Adaptive-neuro-fuzzy inference system approach for transmission line fault classification and location incorporating effects of power swings

In the present milieu, changes in regulations and the opening of power markets have manifested in the form of large amount of power transfer across transmission lines with frequent changes in loading conditions based on market price. Since conventional distance relays may consider power swing as a fault, tripping because of such malfunctioning would lead to serious consequences for power system stability. A frequency domain approach for digital relaying of transmission line faults mitigating the adverse effects of power swing on conventional distance relaying is presented. A wavelet-neuro-fuzzy combined approach for fault location is also presented. It is different from conventional algorithms that are based on deterministic computations on a well-defined model for transmission line protection. The wavelet transform captures the dynamic characteristics of fault signals using wavelet multi-resolution analysis (MRA) coefficients. The fuzzy inference system (FIS) and the adaptive-neuro-fuzzy inference system (ANFIS) are both used to extract important features from wavelet MRA coefficients and thereby to reach conclusions regarding fault location. Computer simulations using MATLAB have been conducted for a 300 km, 400 kV line and results indicate that the proposed localisation algorithm is immune to effects of fault inception, angle and distance. The results contained here validate the superiority of the ANFIS approach over the FIS for fault location.