Visualization of power system static security assessment based on GIS

According to the growth rate of Machine Learning (ML) application in some power system subjects, this paper introduce a comprehensive survey of Artificial Neural Network (ANN) in Static Security Assessment (SSA). Advantages and disadvantages of using ANN in above mentioned subjects and the main challenges in these fields have been explained, too. We explore the links between the fields of SSA and NN in a unified presentation and identify key areas for future research. Recent developments in the solution methods for SSA are reviewed. Hybrid techniques in SSA are also discussed and reviewed and future directions for research are suggested.

In this paper, a knowledge-based system for static security assessment of power system is proposed and investigated. An expert system (ES) for screening the consequences of transformers' and electrical lines' single outage was developed. The rules derived from a simulation model, irrespective of the size of the power system, are thus obtained. A dedicated artificial intelligence language (Prolog) for rules implementation was used to build the ES named CONTIG. The results show that such ES can be very effective for contingencies' selection. The benefits for a moderate size power system (25 buses and 30 branches) were analyzed using CONTIG. This approach has a great potential for online application

Machine learning (ML) algorithms have been widely developed to enable real-time security assessment for large-scale electricity grids. However, it also has been extensively recognized that the ML models are vulnerable to adversarial examples, which are slightly perturbed instances that can mislead the classifications but cannot be distinguished by human eyes. Considering the adversarial examples against the ML-based security assessment, they must not only cause misclassification but also follow the power balance and transfer limits and bypass the bad data detection. To this end, this paper proposes a novel concept named physics-constrained robustness that aims to computing a lower-bound of adversarial perturbations, evaluating the vulnerability of the ML-based intelligent security assessment (ISA) for power systems. A general optimization problem is formulated to compute the physics-constrained robustness of ISA with the mislabeling, power balance, power limitation, and invisible constraints. The analytical results and comparing relationship of ISA’s robustness with different constraints are provided. By using the static security assessment as an example, we provide explicit formulations to evaluate the physics-constrained robustness of. Finally, extensive experiments are conducted to evaluate the physics-constrained robustness of ISA in static and dynamic cases with the real-world load profiles from New York State and provide suggestions to select the ML models and parameters.

Power system security is one of the major concerns in recent years due to the deregulation of power systems which are forced to operate under stressed operating conditions. This paper presents a novel method based on growing and pruning training algorithm using radial basis function neural network (GPRBFNN) and winner-take-all neural network (WTA) to examine whether the power system is secure under steady-state operating conditions. Hidden layer neurons have been selected with the proposed algorithm which has the advantage of being able to automatically choose optimal centers and distances. A feature selection technique-based class separability index and correlation coefficient has been employed to identify the inputs for the GPRBF network. The advantages of this method are simplicity of algorithm and high accuracy in classification. The effectiveness of the proposed approach has been demonstrated on IEEE 14-bus and IEEE 30-bus systems.

The increasingly complex power grid structure and the volatility caused by the high proportion of renewable energy have brought great challenges to the traditional static security assessment of power grids. To solve this problem, a multi-source data-driven power grid static security risk assessment method is proposed in this paper. Firstly, the historical operation data of the power grid, including the grid structure of the system, load power, generator power and weather information, are used to build a multi-source data set. Then, a static security assessment model is constructed using long-term and short-term memory neural network and deep neural networks, and the multi-source data sets are used for off-line training. According to the output results of the assessment model, a three-level static security risk assessment index system is then developed. Finally, the proposed method is tested through a provincial 500kV power grid. The example results show that the method proposed in this paper can effectively realize the assessment of power grid static security risks, which can be used to assist the system operators for future intelligent dispatch and control.

It is fundamental for the kinematics simulation and mechanism design to apply the visualization in scientific computing on the simulation research of 3D mechanism. It is also the basis of independent development for 3D CAE software without any copyright limit. This paper offered a parameterized kinematics simulation template for 3D mechanism based on the visualization in scientific computing, in which the open graphics library is applied by MFC compiler. This paper illuminates the fundamental principle of the simulation development applying the OpenGL technology. The principle of OpenGL, the procedure structure, the working flow of OpenGL, the concept of program designing and the code implementation based on VC++ is demonstrated and an application approach for mechanism simulation is developed under the MFC environment. Keywords: visualization in scientific computing, MFC compiler, OpenGL, parameterized, kinematics simulation for 3D mechanism

This paper presents an efficient security assessment system for validating power system operation planning, which has been used in Henan provincial power grid in China. Daily operation planning is to schedule unit commitment and to dispatch generator output economically considering next day generators and transmission components' maintenance planning. The security assessment for validating the daily operation planning includes static security assessment and dynamic security assessment which are done for all the 96 power flow snapshots for next day. It is obviously a big challenge in reducing exhausting calculation burden. To speed up the calculation, a flexible and distributed parallel computing platform is designed which is based on a PC cluster and Multi-Agent system. The framework of the security assessment system for daily operation planning validation is introduced. And the technologies to implement the high performance computing are given. Some calculations for daily operation planning validation for control centre of Henan power grid are done and the results show that the parallel computing platform is efficient in computation.

Contingency ranking is one of the methods used in power system operations and planning to foresee the behavior of a system when there is a large disturbance in the system. Several indices have been proposed in the literature for estimating the severity of a particular contingency but mostly in the area of static security assessment. Therefore, in order to effectively capture the performance of a large power system under contingencies, dynamic security assessment (DSA) indices would be more desirable. In this paper, a score is presented with relatively less computational burden and used to determine the severity of a large disturbance in the power system for the purpose of contingency ranking. This score is formulated from the algebraic state variables that are related to the machines in a multi-machine power system modeled with differential algebraic equations (DAE). The proposed score is used with the angle stability criteria and applied on the IEEE 14-Bus test system in Matlab environment to determine the critical transmission lines in the system.

The secure integration of renewable generation into modern power systems requires an appropriate assessment of the security of the system in real-time. The uncertainty associated with renewable power makes it impossible to tackle this problem via a brute-force approach, i.e. it is not possible to run detailed online static or dynamic simulations for all possible security problems and realizations of load and renewable power. Intelligent approaches for online security assessment with forecast uncertainty modeling are being sought to better handle contingency events. This paper reports the platform developed within the iTesla project for online static and dynamic security assessment. This innovative and open-source computational platform is composed of several modules such as detailed static and dynamic simulation, machine learning, forecast uncertainty representation and optimization tools to not only filter contingencies but also to provide the best control actions to avoid possible unsecure situations. Based on High Performance Computing (HPC), the iTesla platform was tested in the French network for a specific security problem: overload of transmission circuits. The results obtained show that forecast uncertainty representation is of the utmost importance, since from apparently secure forecast network states, it is possible to obtain unsecure situations that need to be tackled in advance by the system operator.

Initial impetus for scientific visualization was provided in 1987 by a National Science Foundation (NSF) Panel Report of a Workshop on ‘Visualization in Scientific Computing’ (McCormick et al. 1987).

Power system security is a major concern in real‐time operation. It is essential to protect the system from blackout by taking proper control actions. This study proposes a boosting algorithm for the precise and accurate prediction of static security assessment of power systems using synchronised measurements. In addition to security status, the proposed approach also predicts the type of violations which may be either line overload/voltage violation or both of the insecure operating conditions. To overcome the computational complexity, the number of input phasor measurements is reduced by a statistical approach based on class separability and correlation coefficient indices. In the classification stage, support vector machines (SVMs) are used as weak classifiers and a strong classifier is constructed as the linear combination of many weak SVM classifiers. The performance of the Adaptive Boosting (AdaBoost) algorithm is further improved by a new weight updation strategy using fuzzy clustering thresholding technique. The efficiency of the proposed approach is demonstrated on IEEE 14‐bus, IEEE 30‐bus, and Indian 246‐bus systems. Further, the test results reveal that the proposed method of security assessment performs better than the other traditional classifiers viz. SVM, feed forward neural network and k‐nearest neighbour classifier.

The increasing penetration of renewable energy into the power system has aggravated the uncertainties during grid operation. Hence fast security assessment method has become highly imperative for system operators. In this paper, a deep convolutional neural network (deep CNN) is developed as an efficient tool to implement fast static security assessment, which classifies system security status via data mining. The multiple convolutional layers within the deep CNN can automatically extract features from the raw data and formulate an approximated mapping between the input and the output without intensive numerical computation. Applying the proposed deep CNN on standard IEEE test cases verifies its accuracy and efficiency for system operation security classification, which indicates its considerable potential for future online application.

The growth of large interconnected electricity networks requires a high degree of security for normal operation. This paper attempts to overview several available techniques for assessing the Transient Security Assessment (TSA) of a power system. Different algorithms are explained in details (Static and Dynamic Security Assessment) with the uses of Artificial Intelligent (AI) method. Transient effects can be roughly described as undesired voltage/ current that may result a contingencies in the power system. However, it is only considered lightning and switching as the main causes of TSA. In this proposed method, Artificial Neural Network (ANN) and Fuzzy techniques are able to use in term of classification, prediction and to determine the system security status. Time domain analysis is performed for each credible contingency using signal processing method; than an AI model is proposed for the TSA analysis. The novelty of the proposed approach is that the fast ability to detect and classify any disturbance (lightning (or) switching) in the electric power system using AI techniques.

Nowadays, the increasing energy demand, development of smart grids, and the combination of different energy systems have led to the complexity of power systems. On the other hand, ever-expanding energy consumption, development of industry and technology systems, and high penetration of solar and wind energies have made electricity networks operate in more complex and uncertain conditions. Therefore, analysis of traditional power and energy systems requires physical modeling and extensive numerical computation. To analyze these systems’ behavior, advanced metering and condition monitoring devices and systems are utilized, which generate huge amounts of data. Assessment of these data is approximately impossible by conventional methods and requires powerful data mining procedures. Machine learning, deep learning, and a variety of regression, classification, and clustering algorithms are powerful tools to use in these issues. These procedures can be utilized for load/demand forecasting, demand response evaluation, defect/fault detection in electrical equipment, power system analysis and control, cybersecurity, and renewable energy generation prediction. Understanding the structure and functioning of each learning method is therefore one of the most important issues in the application of them to solve power system problems. In this chapter, we will introduce and discuss selected methods of data mining based on their learning, structure, formulation, mode of operation, and application in power systems. Literature on machine learning and deep learning procedures, train and test process of networked methods, and, finally, applications of each procedure are presented in this chapter.

Preface. Contributors. 1 The Real-Time and Study-Mode Data Environment in Modern SCADA/EMS ( Sudhir Virmani and Savu C. Savulescu ). 1.1 Introduction. 1.2 SCADA/EMS Architectures. 1.3 Integrating Stability Applications with the SCADA/EMS. 1.4 References. 2 Overview of Key Stability Concepts Applied for Real-Time Operations ( Savu C. Savulescu ). 2.1 Introduction. 2.2 In Search of the Stability Limits. 2.3 Transient and Voltage Stability Limits. 2.4 Steady-State Stability Limits. 2.5 Concluding Remarks. 2.6 References. Annex 1-1. Reactive Power Steady-State Stability Criterion dDELTAQ / dV. 3 LIPA Implementation of Real-Time Stability Monitoring in a CIM Compliant Environment ( Loris Arnold, Janos Hajagos, Susan M. Manessis, and Anie Philip ). 3.1 Introduction. 3.2 Static and Dynamic Security Assessment at LIPA. 3.3 Benchmarking the Real-Time Stability Application. 3.4 Practical Experience and Outlook. 3.5 References. 4 Real-Time Stability Monitoring at the Independent System Operator in Bosnia and Herzegovina ( Dusko Vickovic and Roland Eichler ). 4.1 Introduction. 4.2 Interim Implementation of Real-Time Stability Assessment at NOS BiH. 4.3 Real-Time Stability Assessment in the New SCADA/EMS Environment. 4.4 Conclusions and Recommendations. 4.5 References. Annex 4-1. TSL, TTC, and the Stability Envelope. Annex 4-2. Siemens Implementation of the Continuation Power Flow. 5 Experience with Real-Time Stability Assessment at Transelectrica ( Horia S. Campeanu, Cornel Erbasu, and Cornel Aldea ). 5.1 Introduction. 5.2 Security Assessment Philosophy and Criteria. 5.3 Real-Time Steady-State Stability Assessment and Monitoring. 5.4 Off-Line Stability Tools in Support of System Operations. 5.5 Conclusions and Outlook. 5.6 References. 6 Implementation of Online Dynamic Security Assessment at Southern Company ( Kip Morison, Lei Wang, Fred Howell, James Viikinsalo, and Alan Martin ). 6.1 Introduction. 6.2 DSA Implementation Fundamentals. 6.3 Transient Security Assessment Implementation at Southern Company. 6.4 Conclusions. 6.5 References. Annex 6-1. Further Details of the DSA Software and Hardware Architecture. Description of the Core DSA Software. Online DSA Implementation Using DSATools. 7 Online Security Assessment for the Brazilian System A Detailed Modeling Approach ( Jorge L. Jardim ). 7.1 Introduction. 7.2 Security Criteria and Functions. 7.3 Solution Methods and Architecture. 7.4 Practical Implementation Aspects. 7.5 User Interface And Performance. 7.6 Concluding Remarks. 7.7 Acknowledgments. 7.8 References. 8 Dynamic Network Security Analysis in a Load Dispatch Center ( Guenther Beissler, Olaf Ruhle, and Roland Eichler ). 8.1 Introduction. 8.2 Siemens Approach to Dynamic Security Assessment. 8.3 Case Studies: Challenges, Implementation Approach, and Solution Features. 8.4 References. Annex 8-1. Further Dynamic Simulation Capabilities. Time Frame for Dynamic Simulations. Simulation in the Frequency Domain. Eigenvalue and Modal Analysis. 9 Real-Time Transient Security Assessment in Australia at NEMMCO ( Stephen J. Boroczky ). 9.1 Introduction. 9.2 Transient Security Assessment at NEMMCO. 9.3 Performance and Reliability. 9.4 Experience, Benefits, and Outlook. 9.5 References. 10 Online Voltage Security Assessment in the Hellenic Interconnected System ( Costas Vournas, George Christoforidis, and Thierry Van Cutsem ). 10.1 Introduction. 10.2 The Control Center of HTSO. 10.3 Online VSA in the Hellenic System. 10.4 Use of Online VSA For Arming Load-Shedding Protection. 10.5 Conclusion. 10.6 References. Annex 10-1. Quasi-Steady-State Simulation. Principle of the QSS Approximation. Handling of Frequency in QSS Simulation. QSS Model of the Synchronous Machine and its Regulations. Numerical Integration of the QSS Model. 11 The Real-Time Supervision of Transmission Capacity in the Swedish Grid ( Lars Sandberg and Klas Rouden ). 11.1 Introduction. 11.2 Prior and Current Application Development at SVK. 11.3 Voltage Security Assessment with SPICA. 11.4 Benefiting from the Knowledge of the Current Transmission Capacity. 11.5 Additional SPICA Functionality. 11.6 Summary. Appendix A Dimo's Approach to Steady-State Stability Assessment: Methodology Overview, Numerical Example, and Algorithm Validation ( Roberto D. Molina Mylius, Martin Cassano, and Savu C. Savulescu ). A.1 Methodology Overview. A.2 Numerical Example Independent Testing of Algorithm Implementation. A.3 Benchmarking the Methodology. A.4 Conclusions. A.5 References. Appendix B SIME: A Comprehensive Approach to Transient Stability ( Mania Pavella, Daniel Ruiz-Vega, and Mevludin Glavic ). B.1 Introduction. B.2 Basic Formulation. B.3 Preventive SIME. B.4 Emergency SIME. B.5 Postface. B.6 References. Notation. Abbreviations and Acronyms. Appendix C Detection and Evaluation of Stability Constrained ( Marius Pomarleanu and Savu C. Savulescu ). C.1 Introduction. C.2 Approach. C.3 Conclusions. C.4 References. Index.