Artificial Neural Network Approach for Fault Detection and Identification in Power Systems with Wide Area Measurement Systems.

This paper presents a fault detection and identification system for power systems using an artificial neural network approach while discussing its advantages and disadvantages. The initial data for the proposed technique are a set of simulated post-fault bus voltages and currents obtained at a sampling rate which emulates a complete phasor measurement unit (PMU)-based wide area measurement system (WAMS). Several types of faults are considered, such as short circuits and line and load contingencies. All fault and steady-state simulations have been performed on MATLAB using the Power System Toolbox. The artificial neural network was designed using an architecture proper for pattern recognition with supervised learning. As a result, satisfactory predictions within short time periods are obtained. The test system used in all simulations is the IEEE 39-Bus New England Power System, which has 10 generation units, 21 loads, and three distinct areas alongside transient and sub transient models, with PMUs distributed over up to 14 buses. Future works are also discussed in this paper, showing the possibilities for feature engineering in this type of problem, as well as the application of other machine learning and data analytics techniques for PMU-based WAMS databases. [ABSTRACT FROM AUTHOR]