Artificial Neural Net Based Performance Index for Voltage Security Assessment

A novel, uncomplicated and cursory process of transmission line outage analysis and evaluation for voltage security assessment is developed for real-time power system monitoring applications. The implied approach uses the bus voltage magnitudes to develop artificial-neural-network models to monitor the bus voltages in the power network and provide outputs in binary form signifying the power network state. These models of developed neural networks can then monitor the bus voltage magnitudes in real-time, to minimize the time taken in decision making process for the power system control operations. The binary outputs of the monitoring neural net are utilized to calculate an index to determine the state of the voltage security of the power network-grid, proposed in this papers work. The proposed approach was applied to a test bus system and a government-owned utility. The results are compared with the traditional method of voltage security assessment and ranking. The results testify that the proposed method will furnish good precision and interpretability with faster response and are apt for on-line voltage security assessment. The utilization of advanced computers with good memory reduces time consumption and provides results within 9 min. Also, the critical contingencies can be detected in a matter of seconds.