Online power system dynamic security assessment with incomplete PMU measurements: a robust white‐box model

The increasing complexity of power systems as well as the rapid expansion of renewable energy resources and deregulation of electricity industry lead to continual demand for operating power systems at higher efficiencies. The modern power systems are pushed to operate close to their secure limits. When subjected to a severe contingency, the stressed power systems may lose its dynamic security, resulting in catastrophic consequences such as cascading failure and even wide-spread blackout. Under this new reality, online and real-time power system stability assessments have great impacts on avoiding blackout events. The traditional stability methods are mainly based on time-domain simulation, which are not fast enough to satisfy the online and real-time application requirements. In recent years, with the development of advanced real-time system monitoring and communication techniques, the data-driven methods have been identified as powerful tools to help power systems counteract large disturbance and avoid instability. To solve above threats, this Ph.D. research aims to develop data-analytics methodologies from power grid measurement data to recognize the system stability, covering both pre-fault dynamic security assessment (DSA) and post-fault real-time short-term voltage stability (STVS) assessment areas under some extreme scenarios and practical issues. Specific objectives of this Ph.D. research are to develop an intelligent system for the future smart grid. Based on several kinds of promising advanced data-analytics technologies, including randomized learning, incremental broad learning (BL), transfer learning (TL), adversarial machine learning (ML), and generative adversarial network (GAN), etc, an intelligent system will be developed to interpret the power grid stability characteristics, and to support stability-constrained operation control actions. Hence, it can make power systems achieve seven goals, including extensibility, efficiency, robustness, security, personalization, reliability, and effectiveness. The outcomes of this Ph.D. research will enable a more secure, intelligent, and knowledge-transparent future of the next-generation smart grid. The main contributions through this Ph.D. research are as follows: Firstly, the temporal-adaptive data-driven methods are proposed based on optimized hybrid ensemble learning mechanism for online STVS assessment. Compared to the traditional data-driven stability methods, the proposed methods can balance the tradeoff between the stability accuracy and speed and select the most suitable Pareto set. Secondly, in the area of DSA, an online updating DSA method is developed by using incremental BL technique. The incremental BL method only needs to calculate the pseudoinverse of new state matrix without the computations of the whole output weights matrix. In this way, it does not need re-training the whole model to continuously maintain and improve the online DSA accuracy. Besides, the proposed method can achieve under three different increment scenarios, including increment of enhancement hidden nodes, features, and new training instances. Thirdly, in the area of missing phasor measurement unit (PMU) data, two different fully robust data-driven stability methods are developed, respectively for pre-fault DSA and post-fault STVS assessment. The former one is based on GAN without observability-constrained feature subsets to ensure its availability under any PMU missing scenario. The latter one is based on super-resolution perception and incremental BL, which can achieve both satisfactory stability accuracy and speed. Fourthly, in order to accurately quantify the robustness of the ML-based model under adversarial perturbations on safety-critical power system stability problem, an adversarial robustness verification method for data-driven stability models is proposed. Besides, a model-free and attack-independent robust index are defined to evaluate the ability of the ML-based stability models against adversarial examples, which can be used to select the candidate model and provide formal robustness guarantee for stability application in practice. Rigorous mathematic proof is provided for the robust index under both linear and non-linear binary scenarios. Moreover, the proposed robust index can be used to mitigate the adversarial examples via adversarial training. Finally, three different TL-based DSA methods are proposed to use one known fault to evaluate other related but different unknown faults. The first two methods aim to reduce the distribution differences between the trained data and unknown data with the complete unlearned faults. The third one considers the different faults with incomplete data scenario. Through applying the adversarial training process, the DSA model trained by one fault can work for a different but related fault by confusing domain discriminator. With the property of feature extractor network, the proposed integrated TL-based method can solve the missing data issue for the unknown faults. All the methodologies have been tested on benchmark power systems to verify their effectiveness, and comparative and comparative studies with existing methods in the literature are conducted where applicable.

In this paper, implementation of power system dynamic security assessment (DSA) into a time domain simulation environment is described. The paper discusses general characteristics of DSA in time domain and presents a framework for software implementation. The implemented DSA system is user oriented and enables simple investigation of power system security in normal or contingency provoked system conditions. Using continuous processing, DSA is fully automated and can process any number of cases without user interaction, however, with some user established security constraints. If a security violation is detected, the contingency is documented and more detailed case study is possible. The paper presents methodology of implementation of DSA into well established simulator PSStradeNETOMAC, an overview of the considered power system security constraints and visualization options developed. The paper concludes with a case study. The DSA system was tested for performance on a generic single processor computer.

Synchronized phasor measurement unit (PMU) data contain rich information about power systems, hence the quality of estimates is of utmost concern. The existing methodologies for estimation rely on certain assumptions regarding the error in the measurement data. This paper revisits a key assumption specifically the Gaussian character of the error. A quantification of the PMU error yields its nature and statistical properties including its dependence on various sections of the PMU instrumentation channel (supposedly the major source of error in the PMU data). The non Gaussian nature of the error is asserted using various null hypotheses tests and a novel Gaussian mixture model based clustering technique is proposed to characterize and relate the errors present in PMU measurement data to the saturation in current transformer, cable length and the PMU burden. The proposed approach is tested using both real and synthetic PMU datasets. The ultimate goal of the paper is towards creating a PMU error emulator for testing and research of data analytic algorithms focused on crucial WAMS based applications.

This paper concerns with the production of synthetic phasor measurement unit (PMU) data for research and education purposes. Due to the confidentiality of real PMU data and no public access to the real power systems infrastructure information, the lack of credible realistic data becomes a growing concern. Instead of constructing synthetic power grids and then producing synthetic PMU measurement data by time simulations, we propose a model-free approach to directly generate synthetic PMU data. we train the generative adversarial network (GAN) with real PMU data, which can be used to generate synthetic PMU data capturing the system dynamic behaviors. To validate the sequential generation by GAN to mimic PMU data, we theoretically analyze GAN's capacity of learning system dynamics. Further by evaluating the synthetic PMU data by a proposed quantitative method, we verify GAN's potential to synthesize realistic samples and meanwhile realize that GAN model in this paper still has room to improve. Moreover it is the first time that such generative model is applied to synthesize PMU data.

The increasing complexity of power systems due to their growth, operation close to technical limits, economical constraints and new regulations, calls for the inclusion of dynamic security assessment (DSA) into energy management systems where the overall system control is performed. Recent researches on DSA have shown a significant interest in the accuracy of tools based on hybrid methods, a combination of time domain simulation and transient energy functions. A synthetic review of a hybrid method based procedure, implemented by the authors using a suitably adapted simulation code, is first recalled. Successively the possible application of a tool based on artificial neural networks (ANN) for operating a contingency pre-screening by identifying stable and unstable situations is proposed. The ANN capability of identifying the stable and unstable clusters which may originate after a perturbation is also investigated. The proposed ANN structure has been trained and validated by simulating properly arranged scenarios from a test system constituted by a real size HV network of the Mediterranean area.

This paper presents an on-going research project to develop an intelligent system (IS) that can be used together with existing power system dynamic security assessment tools in order to enhance the capabilities of online security assessment for power system operations. The use of intelligent systems in this application is expected to improve the speed, accuracy, and robustness of security assessment. A prototype system named POSSIT, POwer System Security using Intelligent Technologies, is presently being developed. An overview of the functional design of this prototype is given here and shows how this approach is applied to the Hydro-Quebec and BC Hydro power systems.

On-line dynamic security assessment offers several significant engineering and financial benefits. However, Current EMS systems can not perform online dynamic security assessment (DSA) to ensure the ability of the power system to withstand some contingencies. We have designed and implemented a reliable and effective system, called BCU-DSA, for online dynamic security assessments and energy margin calculations of practical power systems. BCU-DSA system achieves high level of reliability and accuracy by effective exploration of the merits of both the improved BCU classifiers and the detailed time-domain simulation program. The system has been evaluated on practical power system models with promising results. The BCU-DSA system gives exact stability/instability assessments and accurate energy margin for every contingency of practical power systems.

This study proposes a deep learning-based fault detection method for intelligent distribution networks using Phasor Measurement Unit (PMU) data. With the increasing development of intelligent distribution systems, the need for fast and accurate fault detection systems is crucial to improve the reliability and resilience of the power grid. Utilizing PMU data, which provides real-time information on voltage, current, and frequency, enables more precise and rapid fault detection. In this study, we developed a deep learning model that uses Long Short-Term Memory (LSTM) to sequentially process PMU data and detect faults such as short circuits, phase faults, and line outages. The model was trained on a PMU dataset covering a wide range of normal and fault conditions in the distribution network. Evaluation results show that the proposed model is capable of detecting faults with >98% accuracy and has a faster detection time compared to traditional detection methods. This approach also demonstrates the ability to identify fault types with a high degree of reliability and reduces the risk of system failure due to detection delays. By using deep learning methods, this study contributes to improving the reliability of intelligent distribution systems and provides a basis for the application of PMU technology in more efficient and automated distribution network monitoring and maintenance.

A dynamic state estimator for power system dynamic security assessment

Spatial-temporal adaptive transient stability assessment for power system under missing data

Introduction of Synchronized phasor measurement unit (PMU) in power system is a solution for monitoring system wide disturbances. PMUs provide precise information about a system’s phasors such as magnitude and phase angle of sine waves of the system. PMU data is a valuable source when determining the post-mortem of a fault, or a system disturbance. It can be unveiled what time the system began to falter and exactly what instabilities the system experienced. Knowing the cause of such instabilities will allow enhancement of the current system protection system. This will help in minimizing risk, disruptions or total system collapse. PMUs are synchronized via global positioning system (GPS). For wide area monitoring (WAM), synchronization of the PMUs allows for interconnected systems to be monitored simultaneously, giving real time records. This paper explores the impact of PMU in modern power system, deployment strategies of PMU network around Texas Tech University, importance of PMU data collected from the network, correlation of events by data analysis and focus on how the time stamped information is valuable for grid stability. The ongoing smart architecture of grid will increase dependency and importance on PMU based network in future.

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.

A new dynamic security assessment framework based on semi-supervised learning and data editing

In recent years, as power systems have become larger, power oscillations have become multifaceted, and so online Dynamic Security Assessment (DSA) has become essential to estimate these low-frequency electromechanical modes. To use this information for stabilization control of angle stability, it is important to obtain information on not only the frequency and damping of those modes but also the relative phase relation between each generator. This paper introduces a technique to estimate the relative phase relation of generators from time series data. The proposed method is applied to a two-variable ARMA model to estimate the low-frequency modes, and is applied to the cross spectrum to estimate the eigenvector efficiently. The proposed technique is verified by numerical examples with the IEEE 39-Bus system and the West 30-machine system model (115-Bus) which simulates the power system of Japan, and is compared with the eigenvector estimated by eigenvalue analysis.

Phasor measurement units (PMUs) equipped with global positioning system (GPS) receivers are the first devices capable of efficiently performing real-time monitoring of remote electrical power systems. Reliability of the monitoring system that exclusively uses PMUs is directly related to the reliability of each unit allocated on the system. As the failure of measurement channels is more common than PMU's failure, a probabilistic evaluation method of the PMUs measurement channels availability for electrical network observability analysis is proposed. In this method, the Markov process is adopted for estimating the measurement channels availability, as well as for determining an equivalent of the state space diagram of all possible operation states of channels for each unit. With the objective to assess the impact of the failure of measurement channels in the observability and reliability of the system, an algorithm that determines the optimal placement of PMUs using a modified binary search, the measurement channels availability for each unit, the global measurement availability, and the critical measurement channels for power system observability analysis was developed. Numerical results using the IEEE 14-bus, IEEE 30-bus, New England 39-bus, and IEEE 118-bus test systems are presented and discussed.