Application of Pattern Recognition in Transient Security Assessment

Abstract

One of the primary requirements of reliable service in electric power systems is to retain the synchronous machines running in parallel with adequate capacity to meet the load. In the normal operation of power systems, there may he faults or other large disturbances which have the potential of shifting the system operating point. Transient security assessment consists of determining whether the system oscillations, following the occurrence of a fault or a large disturbance from a contingency set, will cause loss of synchronism among the system generators. In order to have a highly reliable service, the system operating point has to be monitored and as soon as the system becomes vulnerable to a fault or disturbance, the control center should change the operating point of the system in a way to enhance its security. Pattern recognition is one of the promising methods for power system transient security assessment. The main objective of this method is to reduce the on-line computational requirement to a minimum. This paper is a review of the progress in the application of pattern recognition to power system transient security assessment. The recent results indicate that this method has reached a level of maturity that could be considered for on-line transient security nssessment of real systems.

Supervised fuzzy C-means clustering technique for security assessment and classification in power systems

“…Transient security of a power system addresses whether, after a perturbation, the system proceeds to operate consistently within the limits imposed by the system stability phenomena (Shahidehpour et al, 2003;Pang et al, 1973;Pang et al, 1974). Transient security assessment consists of determining, whether the system oscillations, following the occurrence of a fault or a large disturbance, will cause loss of synchronism among system generators (Hakim, 1992). TSA is a subset of transient stability analysis.…”

Pattern analysis and classification for security evaluation in power networks

“…Literatures have reported the use of AI techniques like Kohonen Neural Network [9], Multilayer feed forward with back propagation algorithm [10][11][12][13], fuzzy logic combined with neural network [14,15], genetic-based neural network [16] for static and transient security evaluation process. Application of Artificial Neural Network (ANN) based pattern recognition approach [17][18][19] has also been widely exploited in the literatures. Although ANN is the most popular machine learning method to classify patterns, it requires extensive training process and a complicated design procedure.…”

A new BVM based approach to transient security assessment

“…The transient stability can be assessed by different techniques such as time domain integration [1][2][3], direct methods based on energy function and extended equal area criterion [4][5][6], pattern recognition [7,8], decision trees (DTs) [9,10], and artificial neural networks (ANNs) [11][12][13][14][15][16][17].…”