Dynamic Security Assessment Research Articles

An integrated scheme for dynamic security assessment considering misclassification constraint based on umbrella Neyman-Pearson classifiers

Power system is one of the most complex dynamic industrial systems with the continuous expansion of the system scale and extensive application of phasor measurement units (PMUs). Dynamic security assessment (DSA) misclassification of the system will bring unpredictable consequences. Therefore, an integrated scheme for DSA that considers misclassification constraint is proposed in this paper to satisfy practical applications. The scheme includes a feature selection process and a DSA model, which are based on the bagging nearest-neighbor prediction independence test (BNNPT) and umbrella Neyman-Pearson (NP) classifiers, respectively. The BNNPT can explore the relationships between variables and the dynamic security index (DSI) to screen out the crucial features highly related to the DSI. By controlling the Type I error threshold and the cyclic split training mode, umbrella NP classifiers can effectively constrain Type I error, reduce the effect of misclassification, and improve DSA for the secure operation of the system. The performance of this integrated scheme is demonstrated through tests on the IEEE 39-bus system and a practical 500-bus system.

Monitoring of the power system load margin based on a machine learning technique

The voltage stability margin is an important load margin measure used in power system operating centers to prevent a voltage collapse. However, oscillatory problems that arise with increasing load can also compromise the performance and stability of the power system. Thus, it is essential to determine a load margin that meets the requirements for voltage stability and small-signal stability in dynamic security assessment. This article proposes to use a artificial neural network, a supervised machine learning technique, to predict the load margin range of the power system considering the requirements of voltage stability and small-signal stability and using data of electrical quantities of certain buses that have a phasor measurement unit. A direct method based on a power systems model that determines the load margin meeting the voltage and small-signal stability requirements will be applied to generate the database for the training and testing stages of artificial neural network. The sequential forward selection algorithm was used in this research to select the buses to have a phasor measurement unit. Case studies are presented and discussed to verify the proposed load margin monitoring system based on artificial neural networks.

A Confidence-Aware Machine Learning Framework for Dynamic Security Assessment

Dynamic Security Assessment (DSA) for the future power system is expected to be increasingly complicated with the higher level penetration of renewable energy sources (RES) and the widespread deployment of power electronic devices, which drive new dynamic phenomena. As a result, the increasing complexity and the severe computational bottleneck in real-time operation encourage researchers to exploit machine learning to extract offline security rules for the online assessment. However, traditional machine learning methods lack in providing information on the confidence of their corresponding predictions. A better understanding of confidence of the prediction is of key importance for Transmission System Operators (TSOs) to use and rely on these machine learning methods. Specifically, from the perspective of topological changes, it is often unclear whether the machine learning model can still be used. Hence, being aware of the confidence of the prediction supports the transition to using machine learning in real-time operation. In this paper, we propose a novel Conditional Bayesian Deep Auto-Encoder (CBDAC) based security assessment framework to compute a confidence metric of the prediction. This informs not only the operator to judge whether the prediction can be trusted, but it also allows for judging whether the model needs updating. A case study based on IEEE 68-bus system demonstrates that CBDAC outperforms the state-of-the-art machine learning-based DSA methods and the models that need updating under different topologies can be effectively identified. Furthermore, the case study verifies that effective updating of the models is possible even with very limited data.

A machine-learning based probabilistic perspective on dynamic security assessment

Probabilistic security assessment and real-time dynamic security assessments (DSA) are promising to better handle the risks of system operations. The current methodologies of security assessments may require many time-domain simulations for some stability phenomena that are unpractical in real-time. Supervised machine learning is promising to predict DSA as their predictions are immediately available. Classifiers are offline trained on operating conditions and then used in real-time to identify operating conditions that are insecure. However, the predictions of classifiers can be sometimes wrong and hazardous if an alarm is missed for instance.A probabilistic output of the classifier is explored in more detail and proposed for probabilistic security assessment. An ensemble classifier is trained and calibrated offline by using Platt’ scaling to provide accurate probability estimates of the output. Imbalances in the training database and a cost-skewness addressing strategy are proposed for considering that missed alarms are significantly worse than false alarms. Subsequently, risk-minimised predictions can be made in real-time operation by applying cost-sensitive learning. Through case studies on a real data-set of the French transmission grid and on the IEEE 6 bus system using static security metrics, it is showcased how the proposed approach reduces inaccurate predictions and risks. The sensitivity on the likelihood of contingency is studied as well as on expected outage costs. Finally, the scalability to several contingencies and operating conditions are showcased.

Dynamic Security Assessment Method of Power System Based on Improved XGBoost

With the deployment of wide-area measurement systems (WAMS) equipment, dynamic security assessment (DSA) based on artificial intelligence (AI) has more and more advantages. For the power system, the number of transient stable cases is much larger than that of unstable cases, which leads to insufficient learning of unstable cases and affects the evaluation effect of the model. In addition, during the stability assessment process of the power system, the misjudgment cost of unstable case is much higher than that of stable case. Based on the above two points, we proposed a DSA method of power system based on improved XGBoost. The proposed method introduces the weight adjustment factor into the loss function to balance the quantity variance of two type cases and the difference of misjudgment cost, which greatly reduces the misjudgment rate of unstable samples. The test results on IEEE 16-machine 68-bus test system and IEEE 50-machine 145-bus test system show that the proposed method can have higher recognition of the unstable samples and can be applied to DSA.

Single Value Decomposition to Estimate Critical Clearing Time of a Power System Using Measurements

The transient stability analysis of large-interconnected power systems using time-domain simulations (TDS) is a significant challenge since it represents a huge computational cost. Besides, for dynamic security assessment is required have a quick response. Consequently, recent approaches are relying on using the wide-area measurement system combined with other techniques to perform transient stability assessment and counteract the drawbacks of the TDS method. However, these approaches still requiring to perform TDS to set initial parameters. This paper proposes a new algorithm to estimate the critical clearing time (CCT) based on the eigenvalue calculation and the singular value decomposition using data from wide-area measurement systems. The proposed algorithm uses the phase angles of the voltage phasors measurements at the generation buses to represent the dynamics of the internal angles of the generators. First, from a set of signals, a measurement matrix is formed using a sliding window. Then, a threshold based on the maximum singular value and the dominant eigenvalue of the measurement matrix are computed. Finally, the CCT is estimated using the dominant eigenvalue (the most energetic eigenvalue) and the threshold. The proposed algorithm is evaluated using the Kundur four-machine system and New England 39-Bus system. Its performance contrasts to the CCT calculated using the classical TDS. The simulation results demonstrated acceptable precision of the CCT against TDS. Also, it presents robustness against the effect of the noise in the measurements. Therefore, it is suitable for online applications.

저 차원 Hankel 구조를 이용한 PMU 데이터 복구에 관한 연구

Phasor Measurement Units (PMUs) provide synchronized phasor measurements at much higher sampling rate than that in the traditional Supervisory Control And Data Acquisition (SCADA) system. Several synchrophasor-based algorithms and techniques have been and continue to be developed for real-time operation applications such as state estimation, stability analysis, disturbance detection, dynamic security assessment etc. However, synchrophasor data quality limits the incorporation of synchrophasor-based applications into control room operations environment and processes. The goal of this project is to develop methods that can improve synchrophasor data quality by recovering missing data reliably and efficiently. Data recovery refers to methods that estimate the values of missing data in the synchrophasor streams. Recently, modeless missing data recovery methods have been developed, that exploit the low-rank property of the spatial-temporal synchrophasor data blocks. A spatial-temporal synchrophasor data block can be considered as a matrix that is constructed by the measurements sampled at consecutive time instants with each row denoting the measurement of one certain channel across time. By exploiting the low-rank property of synchrophasor data matrices, the missing data recovery can be formulated as a low-rank matrix completion problem. The low-rank matrix completion problem has been extensively studied in the past few years and several algorithms have been developed to recover a low-rank matrix from partial observations. In this study, synchrophasor data analysis has been combined with low-rank matrix completion theory to develop a missing synchrophasor data recovery technique and tool.

A Bayesian Learning Based Scheme for Online Dynamic Security Assessment and Preventive Control

In this paper, a two-stage Bayesian learning-based approach is proposed to enable online dynamic security assessment (DSA) and preventive control in power systems. To develop a reliable data mining-based model for DSA, the Bayesian neural network is learned by Bayes by Backprop to detect the security status in real-time and to inform the system operators with the confidence of the prediction. For dynamic insecurity prevention, the security-constrained optimal power flow (SCOPF) model incorporating the Bayesian neural network based security constraints is proposed, which is solved by the derivation-free Bayesian optimization. Case studies on the IEEE 39-bus system show that the Bayesian neural network is able to detect the security status of the power system correctly and reliably and is able to avoid the over-fitting problem compared with the traditional point estimation neural network. Also, Bayesian optimization is able to solve the non-analytical SCOPF model efficiently to mitigate the dynamic insecurity by preventive generation rescheduling.

Online dynamic security assessment of wind integrated power system using SDAE with SVM ensemble boosting learner

The increasing trend of decarbonization, particularly high penetration of wind power generation (WPG), has resulted in an increased operational uncertainty of the power system. This emerging trend of wind integration requires novel and effective methods of power system security assessment. This paper proposes a method for dynamic security assessment (DSA) based upon stacked de-noising auto-encoder (SDAE) using support vector machine (SVM) ensemble with boosting learning approach. A two-step feature reduction method is introduced after screening the redundant features among original feature set using mutual information theory. Multi-level features of original input data are extracted using multi-layer SDAE. SVM ensemble classifier is used to perform classification with data from all hidden layers of SDAE. The output of multi-layer SDAE and SVM ensemble are combined together as an input to ensemble boosting learning method which gives the final DSA result. The proposed method is tested on modified New England 39 bus system and extended on simplified AC/DC hybrid power system of Shandong province, China. The effectiveness and accuracy of the proposed method is demonstrated by simulation results and by comparisons with other methods.

Dynamic security regions in power systems with active overexcitation limiters

This paper analyzes the impact of active overexcitation limiters (OELs) on the dynamic security assessment of power systems, with focus on transient stability. The analysis is concentrated on dynamic security regions evaluation, considering different OELs types, including the takeover and summed ones. Initially, the importance of the OEL modelling is exemplified in a study carried out on the Brazilian Interconnected Power System, where the OEL activation results in a significant transfer capability limitation. After that, the work explores the development of dynamic security regions in the IEEE New England system, showing how these regions can be distorted depending on the OELs representation.

Certification and prediction of post-disturbance states in dynamic security assessment

Dynamic security assessment usually involves the simulation of system dynamics under large disturbances. The instant large disturbance occurs, the post-disturbance state of the system could deviate significantly from the pre-disturbance one. It is desirable and necessary to develop an efficient method to certify the existence of state and predict the approximate post-disturbance state because: (1) faster warning can be made in online assessment; and (2) the dynamic simulator can be given better initial values to calculate precise solutions, which prevents convergence failure brought on by poor initial values. We propose a novel approach for efficiently certifying and predicting the post-disturbance states in dynamic security assessment. Based on the fixed-point power flow mapping approach applied to salient pole generator models, the criterion for determining the existence and uniqueness of the post-disturbance solution is derived, and the bounds of post-disturbance solution can be rigorously characterized.

A data-driven approach for online dynamic security assessment with spatial-temporal dynamic visualization using random bits forest

With the continuous expansion of the power system scale and extensive application of phasor measurement units (PMUs), the secure operation of power systems has been increasingly concerned. To construct an efficient dynamic security assessment (DSA) model and make it convenient for practical applications, an integrated framework for online DSA with spatial-temporal dynamic visualization is proposed in this paper. The proposed framework consists of DSA model based on random bits forest (RBF) and spatial-temporal dynamic visualization. By using a feature selection process based on the bagging nearest-neighbor prediction independence test (BNNPT) and Pearson correlation coefficient (PCC), the key features are selected for model training. Once the real-time PMU data from the wide area measurement system (WAMS) are received, the trained DSA model can rapidly provide the corresponding transient stability margin (TSM). Particularly, the spatial-temporal dynamic visualization is presented to describe the quickly captured dynamic security information. The encouraging performance of the framework is demonstrated by tests on a 23-bus test system and a practical 1648-bus system. Especially, some impact factors that influence the practical operation of power systems are considered in the robustness examination, including variations of the topology, power distribution among generators/loads, peak/minimum load and load characteristics.

An Integrated Scheme for Online Dynamic Security Assessment Based on Partial Mutual Information and Iterated Random Forest

With the continuous expansion of the power system scale and extensive application of phasor measurement units (PMUs), the secure operation of power systems has been increasingly concerned. In this paper, an integrated scheme for online dynamic security assessment (DSA) based on feature selection and regression prediction is proposed. First, partial mutual information (PMI) and the Pearson correlation coefficient (PCC) are used to select the key variables in the feature selection process. Second, an iterated random forest (IRF) is applied to predict the transient stability margin (TSM) based on the selected variables. Combining the feature selection process and regression prediction, a DSA model is constructed. Finally, a spatial-temporal dynamic visualization approach is proposed, which can intuitively provide real-time dynamic security information of power systems. The integrated scheme, which is tested on the IEEE 39-bus system and a practical 1648-bus system provided by the software PSS/E, exhibits desirable assessment accuracy and is suitable for online application. In the robustness test, some impact factors for power system operation are considered, such as topology change, variation of generator/load power distribution and variation of load characteristics. Moreover, the impacts of missing data and measurement noise are studied.

Incremental broad learning for real‐time updating of data‐driven power system dynamic security assessment models

This work aims to real-time update the data-driven dynamic security assessment model for accuracy maintenance and improvement. Based on the random vector functional link neural network, an incremental broad learning model is developed as an alternative and much faster approach for deep learning. Besides, the proposed method can significantly reduce the computation burden caused by abundant model parameters of layers and filters. Three real-time increment scenarios are achieved: enhancement hidden nodes, features, and training instances. Distinguished from existing methods, the proposed method can fast remodel in broad expansion without retraining the whole model, since it can only calculate the pseudoinverse of new state matrix without the computations of the whole output weights matrix. Numerical simulation results show that the proposed method can improve the accuracy step by step and update the model within a very short time at the online stage, verifying its real-time computational efficiency and accuracy improvement.

Development of an Ensemble Decision Tree-Based Power System Dynamic Security State Predictor

Real-time assessment and prediction of dynamic security plays an important role in power systems operation and control. Analysis of the current operating state and prediction of plausible future insecurity is crucial for real-time decision-making and implementation of necessary control strategies to ensure secure operation of bulk power systems. On-line security assessment demands low complexity and computational time. The traditional methods of assessment of dynamic security of electric power systems often prove to be inadequate for online and real-time conditions due to their high complexity and long computation time. This article proposes a pattern recognition approach to dynamic security analysis for large and complex power systems using ensemble decision tree to form reliable decision rules for fast and accurate prediction of power system's operating states in a real-time and on-line environment. An ensemble security predictor (ENSP) was developed and trained to act as “dynamic security state predictor” to predict and classify power system's dynamic operating states into secure, insecure, and intermediate transitional classes. Two different case studies were performed on IEEE 118-bus and IEEE 300-bus systems to evaluate and compare the performance of the proposed method on systems of varying size and complexity. While prediction accuracy of some of the single-learner classifiers decreased considerably when implemented on a large sized system, the performance of ENSP declined marginally, and the results were acceptable for very large sized systems.

Time Series Data-Driven Batch Assessment of Power System Short-Term Voltage Security

For power system dynamic security assessment (DSA), the conventional dynamic security region method is able to provide valuable information on security margins for preventive control. However, its event-based nature is likely to induce heavy computational burdens, especially in the presence of substantial presumed events. To tackle this challenging problem, this article develops an efficient time series data-driven scheme for batch DSA in a divide-and-conquer manner. First of all, with emphasis on short-term voltage stability, a novel u-shapelet (representative local trajectory)-based hierarchical clustering method is proposed to automatically divide various training cases into a handful of typical transient scenarios. Then, regressive shapelet learning is efficiently carried out to conquer individual scenarios, resulting in a group of high-precision security margin estimation models. With a desirable data-driven nature, the proposed scheme avoids time-consuming dynamic security region (DSR) characterization for each event, thereby achieving a significant speed-up for batch DSA. Test results on the realistic China Southern Power Grid illustrate its excellent performances on batch DSA.

Risk-Based Active Power Redispatch Optimization

Risk-based redispatch optimization is proposed as a methodology to support the Transmission System Operator (TSO) with preventive remedial actions obtained by extending the security-constrained unit commitment/economic dispatch with constraints resulting from the risk assessed for the power system. Although being heuristic, the methodology is based on comprehensive dynamic security assessment as time-domain simulations are used, allowing to express the degree of all types of instabilities, e.g., caused by contingencies, in monetary terms. Therefore, the risk is assessed as the expected value of the cost incurred by the TSO. Such an approach forms a new pathway to including risk in planning procedures already used by TSOs. Results obtained for the IEEE39 dynamic power system, with costs assigned to load shedding and generator tripping due to single transmission lines short-circuits, are shown as a reference case.

Study on stability feature extraction of power system using deep learning

Dynamic security assessment (DSA) of power grids is widely used in dispatching operation systems, and calculation speed is one of its most important performance indicators. In this paper, a stability feature extraction method is proposed, which is useful for quick judgment of stability and assisted decision-making. Firstly, a simulation sample database is constructed based on historical online data and a deep learning model with least absolute shrinkage and selection operator (LASSO) is trained to pick both the high level and low level stability features. While a new operation mode needs to be evaluated, a fast search is implemented to obtain the most similar samples in the database using the chosen high level features; the final result will be determined comprehensively by the familiar samples. If the power grid is in critical condition, a decision-making will be done by using the low level features. The validity of proposed method is verified by the simulation using online data of Northeast Power Grid of China. It is proved that the method meets the requirements for speed and accuracy of online analysis system.

A Review of Machine Learning Approaches to Power System Security and Stability

Increasing use of renewable energy sources, liberalized energy markets and most importantly, the integrations of various monitoring, measuring and communication infrastructures into modern power system network offer the opportunity to build a resilient and efficient grid. However, it also brings about various threats of instabilities and security concerns in form of cyberattack, voltage instability, power quality (PQ) disturbance among others to the complex network. The need for efficient methodologies for quicker identification and detection of these problems have always been a priority to energy stakeholders over the years. In recent times, machine learning techniques (MLTs) have proven to be effective in numerous applications including power system studies. In the literature, various MLTs such as artificial neural networks (ANN), Decision Tree (DT), support vector machines (SVM) have been proposed, resulting in effective decision making and control actions in the secured and stable operations of the power system. Given this growing trend, this paper presents a comprehensive review on the most recent studies whereby MLTs were developed for power system security and stability especially in cyberattack detections, PQ disturbance studies and dynamic security assessment studies. The aim is to highlight the methodologies, achievements and more importantly the limitations in the classifier(s) design, dataset and test systems employed in the reviewed publications. A brief review of reinforcement learning (RL) and deep reinforcement learning (DRL) approaches to transient stability assessment is also presented. Finally, we highlighted some challenges and directions for future studies.

A Fully Data-Driven Method Based on Generative Adversarial Networks for Power System Dynamic Security Assessment With Missing Data

This paper proposes a fully data-driven approach for PMU-based pre-fault dynamic security assessment (DSA) with incomplete data measurements. The generative adversarial network (GAN), which is an emerging unsupervised deep learning technique based on two contesting deep neural networks, is used to address the missing data. While the state-of-the-art methods for missing data are dependent on PMU observability, they are limited by the placement of PMU and network topologies. Distinguished from existing methods, the proposed approach is fully data-driven and can fill up incomplete PMU data independent on PMU observability and network topologies. Therefore, it is more generalized and extensible. Simulation results show that, under any PMU missing conditions, the proposed method can maintain a competitively high DSA accuracy with a much less computation complexity.