Voltage stability assessment in restructured environment

Abstract

Due to continuous increase in load demand, power utilities are forced to enhance the utilization of existing transmission facilities. It is quite difficult to construct new transmission lines due to environmental and economic considerations. As power systems become more complex and heavily loaded, along with environmental and economical constraints have forced operation of power systems near to their operating boundaries. Under such situations, a power system enters a state of voltage instability, which results in a progressive and an uncontrollable voltage decline leading to voltage collapse. Voltage collapse is a major cause for many power system blackouts around the world and voltage instability tends to occur from lack of reactive power supports In order to prevent the occurrence of voltage collapse, it is essential a fast and accurate voltage stability index to help them for monitoring the voltage stability condition of a power system and enhancing the voltage stability when the system enters near the unstable condition. Therefore, this research work presents a new methodology for the estimating of voltage stability margin as well as adequate VAR support providing for enhancing voltage stability margin of power system based on Artificial Neural Network (ANN), Support Vector Machine (SVM), Fuzzy Logic Controller (FLC). Particle Swarm Optimization (PSO) and Support Vector Regression (SVR). The objectives of the thesis work are 1. To assess the Voltage Stability Margin (VSM) of power system using proper input features of Artificial Neural Network (ANN). 2. To use the determined input features for estimating the voltage stability margin using Support Vector Machine (SVM). 3. To assess online voltage stability margin using ANN and Fuzzy Logic Controller (FLC) and study the improvement. 4. To predict and improve the VSM of a power system in a restructured environment using combined Support Vector Regression (SVR) and FLC. 5. To optimize the parameters of the SVM using Particle Swarm Optimization (PSO) and to assess the VSM in the deregulated power system. newline newline newline