Identification of coherent synchronous generators in a Multi-Machine Power System using Support Vector Clustering

Abstract

This paper illustrates the application of a new technique, based on Support Vector Clustering (SVC) for the direct identification of coherent synchronous generators in a large interconnected Multi-Machine Power Systems. The clustering is based on coherency measures, obtained from the time domain responses of the generators following system disturbances. The proposed clustering algorithm could be integrated into a widearea measurement system that enables fast identification of coherent clusters of generators for the construction of dynamic equivalent models. An application of the proposed method is demonstrated on a practical 15 generators 72-bus system, an equivalent of Indian Southern grid in an attempt to show the effectiveness of this clustering approach. The effects of short circuit fault locations on coherency are also investigated.

Online Identification of Power System Dynamic Signature Using PMU Measurements and Data Mining

“…A variety of clustering algorithms have been applied in the past to identify the coherency of generators using trajectory of rotor angles or speeds, including Fuzzy -means, principle component analysis, independent component analysis, support vector clustering, hierarchical clustering, etc. [21]- [24]. In all these studies however, number of groups of generators exhibiting similar behavior, or other types of parameters, need to be decided in advance for specific contingencies.…”

Non-heuristic Identification of the Optimal Number of Oscillation Patterns in Uncertain Power Systems

“…The ASW is the average of the silhouette coefficient ( ) over all elements in a dataset and is defined in (4).…”

“…Probabilistic approaches seem to be the best option to study these scenarios [1,2]. These studies generally involve the simulation of large number of operating conditions, facilitating the application of data mining techniques for training or classification purposes so that some specific feature of the system can be assessed or predicted, e.g., clustering algorithms that use rotor angle or speed for coherency identification are reported in [3][4][5].…”

Probabilistic Framework for Online Identification of Dynamic Behavior of Power Systems With Renewable Generation

“…Since transient stability is the main focus of this paper, it is important that the grouping of generators (based on similarity of rotor responses) reflects which generators are unstable, what group they belong to and in which order the groups of, or individual generators, lose synchronism. There are several clustering algorithms available in the literature that have been applied to identify coherent groups of generators, such as fuzzy C-means, principal and independent component analysis, support vector clustering and hierarchical clustering [23]- [26]. Hierarchical clustering is applied in this study, to determine the unstable generator groups, for each simulated contingency following the Monte Carlo probabilistic approach.…”