability evaluation model based on SSDAE with imbalanced correction

With the rapid development of machine learning technology, a new tool is provided for real-time stability evaluation in power systems. The training of a machine learning-based model is inseparable from a large number of training samples. However, compared with stable samples, unstable samples in power systems are infrequent. The results of the model evaluation are biased due to the imbalance of training samples. Faced with such a problem, a framework based on deep imbalanced learning is proposed. Firstly, for each sample, the samples nearby in the opposite class are applied to calculate its space information. Based on the space information of all samples, the spatial distribution characteristics of the training samples are obtained. And then, in order to obtain balanced training samples, unstable samples are generated according to their spatial distribution characteristics. Finally, stacked sparse denoising auto-encoder (SSDAE) based model, which has the ability of anti-noise, is established as the classifier. Simulation results in IEEE 39-bus system show the high performance of the proposed imbalanced correction scheme and evaluation scheme.

An enhanced approach for probabilistic evaluation of transient stability

Due to the high penetration of renewable energy resources leading to the enhancement of uncertainty, the probabilistic assessment of the transient stability has become more important than deterministic assessment. In a previous method published by the authors, an algorithm to find the probability density function of the transient stability margin of the power system was published. This present paper presents a modified algorithm to find the probability density function of critical clearing time for each generator for the whole power grid for a certain contingency and during the fault-on period. First, the critical corrected kinetic energy is calculated based on a modified sensitivity-based algorithm at each step of the simulation during the fault-on period. Since the total kinetic energy of the generators does not contribute in the critical kinetic energy of the whole system, a new criterion - based on the rate of change of kinetic energy - is utilized to classify severely disturbed generators from less disturbed generators. Utilizing critical corrected kinetic energy of the whole power grid, an index based on the critical clearing time, so-called network critical clearing time, is calculated. Eventually, the proposed algorithm is applied on the optimal placement of a superconducting magnetic energy storage unit. It is shown that utilizing the proposed objective function for locating superconducting magnetic energy storage units effectively results in the improvement of the transient stability margin of the power system.

Research on Power System Performance Evaluation Based on Machine Learning Technology

Power systems often suffer from various large disturbances during operation, especially grounding and short-circuit faults of operating lines, which may lead to transient instability of the system. In view of the fact that the existing relay protection is difficult to be fully applied to the power system with high permeability distributed energy, the machine learning algorithm is applied to the relay protection of the power system. Enhance the robustness of the model to noise; In the training, more weight is given to the unstable samples to balance the influence caused by the difference in the number of samples. In addition, a regular term is introduced into the loss function to control the complexity of the model and reduce over-fitting, thus adapting to various operating conditions of the power system. By comparing the difference between measured data and estimated data to detect bad data, the machine learning method is more intelligent than the traditional method. The research results show that the transient stability evaluation method based on incremental learning of support vector machine greatly reduces the learning time while maintaining the evaluation performance, and is a promising online learning algorithm for transient stability evaluation.

An Evaluation of Flux-Coupling Type SFCL Placement in Hybrid Grid System Based on Power Quality Risk Index

Due to the expansion of restructured electricity markets and consequently power network operation approaching dynamic and static margins, the probability of transient instability has remarkably been increased. To reduce the transient instability risk or probabilistic cost of power quality, the present study focuses on determining the optimum location of a flux-coupling type SFCL. To this end, the candidate locations with lower related transient instability risk are selected as the best locations for installing flux-coupling type SFCLs. Nowadays, the type of SFCL employed in this study, which enjoys the benefits of both resistive and inductive type SFCLs, is a suitable means for enhancing the transient stability of electrical grids. Despite being another useful approach in transient stability evaluation, the equal-area criterion is merely restricted to the analysis of the stability of a single-machine power system connected to an infinite bus and also a two-machine power system. The online approach employed in this study is based on the corrected transient energy margin (CTEM), some probabilistic factors, and the cost of transient instability. Furthermore, CTEM index is a useful tool for calculating the critical clearing time (CCT). Therefore, in recent years, this index has become more and more useful. The studies carried out on the IEEE New England 39-bus test system ascertain the high applicability of the proposed method.