Pradyumna Kumar Sahoo

Performance Comparison for Feed Forward, Elman, and Radial Basis Neural Networks Applied to Line Congestion Study of Electrical Power Systems

This paper presents a comparative analysis of the training performance for three important types of neural networks, namely Feed Forward neural network, Elman neural network, and Radial Basis Function neural network. In order to do this analysis, the authors performed sequential training of all the three neural networks for monitoring the congestion level in the transmission lines of the power system under study. This is accomplished through neural network simulation on the IEEE 30-bus test system under various operating conditions, namely base case, higher loading scenario, and contingency conditions. The findings of this study justify two things. On one hand, the results reveal that all the three neural networks yield successful training and are capable of reducing both the complexity and computational time as compared to the conventional iterative power flow simulation. Furthermore, the comparative analysis justifies that the radial basis function neural network is the fastest of all the three neural networks considered.

Impact analysis of wind power integration in existing power systems for study of voltage stability conditions

Voltage stability conditions during normal operation of existing grids is primarily governed by conventional reactive power management. However, during wind power integration, the integrated system behaves erratically causing lots of concern to the grid operators in evacuating the available power from the wind farms. The major thrust in this paper is to study the impact of voltage stability conditions in existing grid arising out of additional wind power integration. This has been performed by monitoring voltage deviation and L-index at critical buses in the pre-integration and post-integration stages. It is observed that consistency of critical bus bars in terms of location and criticality is largely affected due to the combined actions of load variation and degree of wind power penetration. This has been justified through simulation results of IEEE 30-bus test system and Indian 28-bus system. Further, the results emphasize the need for a rigorous reactive power planning for safe and reliable evacuation of wind power through the existing grid.