ML based Voltage Stability Index Prediction
Abstract
Voltage stability assessment plays a crucial role in ensuring the operation of modern power systems, particularly under varying load conditions. conventional voltage stability analysis relies on iterative load flow computations, which are mathematically intensive and unsuitable for everyday applications. This paper proposes an AI - BASED framework for predicting the Voltage Stability Index (VSI) of IEEE-14 bus system using ML models. The dataset was generated using MATPOWER by varying the system loading factor and performing Newton-raphson load flow analysis. System parameters such as loading factor, active power demand, reactive power, and minimum bus voltage were extracted to compute the VSI. The generated dataset was utilized to train and evaluate the proposed ML model. Their performance was evaluated using RMSE, MAE, and R2. Comparative analysis demonstrated that AI - BASED models can predict voltage while significantly reducing the computational time compared to repeated power flow analysis. The proposed framework provides a reliable and computationally efficient solution for real time voltage stability monitoring in smart power systems.