Hybrid ANN methods to reduce the sheath current effects in high voltage underground cable line

Abstract

The sheath current generates on metal sheath of underground cable, and it causes cable faults, electroshock risk and reducing of cable performance in high voltage underground cable line. Therefore, the sheath current must be reduced, and if the sheath current can be determined before high voltage underground line is installed, the required precautions can be taken to reduce the sheath current. Hence, cable faults and electroshock risk are prevented, and cable performance increases. In this study, simulations of high voltage underground cable line are made in PSCAD/EMTDC, and the sheath current is forecasted by using hybrid artificial neural network (ANN) method. Differential evolution algorithm (DEA) and particle swarm optimization (PSO) are used to generate hybrid ANN method. The results of hybrid ANN method are better than classic ANN, and the results of DEA-ANN method are better than PSO-ANN. Also DEA-ANN can be used in forecasting studies.