Power System Security Assessment and Contingency Analysis using Supervised Learning Approach.

Abstract

The most important requirement and need for proper operation of power system is maintenance of the system security. The security assessment analysis is done to determine until what period the power system remains in the safe operable mode. Contingency screening is done to identify critical contingencies in order to take preventive actions at the right time. The severity of a contingency is determined by two scalar performance indices: Voltage-reactive power performance index(𝑃𝐼𝑣𝑞) and line MVA performance index(𝑃𝐼𝑚𝑣𝑎). Performance indices are calculated based on the conventional method known as Newton Raphson load flow program. Contingency ranking is done based on the severity of the contingencies. In this proposed work, contingency analysis is done with IEEE 14 bus. Since the system parameters are dynamic in nature and keeps on changing, there is need of soft computing technologies. Supervised learning approach that uses Feed-Forward Artificial Neural Network(FFNN) is employed using pattern recognition methodology for security assessment and contingency analysis. A feature selection technique based on the correlation coefficient has been employed to identify the inputs for thee FFNN. With these soft computing techniques, greater accuracy is achieved