ABSTRACT
The increasing uncertainty in power systems has brought various challenges, including transient stability assessment. The conventional approaches, such as, time-domain simulation approach and direct method (based on Lyapunov function and transient energy function), to estimate the transient stability are not appropriate for online application, as they suffer from various drawbacks of large computation time (time-domain simulation) and delivering approximate results (direct method). The field of machine learning and soft computing provides a good alternative to the conventional approaches, for transient stability evaluation. Thus, this paper aims to discuss the application of support vector machine (SVM) for predicting the probabilistic transient stability. DIgSILENT PowerFactory was utilised for conducting time-domain simulations (to obtain the training data), and MATLAB was used for support vector regression (SVR) training. For the SVR model, fault type, fault location, fault clearing time, and system load were chosen as the predictors and the transient stability index (TSI) was used as the response. Various regression metrics were computed, for the IEEE 14-bus system, to validate the effectiveness of the proposed approach. The results obtained verify the efficiency of the proposed approach and provide a great potential to be applied for online dynamic security assessment (DSA).
List of Abbreviations
Nomenclature
Table
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Notes on contributors
Umair Shahzad
Umair Shahzad was born in Faisalabad, Pakistan. In 2021, he received the Ph.D. degree in Electrical Engineering from The University of Nebraska-Lincoln, USA, as a Fulbright Scholar. Moreover, he received a B.Sc. Electrical Engineering degree from the University of Engineering and Technology, Lahore, Pakistan, and a M.Sc. Electrical Engineering degree from The University of Nottingham, England, in 2010 and 2012, respectively. His research interests include power system security assessment, power system stability, machine learning, and probabilistic methods applied to power systems.