Power System Security Assessment Research Articles

The role of data-driven methods in power system security assessment from aggregated grid data

Data-driven techniques have been considered as an enabling technology for reducing the computational burden of both static and dynamic power system security analysis. Anyway, the studies reported in the literature mainly focused on inferring from historical data the mapping between the bus variables before and after a certain contingencies set, while, to the best of the Author's knowledge, limited contributions have been devoted to try and classify the power system security state by processing aggregated grid data. This is a relevant issue to address for a Transmission System Operator since it could allow a sensible decrease in the computational burden and, considering that aggregated grid data can be reliably predicted from several hours to one day ahead, it may enable the evolution of security assessment to security forecasting. In trying and filling this research gap, this paper explores the role of machine learning and feature selection algorithms. A realistic case study involving 2 years of synthetic grid data simulated on the Italian power system model against future potential operational scenarios characterized by a high share of renewables is presented and discussed to identify the most promising computing paradigms, analyzing the criticality of tuning the feature selection and classifier algorithms.

Data creation techniques and data-oriented models for dynamic security assessment of power system

Data creation techniques and data-oriented models for dynamic security assessment of power system

A Novel Image Classification Approach via MobileNet Model for Security Assessment of Power System

The computational complexities of conventional techniques used for security assessment of power system are addressed by proposing a maiden deep learning-based technique capable of boosting security calculations, increasing decision-making efficiency, and reducing hazards for real time operation. This approach uses MobileNet Convolutional Neural Network (MCNN) to evaluate security with reduced model size and computational burden as compared to traditional CNN architectures by leveraging special type of convolution technique. MCNN's automatic feature extraction and strong generalization allow the operator to determine whether the current operating state of power system is secured or not. All of the system’s critical operational scenarios are developed via load flow studies for generation of data while accounting for small signal stability with ℓ − 1 security and converted into RGB images of varied input dimensions for training and testing of the MCNN. Once trained, the MCNN is well-suited for real-time applications like assessing whether current state of the system is secured or not including unforeseen occurrences like topological changes in a computation-free manner. The comparative performance of the proposed method with customized CNN on three typical IEEE test system demonstrates its superior performance in terms of better accuracy and computational efficiency.

A Dynamic Equivalent Method for PMSG-WTG Based Wind Farms Considering Wind Speeds and Fault Severities

The dynamic security assessment of power systems needs to scan contingencies in a preselected set through time-domain simulations. With more and more wind power generation integrated into power systems, the complexity of simulation will increase greatly if wind farms are modeled in detail. Thus, it is critical to develop dynamic equivalent methods for wind farms. The dynamic response characteristics of permanent magnet synchronous generator-wind turbine generators (PMSG-WTGs) are not only influenced by their control strategies, but also by the operating wind speeds and the fault severities. Thus, this paper proposes a dynamic equivalent method for a PMSG-WTG based wind farm considering the wind speeds and the fault severities. Firstly, we propose a clustering method based on the operating wind speed and the terminal voltage of each PMSG-WTG at the end of the fault. Then, a single-machine equivalent method is introduced for each cluster of PMSG-WTGs. For the cluster of PMSG-WTGs with active power ramp recovery process, an equivalent model with segmented ramp rate limitation for active current is designed. In order to obtain the clustering indicators, a simulation-based iterative method is put forward. Eventually, the efficiency and accuracy of the proposed method are verified by the simulation results.

Distributed Feature Selection for Power System Dynamic Security Region Based on Grid-Partition and Fuzzy-Rough Sets

In order to satisfy the requirements of modern online security assessment of power systems with continuously increasing complexity in terms of structure and scale, it is desirable to develop a power system dynamic security region (DSR) analysis. However, data-driven methods suffer from expensive model training costs and overfitting when determining DSR boundaries with high-dimensional grid features. Given this problem, a distributed feature selection method based on grid partition and fuzzy-rough sets is proposed in this paper. The method first employs the Louvain algorithm to partition the power grid and divide the original feature set so that high-dimensional features can be allocated to multiple computational units for distributed screening. At this point, the connections between features of different computational units are minimized to a relatively low level, thereby avoiding large errors in the distributed results. Then, an incremental search algorithm based on the fuzzy-rough set theory (FRST) is used for feature selection at each computational unit, which can effectively take into account the intrinsic connections between features. Finally, the results of all computational units are integrated in the coordination unit to complete the overall feature selection. The experimental results based on the IEEE-39 bus system show that the proposed method can help simplify the power system DSR analysis with high-dimensional features by screening the critical features. And compared with other commonly used filter methods, it has higher screening accuracy and lower time costs.

Online Monitoring of Oscillation Modes for Small-Signal Security Assessment

This paper presents the main concepts of small-signal security assessment of power systems, focusing on the online monitoring of small-signal stability. In this work, a computational tool for online monitoring of oscillation modes (OLMO) in power systems is proposed. The objective of the methodology consists of determining small-signal stability margins, security levels, and corrective measures that can improve the damping factor of oscillation modes present in such systems. These corrective measures can be associated with possible redispatches of power plants. In this context, the Closest Security Boundary for Generation Redispatch using Eigenvalue Sensitivities, known as CSBGRES Method, could be applied to determine an optimized redispatch for the power plants of the system to ensure a desired minimum damping factor, previously chosen, for oscillation modes. The proposed tool can be applied for controlling power plant dispatches on Smart Grids, focusing on the damping factor of oscillation modes. A small test system is used to evaluate the proposed computational feature and the results were presented to demonstrate its importance to power system security. Results of the utilization of OLMO on the Brazilian Interconnected Power System (BIPS) are presented to prove the viability of using this method in large-scale power systems.

The Total Transfer Capability Assessment of Transmission Interfaces Combining Causal Inference and Multi-Task Learning

Power system security assessment has many tasks for different evaluation topics or objects, such as the Total Transfer Capability (TTC) assessment of different transmission interfaces. Some different tasks are related with each other, which is an important characteristic to improve the assessment performance if used properly but easily to be neglected. In this study, a novel architecture of the Causality-based Multi-Task Neural Network (CMTNN) is proposed, which can take the causal relevance between tasks into account while avoiding the introduction of too much extraneous information. First, the mask layer is applied after the input layer to filter irrelevant information task-specifically. Then, the causal analysis based on the Peter-Clark algorithm is performed to find those causally-related tasks. Finally, the causality-based information-sharing mechanism between related tasks is designed in the neural network to share deep information, so as to improve the model assessment performance on those tasks. In this paper, the proposed method is applied on the total transfer capability assessment problem of multiple transmission interfaces, and the case study on a real-world regional system with more than 8,000 nodes in China validates its effectiveness.

An ensemble based data mining model for contingency analysis of power system under STLO

<span lang="EN-US">In a large, interconnected power system, contingency analysis is a useful tool for pinpointing the potential consequences of post-event scenarios on the system's safety. In this work, the Newton-Raphson technique is applied to every single outage of a transmission line to compute the load flows. For the static security classification of the power system, the line voltage stability performance index (LVSI) is used. There are three levels of static security of power system namely: non-critical (the least severe), semi-critically insecure (the next lowest severe), and critical (the next highest severe). The various data mining techniques such as decision trees, bagging-based ensemble methods, and boosting-based ensemble methods were applied to assess the severity of the line under various loading and contingency conditions. Test systems based on the IEEE 30 bus system were used with the proposed machine learning classifiers. The experimental results proved that bagging based ensemble method provided better accuracy compared to the decision tree and the AdaBoost ensemble method for predicting the power system security assessment. The bagging-based ensemble method has a predictive accuracy of 85% and an AUC of 0.94.</span>

Dynamic security assessment of electric power systems

Dynamic security assessment of electric power systems

Pre-Fault Dynamic Security Assessment of Power Systems for Multiple Different Faults via Multi-Label Learning

With the advancement of machine learning techniques, data-driven power system dynamic security assessment (DSA) has received great research interests. Traditional methods usually apply one DSA model for one specific fault and cannot simultaneously address different multiple faults by one model. To solve this issue and further improve the DSA accuracy performance, this paper proposes a novel DSA method based on multi-label learning (MLL) with a training database for sufficient and incomplete/uneven coverage labels scenarios. By considering fault correlation between different faults, the proposed MLL-based DSA method can handle multiple faults simultaneously with the high stability assessment accuracy performance. Moreover, this paper provides the detailed optimization process and tight mathematical proof for the proposed MLL-based DSA method. Comprehensive simulation tests and comparisons were conducted on the New England 10-machine 39-bus testing system and the synthetic Illinois 49-machine 200-bus testing system.

State of the art approach for comprehensive power system security assessment—Real case study

Power system security assessment plays a critical role in ensuring the safety and stability of the electric grid, evaluated by the operating state’s proximity to the loadability limits. However, with the increasing integration of intermittent renewable energy sources and rising electricity demands, there is a growing need for fast and reliable algorithms to perform power system security assessments effectively. This work reviews state-of-the-art approaches for steady-state security assessment and demonstrates the advantages of the recently proposed Transversality Enforced Newton Raphson (TENR) algorithm. The algorithm provides better computational tractability, scalability, and the capability to incorporate various technological constraints like limits on voltage setpoints, transmission line thermal limits, generator power outputs, etc. This work presents a generalization of the TENR algorithm, proof of convergence, and an adaptive step-size strategy with improved computational performance. The proposed algorithm was used to study maximum loadability, maximum boundness of the nodal power injections, and total transfer capability on a realistic case study of the Russian Far-East power system model, which expects substantial development in the nearest future.

Optimal classification tree for frequency security assessment of power systems with inverter‐based resources reinforcement

AbstractFrequency security is the premise of realizing the net‐zero transition. A novel assessment scheme is proposed to quantify the frequency security levels of transmission systems under different inverter‐based resources (IBRs) and their control parameter combinations. A novel system frequency dynamic model is proposed as a parametric optimization method, where the saturation of generators, energy storage systems, and renewable energy sources is incorporated as differential algebra equations. This problem is further reformulated as a mixed‐integer linear programming problem to generate a sufficient amount of data under different IBR integration and control parameters. The frequency security assessment problem is formulated as a data‐driven multivariate classification problem, which is solved by the optimal classification tree (OCT) algorithm with better interptretionability. Simulations are conducted on a transmission system. Numerical results indicate that the proposed system frequency dynamic model can capture the frequency dynamic under different IBR reinforcement plans and the OCT can realize accurate classification of the synthetic data regarding frequency security.

High-performance computing for static security assessment of large power systems

Contingency analysis (CA) is one of the essential tools for the optimal design and security assessment of a reliable power system. However, its computational requirements rise with the growth of distributed generations in the interconnected power system. As CA is a complex and computationally intensive problem, it requires a fast and accurate calculation to ensure the secure operation. Therefore, efficient mathematical modelling and parallel programming are key to efficient static security analysis. This paper proposes a parallel algorithm for static CA that uses both central processing units (CPUs) and graphical processing units (GPUs). To enhance the accuracy, AC load flow is used, and parallel computation of load flow is done simultaneously, with efficient screening and ranking of the critical contingencies. We perform extensive experiments to evaluate the efficacy of the proposed algorithm. As a result, we establish that the proposed parallel algorithm with high-performance computing (HPC) computing is much faster than the traditional algorithms. Furthermore, the HPC experiments were conducted using the national supercomputing facility, which demonstrates the proposed algorithm in the context of N−1 and N−2 static CA with immense power systems, such as the Indian northern regional power grid (NRPG) 246-bus and the polish 2383-bus networks.

Generating quality datasets for real-time security assessment: Balancing historically relevant and rare feasible operating conditions

This paper presents a novel, unified approach for generating high-quality datasets for training machine-learned models for real-time security assessment in power systems. Synthetic data generation methods that extrapolate beyond historical data can be inefficient in generating feasible and rare operating conditions (OCs). The proposed approach balances the trade-off between historically relevant OCs and rare but feasible OCs. Unlike conventional methods that rely on historical records or generic sampling, our approach results in datasets that generalise well beyond similar distributions. The proposed approach is validated through experiments on the IEEE 118-bus system, where a decision tree model trained on data generated using our approach achieved 97% accuracy in predicting the security label of rare OCs, outperforming baseline approaches by 41% and 20%. This work is crucial for deploying reliable machine-learned models for real-time security assessment in power systems undergoing decarbonisation and integrating renewable energy sources.

Data-driven approach to fuzzy inference system tuning for static security assessment of multi-area power systems with renewable energy

Energy market deregulation and increased integration of intermittent renewable energy resources (RE) have pushed modern power systems to operate close to their security limits, which if violated could be catastrophic. To prevent power system failure and damage, a fast and accurate security assessment tool is required. In this paper, a data-driven fuzzy inference system tuned by hybrid genetic-simulated annealing (HGSA-FIS) is proposed for quick static security assessment (SSA) of a power system under a single component failure. An existing composite security index is modified to make a reliable SSA by distinguishing between severe and non-severe operating scenarios and contingencies. The prediction performance of HGSA-FIS was evaluated on an RTS-GMLC test system with operating scenarios varying with RE generation, load demand, and tie-line flows. The findings demonstrate the robust performance of HGSA-FIS in making static security assessments under varying operating scenarios, exceeding ANFIS in most and ANN in a few scenarios.

Data security of machine learning applied in low-carbon smart grid: A formal model for the physics-constrained robustness

Towards the low-carbon goal, a smart grid features remote connection, data sharing, and cyber–physical integration to increase the flexibility of energy supplies, to reduce electricity wastage, and to enhance safety under intermittent renewables. In this context, machine learning (ML) is increasingly employed in smart grids to solve tasks that require deep data analytics. However, it is well recognized that ML models are vulnerable to adversarial examples that might be contained in open shared data, which creates opportunities for potential attackers to launch cyberattacks. In particular, system operating states acting as critical inputs to ML-based smart grid applications (MLsgAPPs) can be manipulated by malicious actors to mislead the system operator into making wrong decisions that in turn may cause major blackouts and other damaging cascading events. It is thus imperative to advance vulnerability assessment for MLsgAPPs.In this paper, we propose a physics-constrained robustness evaluation framework for MLsgAPPs, which is a first attempt of using tree ensemble (TE) models. Unlike adversarial attacks against prior studied image-classification tasks, adversarial examples against TE-based smart grid applications (TEsgAPPs) must not only cheat human intuition but also follow laws of physics and bypass error-checking mechanisms for power systems. Thus, formulation of the traditional robustness evaluation problem must be reconsidered to account for domain-specific misclassification, physical limit, power balance, and error-bypass constraints, in order to obtain tight lower bounds of the magnitudes of tolerated adversarial perturbations. We adopt a formal modeling approach to construct a discrete tree structure and to specify the model evasion conditions. We propose an efficient robustness evaluation method by transforming variables considering ℓ1 and ℓ∞ norms, followed by a generalization that expands the variable space to admit other types of norms. Using TE-based power system security assessment as an example, comprehensive simulations are conducted for evaluating the physics-constrained robustness under different TE models and model parameters.

Unique Symbolic Factorization for Fast Contingency Analysis Using Full Newton–Raphson Method

Contingency analysis plays an important role in assessing the static security of a network. Its purpose is to check whether a system can operate safely when some elements are out of service. In a real-time application, the computational time required to perform the calculation is paramount for operators to take immediate actions to prevent cascading outages. Therefore, the numerical performance of the contingency analysis is the main focus of this current research. In power flow calculation, when solving the network equations with a sparse matrix solver, most of the time is spent factorizing the Jacobian matrix. In terms of computation time, the symbolic factorization is the costliest operation in the LU (Lower-upper) factorization process. This paper proposes a novel method to perform the calculation with only one symbolic factorization using a full Newton–Raphson-based generic formulation and modular approach (GFMA). The symbolic factorization retained can be used during the iterations of any power flow contingency scenario. A computer study demonstrates that reusing the same symbolic factorization greatly reduces computation time and improves numerical performance. Power system security assessment under N-1 and N-2 contingency conditions is performed for the IEEE standard 54-bus and 108-bus to evaluate the numerical performance of the proposed method. A comparison with the conventional power flow method shows that the time required for the analysis is shortened considerably, with a minimum gain of 228%. The comparative analysis demonstrates that the proposed solution has better numerical performance for large-scale networks.

Online Probabilistic Static Security Assessment for Power Systems Considering High Renewable Penetration

With the rapid development of renewable energy, a large number of renewable energy stations are connected to the power system, which leads to a decrease in the inertia of the power system and an increase in safety risks suffered. Thus, online static security assessment (SSA) is increasingly necessary. However, because of the uncertainty of renewable energy, it is not feasible to check all possible scenarios in online SSA. To reduce the number of calculations and achieve SSA in a short time, a new online SSA method based on scenario clustering for future ultra-short-term security assessment is proposed in this paper. In the offline stage, a key scenario set is constructed by Markov Chain Monte Carlo and K-means with historical data. In the online application, the initial probability distribution of renewable energy outputs is calculated by joint distribution with the output of the previous interval and corrected by weather data. Then load flow calculation with N-1 criteria is executed, and the probability for the safe operation of the system is calculated. The effectiveness of the proposed online SSA scheme has been verified in the IEEE-300 system, where one of the generators is replaced by a renewable energy station.

Dynamic Security Assessment of Small-Signal Stability for Power Grids Using Windowed Online Gaussian Process

The online small-signal stability assessment of electrical power grids is typically a challenging problem due to uncertainties and parameter variations of power system dynamics as well as the incurred high computational complexity. This paper proposes a novel theoretical framework for dynamic small-signal stability assessment of power grids by estimating the region of attraction (ROA) for operating states in real time. By analyzing the latest sampling data of power grids in a fixed time window, an up-to-date training set is constructed with the aid of converse Lyapunov function, which enables us to develop an online learning approach based on Gaussian Process (GP) to assess the stability level of power grids. As a result, an iteration algorithm is designed to update the assessment parameters by learning the input-output pairs in the training set. Theoretical analysis is conducted to ensure the existence of converse Lyapunov function for differential-algebraic system that serves to describe power system dynamics, as well as to estimate the region of attraction for operating states with a given confidence level. In particular, a practical method is proposed to leverage time series of phasor measurement unit (PMU) measurements including voltage/current magnitude, phase and frequency (i.e., PMU data) of real power grids for validating the online GP approach. Moreover, validations are taken to substantiate the proposed approach by using PMU data of real smart-grid infrastructure and IEEE test cases. The proposed assessment approach contributes to situational awareness of human operators in the control station, thereby taking proactive remedial actions prior to emergencies. Note to Practitioners—This paper was motivated by the problem of online assessment of power systems security but it also applies to other industrial control systems that have stable state trajectories. Existing approaches to security assessment of power systems generally focus on the adoption of various machine-learning algorithms by treating power grid as a “black box,” which ignores the intrinsic characteristics of power systems and thus restricts the inference performance. This paper proposes a new approach using limited sampling data and system dynamics to construct a domain of stability for power grids, which can reflect the evolution of security zones and provide more accurate predictions. In this work, we mathematically characterize the domain of stability for a practical power grid by analyzing and learning its state trajectories. Then we show how the proposed approach can be efficiently implemented online, which can timely alert human operators to abnormalities. Preliminary validations suggest that this approach is feasible and effective. In future research, we will incorporate it into an energy management system and test it in other industrial processes.

Data-driven power system security assessment using high content database during the COVID-19 pandemic

As the coronavirus disease (COVID-19) broke out in late 2019, the electricity sector was significantly impacted. Hence, the effects of the pandemic and restricting measures in power system operation are investigated during pandemic circumstances. The secure operation of the power system is a fundamental requirement. Appropriate procedures should be taken to mitigate these effects and ensure the power system's security. Accordingly, in this study, the authors determine that the COVID-19 pandemic can change the system's operating conditions in the first stage. Since data-driven security assessment methods require the training database to learn about Security constraints, this paper proposes an efficient database generation strategy respecting the consequences of the COVID-19 outbreak. The proposed strategy provides a training set with high information content compatible with the operating conditions. To this end, the method consists of a characteristics extraction approach and updating scheme. The characteristics should be extracted to represent the operating conditions of the system.Further, the similarity of intervals is compared using characteristics in updating scheme. The copula-based sampling approach is provided to generate the random samples. The proposed strategy generates a database for data-driven methods. Therefore, it can be utilized in various applications of security assessment. Real-world data is mapped to the IEEE 39-bus system to illustrate the framework efficiency. The outcomes indicate that a classification using the proposed strategy outperforms conventional methods in terms of evaluation metrics.© 2017 Elsevier Inc. All rights reserved.