Power System Emergency Control Research Articles

Intelligent Power System Stability Assessment and Dominant Instability Mode Identification Using Integrated Active Deep Learning.

Simulation analysis is critical for identifying possible hazards and ensuring secure operation of power systems. In practice, large-disturbance rotor angle stability and voltage stability are two frequently intertwined stability problems. Accurately identifying the dominant instability mode (DIM) between them is important for directing power system emergency control action formulation. However, DIM identification has always relied on human expertise. This article proposes an intelligent DIM identification framework that can discriminate among stable status, rotor angle instability, and voltage instability based on active deep learning (ADL). To reduce human expert efforts required to label the DIM dataset when building DL models, a two-stage batch-mode integrated ADL query strategy (preselection and clustering) is designed for the framework. It samples only the most helpful samples to label in each iteration and considers both information contents and diversity in them to improve query efficiency, significantly reducing the required number of labeled samples. Case studies conducted on a benchmark power system (China Electric Power Research Institute (CEPRI) 36-bus system) and a practical large-area power system (Northeast China Power System) reveal that the proposed approach outperforms conventional methods in terms of accuracy, label efficiency, scalability, and adaptability to operational variability.

A review of machine learning applications in power system protection and emergency control: opportunities, challenges, and future directions

Modern power systems, characterized by complex interconnected networks and renewable energy sources, necessitate innovative approaches for protection and control. Traditional protection schemes are often failing to harness the vast data generated by modern grid systems and are increasingly found inadequate and challenging for some applications. Recognizing the need to address these issues, this paper explores data-driven solutions, focusing on the potential of machine learning (ML) in power system protection and control. It presents a comprehensive review highlighting various applications which are challenging to address from conventional methods. Despite its promise, the integration of ML into power system protection introduces unique challenges. These challenges are examined in the paper, and suggestions are provided to overcome them. Furthermore, the paper identifies potential future research directions, reflecting the progressive trends in ML and its relevance to power system protection and control. This review thereby serves as an essential resource for practitioners and researchers working at the intersection of ML and power systems.

An athlete–referee dual learning system for real-time optimization with large-scale complex constraints

Constrained optimization (CO) has made a profound impact in solving many real-world problems. Due to the high computation burden in exact solvers, data-driven CO based on machine learning techniques is recently receiving extensive research interests for its capability to solve CO problems in real time. The existing data-driven CO approaches only serve for optimization problems with rather simple constraints that can be directly incorporated into model training. However, constraints that are computationally infeasible or burdensome to evaluate are commonly experienced in realistic optimization applications, especially in the engineering sector. This paper proposes an athlete–referee dual learning system (ARDLS) for end-to-end CO with large-scale complex constraints, where an athlete model is trained as the main optimizer while a referee model is trained as a probabilistic constraint classifier to guide the athlete training. A risk-based constrained loss function is designed to fine-tune the athlete model for constraint satisfaction. A case study on electric power system emergency control application is conducted to validate the proposed ARDLS, where the testing results demonstrate the excellent capability of ARDLS to improve the likelihood of satisfying large-scale complex constraints in CO.

Emergency load shedding strategy for high renewable energy penetrated power systems based on deep reinforcement learning

Traditional event-driven emergency load shedding determines the quantitative strategy by simulation of a specific set of expected faults, which requires high model accuracy and operation mode matching. However, due to the model complexity of renewable power generators and fluctuating power generation, traditional event-driven load shedding strategy faces the risk of mismatching in high renewable energy penetrated power systems. To address these challenges, this paper proposes an emergency load shedding method based on data-driven strategies and deep reinforcement learning (RL). Firstly, the reason for the possible mismatch of the event-driven load shedding strategy in the renewable power system is analyzed, and a typical mismatch scenario is constructed. Then, the emergency load shedding strategy is transformed into a Markov Decision Process (MDP), and the decision process’s action space, state space, and reward function are designed. On this basis, an emergency control strategy platform based on the Gym framework is established for application of deep reinforcement learning in the power system emergency control strategy. In order to enhance the adaptability and efficiency of the RL intelligence agent to multi-fault scenarios, the Proximal Policy Optimization (PPO) is adopted to optimize the constructed MDP. Finally, the proposed reinforcement learning-based emergency load shedding strategy is trained and verified through a modified IEEE 39-bus system. The results show that the proposed strategy can effectively make correct strategies to restore system frequency in the event-driven load shedding mismatch scenario, and have good adaptability for different faults and operation scenarios.

A Data-Driven Method for Power System Emergency Control to Improve Short-Term Voltage Stability

The power system contains a variety of uncertainties of different types of sources and loads, as well as random contingencies. Under these uncertainties and rapidly changing operating conditions, traditional rule-based methods cannot dynamically handle short-term voltage instability. To alleviate this situation, this paper proposes a novel power system emergency control scheme using a data-driven method, which combines edge-conditioned graph convolutional networks and deep reinforcement learning. The edge-conditioned graph convolutional network is utilized to extract the characteristics from not only power system nodes but also transmission lines. Deep reinforcement learning is introduced to perform load shedding actions, so as to guarantee the safety and stability of the electric power system. The IEEE 39-bus network is utilized for simulations to validate the effectiveness of the proposed data-driven method. The outcomes demonstrate the proposed method can generate a superior strategy in a number of the short-term voltage instability(STVI) circumstances.

Fast Algorithms for Estimating the Disturbance Inception Time in Power Systems Based on Time Series of Instantaneous Values of Current and Voltage with a High Sampling Rate

The study examines the development and testing of algorithms for disturbance inception time estimation in a power system using instantaneous values of current and voltage with a high sampling rate. The algorithms were tested on both modeled and physical data. The error of signal extremum forecast, the error of signal form forecast, and the signal value at the so-called joint point provided the basis for the suggested algorithms. The method of tuning for each algorithm was described. The time delay and accuracy of the algorithms were evaluated with varying tuning parameters. The algorithms were tested on the two-machine model of a power system in Matlab/Simulink. Signals from emergency event recorders installed on real power facilities were used in testing procedures. The results of this study indicated a possible and promising application of the suggested methods in the emergency control of power systems.

A comprehensive assessment of the state-of-the-art virtual synchronous generator models

The large-scale penetration of renewable energy sources has a significant impact on the steady-state operation and emergency control of modern electric power systems (EPS). Moreover, as a rule, the mentioned impact is negative. Therefore, the challenge associated with the development of a ‘comprehensive’ control strategy for renewables becomes extremely relevant. Such a strategy should ensure the same reliable operation of EPSs, as in the case of conventional synchronous generation. Among the existing directions, the concept of a virtual synchronous generator (VSG) is the most preferable. Within this paper, the synthesis and combination of the state-of-the-art concepts of VSG into generic structures has been performed. For the obtained structures, a comprehensive assessment and an experimental comparison were performed. On the basis of the results obtained, the benefits and drawbacks of the generic structures are highlighted, and a conclusion is made about the VSG structure, demonstrating the most effective and reliable operation.

Enhanced Oblique Decision Tree Enabled Policy Extraction for Deep Reinforcement Learning in Power System Emergency Control

Deep reinforcement learning (DRL) algorithms have successfully solved many challenging problems in various power system control scenarios. However, their decision-making process is usually regarded as black-boxes. Furthermore, how DRL models interact with human intelligence remains an open problem. Thus, this paper proposes a policy extraction framework to extract a complex DRL model into an explainable policy. This framework includes three parts: 1) DRL training and data generation. We train an agent for a specific control task and generate data, which contains the control policy of the agent. 2) Policy extraction. We propose an information gain rate based weighted oblique decision tree (IGR-WODT) for DRL policy extraction. 3) Policy evaluation. We define three metrics to evaluate the performance of the proposed approach. A case study for the under-voltage load shedding problem shows that the IGR-WODT presents a performance enhancement compared with DRL, weighted oblique decision tree, and univariate decision tree. The proposed policy extraction method could provide an intuitive explanation of the neural network decision-making process to the dispatchers when making final decisions on power grid operation. Also, the resulted rule-based controller could replace the deep neural network-based controller in many field edge devices with limited computing resources, providing comparable performance.

Explainable AI in Deep Reinforcement Learning Models for Power System Emergency Control

Artificial intelligence (AI) technology has become an important trend to support the analysis and control of complex and time-varying power systems. Although deep reinforcement learning (DRL) has been utilized in the power system field, most of these DRL models are regarded as black boxes, which are difficult to explain and cannot be used on occasions when human operators need to participate. Using the explainable AI (XAI) technology to explain why power system models make certain decisions is as important as the accuracy of the decisions themselves because it ensures trust and transparency in the model decision-making process. The interpretability issue in DRL models in power system emergency control is discussed in this article. The proposed interpretable method is a backpropagation deep explainer based on Shapley additive explanations (SHAPs), which is named the Deep-SHAP method. The Deep-SHAP method is adopted to provide a reasonable interpretable model for a DRL-based emergency control application. For the DRL model, the importance of input features has been quantified to obtain contributions for the outcome of the model. Further, feature classification of the inputs and probabilistic analysis of the outputs in the XAI model is added to interpretability results for better clarity.

Frequency prediction model combining ISFR model and LSTM network

Frequency prediction after a disturbance is devoted to providing a decision-making foundation to power system emergency control. In practice, the quantity of utilized variables is limited by the dimensionality of the physical model. Meanwhile, the accuracy of cognitive results is affected by the modeling precision. Owing to the model simplification, the computation efficiency of model-driven methods is improved, but the accuracy is sacrificed. In this paper, a prediction model combining the improved system frequency response (ISFR) model and long short-term memory (LSTM) network is proposed to overcome this problem. Firstly, the ISFR model is employed to generate features representing system dynamic characteristics. Combined with the features provided by the ISFR model, the system operating features are applied to construct the training set for the deep learning network. Then, the LSTM network is introduced and trained to fit mapping relationship between multi-dimensional input features and system frequency response, thereby improving the overall accuracy of the integrated model. Finally, the simulation verification of the proposed model is performed in the IEEE 39-bus system and a realistic regional system. The simulation results demonstrate that the proposed model has better performance than that of traditional models.

Power System Emergency Control Strategy Based on Severely Disturbed Units Identification and Stgcn-Ddqn

Power System Emergency Control Strategy Based on Severely Disturbed Units Identification and Stgcn-Ddqn

A topology adaptive high-speed transient stability assessment scheme based on multi-graph attention network with residual structure

Reliable and fast transient stability assessment (TSA) is significantly required for the power system emergency control. We propose a topology adaptive high-speed transient stability assessment (HSTSA) scheme, where the inputs of the model adopt only the pre-fault state and the dynamics at the fault occurrence snapshot. A novel multi-graph attention network with residual structure (ResGAT) is designed to capture the stability characteristics. ResGAT applies improved graph attention mechanism to enhance its adaptability to the power system topology changes and the residual structure helps to avoid network degeneration. Meanwhile, a new piece-wise transient stability index (PSI) is proposed for the stability level prediction. Integration of both the stability category and the stability level results increase the precision of the HSTSA scheme. Test results on IEEE 39 Bus system and IEEE 300 Bus system indicate the superiority of the proposed scheme over existing models and its robustness under various scenarios. .

Идентификация кибер- атак на системы SCADA и СМПР в ЭЭС при обработке измерений методами оценивания состояния

The hardware and software tools of the data acquisition and processing systems, as well as the state estimation procedure intended to support the actions of dispatching personnel in performing operational and emergency control of electric power systems (EPS), are critically important components of the EPS information and communication subsystem, but at the same time, they are most vulnerable to cyberattacks. To reduce the extent to which cyberattacks can affect the control quality, it is proposed to use statistical methods for processing measurement information. First of all, these are static and dynamic state estimation methods, including a procedure for verifying measurements or detecting bad data. An analysis of data quality can determine the type of cyberattack undertaken and identify overlooked vulnerabilities. The article presents the findings from a study of two most commonly used bad data detection methods: the a priori method for analyzing the residuals of test equations and the a posteriori method for analyzing the weighted estimation residuals to identify data distorted as a consequence of specially generated cyberattacks. An algorithm to detect erroneous measurements that appear during cyberattacks and are not identified by conventional measurement verification methods in performing EPS state estimation is proposed

Transient stability assessment combined model framework based on cost‐sensitive method

The real-time transient stability assessment (TSA) is critical for emergency control of power systems. Accurate and fast TSA can provide an important basis for post-fault control of power systems. At present, the accuracy of the evaluation model based on machine learning is very high, but there are still some misjudgements in the results. In order to build a high-accuracy evaluation model, a novel frame based on the cost-sensitive method is proposed. Firstly, a deep belief network (DBN) is applied to build a TSA frame. The DBN is effectively trained by means of pre-training and fine tuning. Secondly, two models with the opposite preference are constructed based on the cost-sensitive method. Based on the output results of the two models, the deterministic or uncertain evaluation results are obtained. The samples that may be misclassified are divided into uncertain evaluation results. Thus, the accuracy of the deterministic evaluation results can be improved greatly. Through this design, the practicability of the evaluation model based on machine learning is greatly improved. The effectiveness of the proposed scheme is verified by the simulation results in the IEEE-39 bus system and a realistic regional system.

Adaptive Power System Emergency Control Using Deep Reinforcement Learning

Power system emergency control is generally regarded as the last safety net for grid security and resiliency. Existing emergency control schemes are usually designed off-line based on either the conceived "worst" case scenario or a few typical operation scenarios. These schemes are facing significant adaptiveness and robustness issues as increasing uncertainties and variations occur in modern electrical grids. To address these challenges, for the first time, this paper developed novel adaptive emergency control schemes using deep reinforcement learning (DRL), by leveraging the high-dimensional feature extraction and non-linear generalization capabilities of DRL for complex power systems. Furthermore, an open-source platform named RLGC has been designed for the first time to assist the development and benchmarking of DRL algorithms for power system control. Details of the platform and DRL-based emergency control schemes for generator dynamic braking and under-voltage load shedding are presented. Extensive case studies performed in both two-area four-machine system and IEEE 39-Bus system have demonstrated the excellent performance and robustness of the proposed schemes.

Intellectualization of Emergency Control of Power Systems on the Basis of Incorporated Ontologies of Knowledge-Bases

Abstract The research deals with improvement of methods and systems of controlling integrated power systems (IPSs) on the basis of intellectualization of decision-making support. Complex analysis of large-scale accidents at power facilities is performed, and their causes and damages are determined. There is substantiated topicality of building condition knowledge-bases as the foundation for developing decision-support systems in power engineering. The top priorities of the research include developing methods of building a knowledge base based on intensity models of control actions influencing the parameters of power system conditions and introducing the smart system into information contours of the automated dispatch control system (ADCS), as well as assessing practical results of the research. To achieve these goals, the authors apply methods of experiment planning, artificial intelligence, knowledge presentation, mathematical simulation, and mathematical statistics as well as methods of power systems studying. The basic research results include regression models of a power system sensitivity to control actions, methods of building a knowledge base based on the models of sensitivity matrices, a structure of the smart decision-support system, a scheme of introducing the decision-support system into the operating ADCS environment. The problem of building a knowledge base of the dispatch decision-support system on the basis of empirical data resulted from calculating experiments on the system diagram has been solved. The research specifies practical efficiency of the suggested approaches and developed models.

An Efficient Parallel Sequential Approach for Transient Stability Emergency Control of Large-Scale Power System

Generator-tripping and load-shedding are important emergency control measures to maintain the transient stability of the power system. In this paper, emergency control is modeled as a large-scale optimal control problem. An efficient parallel sequential approach, which consists of preprocessing layer, simulation layer, and optimization layer, is proposed to solve the problem. In the preprocessing layer, power system partitioning is performed to construct a Jacobian matrix of double-layered bordered block diagonal (BBD) structure, control variable selection and initialization are designed to reduce computation cost and improve convergence. In the simulation layer, the differential algebraic equations are solved in parallel with the sensitivity analysis by reusing the LU-factorizations. Based on the BBD structure of Jacobian matrix, a parallel block algorithm is proposed to further accelerate computation speed. In the optimization layer, the resulting nonlinear programming problem is efficiently solved by predictor–corrector interior point method. The efficiency and practicality of the proposed approach are verified by numerical experiments on three test systems.

Prediction Model of the Power System Frequency Using a Cross-Entropy Ensemble Algorithm

Frequency prediction after a disturbance has received increasing research attention given its substantial value in providing a decision-making foundation in power system emergency control. With the advancing development of machine learning, analysis power systems with machine-learning methods has become completely different from traditional approaches. In this paper, an ensemble algorithm using cross-entropy as a combination strategy is presented to address the trade-off between prediction accuracy and calculation speed. The prediction difficulty caused by inadequate numbers of severe disturbance samples is also overcome by the ensemble model. In the proposed ensemble algorithm, base learners are selected following the principle of diversity, which guarantees the ensemble algorithm’s accuracy. Cross-entropy is applied to evaluate the fitting performance of the base learners and to set the weight coefficient in the ensemble algorithm. Subsequently, an online prediction model based on the algorithm is established that integrates training, prediction and updating. In the Western System Coordinating Council 9-bus (WSCC 9) system and the Institute of Electrical and Electronics Engineers 39-bus (IEEE 39) system, the algorithm is shown to significantly improve the prediction accuracy in both sample-rich and sample-poor situations, verifying the effectiveness and superiority of the proposed ensemble algorithm.

Scheme design considering network topology and multi-attribute decision-making for under frequency load shedding

Power system emergency control is one key defense strategy in contingencies for protecting the system from cascading blackout. Under Frequency Load Shedding (UFLS) is one such strategy to ensure system stability by shedding load to retrieve balance between power supply and demand. Novel UFLS scheme design and a scheme optimization approach are proposed in this paper to find the optimal load-shedding schemes for different network partition resulted from contingencies. To obtain all possible UFLS schemes for a certain area, a candidate scheme set design algorithm based on value assigning of scheme parameters is proposed and then a relatively complete candidate scheme set is constructed. Considering network splitting caused by protection, several subsystems may exist from the reconstruction of independent network areas. The concept of homological area is defined and a graph-based method is used to analyse system topology change. Then, a multi-attribute decision-making (MADM) algorithm is introduced for order preference by similarity to an ideal solution (TOPSIS) for global optimizing candidate schemes. Optimal schemes for an area in both isolated area and homological area cases can be derived from all feasible UFLS schemes by MADM method. Simulation results demonstrate that the UFLS schemes can effectively restore system frequency in different network topologies.

Stability mechanism and emergency control of power system with wind power integration

In power system electromechanical transients, wind power (WP) with power electronic interfaces is more capable of controlling active power compared to synchronous generators (SGs), but less capable of controlling voltage. WP is beneficial to transient rotor angle stability because it improves the deceleration of SG, but it is detrimental to transient voltage stability. A mechanism of WP inducing voltage instability is studied. The fast dynamics related to power electronic control transients can be neglected, and the WP is simplified to static power injection model in electromechanical transients. The WP is modelled with power balance algebraic equations, and the system dynamic equations are differential algebraic equations (DAEs). The trajectory encountering a singular point of the DAE corresponds to transient voltage instability in the system. The power balance equation of the WP becomes unsolvable at the point. Simulation results validate the mechanism, and reveal the variation of instability mode of a wind-thermal-bundled sending system. When the proportion of WP in the system increases, the dominant stability problem changes from rotor angle stability to voltage stability, and the stability of the system first gets better then gets worse. An emergency control strategy against the transient voltage instability induced by WP is proposed. WP is shed to shift the singular surface and avoid encountering singular points. An approach to select the most effective locations for WP shedding is proposed.