Study of Different ANN Algorithms for Voltage Stability Analysis

Aydın F., Gumus B.

Akıllı Sistemlerde Yenilikler ve Uygulamaları Konferansı (ASYU) 2020, İstanbul, Türkiye, 15 Ekim 2020 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/asyu50717.2020.9259817
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: artificial neural network, continuation power flow, training functions, voltage stability
  • Marmara Üniversitesi Adresli: Evet

Özet

Nowadays, voltage instability and voltage collapse have become the main issues studied in electrical power systems. The determination of the voltage security of a power system is not an easy task. It is a complex process which consumes a lot of time. In this paper, it was shown that Artificial Neural Network (ANN) can achieve the same results with high accuracy and quickly as conventional voltage stability calculation methods. For this purpose, loading parameter and Voltage Stability Margin Index (VSMI) were calculated using 8 different input variables and 14 different training functions. The proposed approach was carried out using the Power System Analysis Toolbox (PSAT) in MATLAB in the IEEE 57-bus test system. In the voltage stability problem, the most suitable parameters to be used in ANN have been found and the results of the application are promising.