Voltage Stability Margin Estimation Using Machine Learning Tools

Real-time voltage stability assessment, via conventional methods, is a difficult task due to the required large amount of information, high execution times and computational cost. Based on these limitations, this technical work proposes method for estimation margin through application artificial intelligence algorithms. For purpose, several operation scenarios are first generated Monte Carlo simulations, considering load variability n-1 security criterion. Afterwards, PV curves determined each scenario obtain database. This information allows structuring data matrix training an neural network support vector machine, in its regression version, predict margin, capable being used real time. The performance prediction tools evaluated mean square error coefficient determination. proposed methodology applied IEEE 14 bus test system, showing so promising results.