Enhancement of Power System Stability by Optimal Adaptive Under Frequency Load Shedding Using Artificial Neural Networks
Power system frequency is a continuously changing variable which is a function of system generation and supply. Different short circuits, load growth, generation shortages and other faults disturb the voltage and frequency stabilities. This instability causes dispersal of a power system into sub-systems and leads to blackout as well as heavy damages of the system equipment. To control this frequency drop and to maintain system frequency, appropriate amount of load must be intentionally and automatically curtailed. In the modern power systems operating at lower stability margins, conventional non-adaptive schemes cannot offer adequate protection for securing the power system. In this paper, a fast and optimal adaptive load shedding method is presented using artificial neural networks (ANN). Adaptive schemes take into account the actual system state and topology, nature and magnitude of the disturbance. This method is able to determine the necessary load shedding in all steps simultaneously and is much faster than conventional methods. This has been tested in IEEE 39 bus system and the simulations are done in MATLAB platform. Apart from the proposed ANN method, an advanced methodology called Adaptive Neuro Fuzzy Inference System (ANFIS) has been used to predict the optimal amount of load shedding amount for any range of input values and to derive a better output.
Emmy Kuriakose, Filmy Francis