Monitoring Transient Stability in Electric Power Systems Using a Hybrid Model of Convolutional Neural Network and Random Forest

Real-time monitoring of transient stability has gained significant importance in the power system. This paper proposes an advanced hybrid Transient Stability Assessment (TSA) monitoring system, composed of a Convolutional Neural Network (CNN) and Random Forest (RF) classifier which captures the PMU measurements in real-time. CNN utilizes heatmaps for detecting the transient stability status which is hereby used as a feature extractor for the RF classifier. The IEEE-14 and the IEEE-39 bus systems are used as case studies in MATLAB. A wind turbine with a doubly-fed induction generator is also installed to inspect its impact on the power system stability. The efficiency of the system is tested under different contingency scenarios by implementing various faults on distinct locations under dynamic loading conditions. The test results verified that the proposed hybrid CNN-RF (Convolutional Neural Network-Random Forest) model exhibited excellent results in terms of monitoring accuracy, higher precision, and performance in the presence of noise.