Assessment of Transient Stability through Coherent Machine Identification by Using Least-Square Support Vector Machine

Abstract

Transient stability assessment (TSA) of the power system is a crucial issue with escalating demands and large operational constraints. Real-time TSA allows for deciding and monitoring of the relevant preventive/corrective control actions depending on the dynamic behavior of the system components. To assess this, coherency of generating machines is to be found. After determination of the coherent machines, any corrective or preventive action can be initiated by the system operator to maintain stability of the system during occurrence of any severe contingency. e Transient Severity Index (TSI) introduced in this paper has proven to be an interesting alternative for determining generator coherency. Furthermore, the numerical values of this index are employed to construct a supervised learning-based classifier and the ranking method with the help of system load and generation as input features. is framework employs the support vector machine (SVM) to perform the ranking of the generators based on severity and classify them into vulnerable and nonvulnerable machines. e results are validated on the IEEE 10generator, 39-bus test (New England) system. It is observed that the proposed index and the supervised learning engine give satisfactory results and both are aligned with the published approaches.

Recent Developments in Machine Learning for Energy Systems Reliability Management

“…The database generation is then usually done offline, given the extensive simulation cost to build it, while the application of the resulting model trained on the dataset can be done offline or online, depending on the application and the context. [15], [16], [19], [22], [27]- [29], [32], [34], [35], [37], [38], [41], [43], [45], [47], [49]- [52], [54]- [56], [63], [64], [67]- [73], [75], [76], [81]- [83], [85]- [88], [90], [92], [93], [98], [102], [105], [107], [113], [115]- [117] Voltage stability [26], [30], [39], [40], [42], [44], [46], [48], [53],…”

“…Table II provides an overview of the main data pre-processing methods used for DSA and DSC discussed below. [34], [35], [37] Genetic algorithms [38], [39] Tree-based algorithms [40]- [43] Feature extraction PCA and variants [44]- [46] Fisher's linear discriminant [47] Shapelets for time series [48] Deep learning auto-encoders [49]- [52] Class imbalance Oversampling [24], [53], [54] Cost-sensitive learning [53], [55] Ensemble methods [41], [45], [56], [57] 1) Feature engineering: Given the large number of features necessary to fully describe the state of a power system and the need for fast algorithms, feature selection techniques are proposed in many papers. Too many features can lead to excessive training time and, if many features are not relevant, could decrease the performance of the learnt model.…”

“…Genetic Algorithms (GAs) can also be used to select features. In [38], the authors use Particle Swarm Optimization (PSO) based feature selection. Packets of features are drawn randomly with PSO and the selected packet is the one maximising the mean of the standard deviations of the packet.…”

“…In [115], the authors propose a preventive control scheme by rescheduling generating units. First, they assess the transient stability of the system [34], [38], [115] Neural networks [116] Tree-based methods [117]- [121] Linear models [122] with a hybrid method based on a SVM model and time-domain simulation. Then, if the system is unstable, they compute from the SVM model the sensitivity of each generator to a transient stability assessment index (derived from the SVM model) to rank the generators and select the ones that are more effective for improving the stability.…”

Development of Back-Propagation Neural Network for Transient Stability Assessment of Power Systems

“…TSA includes evaluating the rotor swings future behaviour after failure or significant disturbance to accurately predict transient stability [6]. The data received from PMUs at the control centre provides sufficient information about the present and future state of the system after disturbance from a stability point of view, it is possible to deal with the stability in real time [7,8,9]. A Multilayer Perceptron neural network with three layers consisting of one input layer, one hidden layer and one output layer is proposed in [10] and compared with radial basis neural networks (RBFNN) in [11].…”