Application of grey predictor model for forecasting flicker severity associated with electric arc furnace load

It is known that rapid voltage fluctuations caused by electric arc furnace loads may generate significant levels of flickers, which have negative impacts to human eyes and power system components. This paper proposes a grey predictor model for the forecast of flicker levels produced by an electric arc furnace load. Actual measured data are adopted to implement the predictor model. Test results based on the proposed model are compared with two other neural network methods. It shows that more accurate forecast is achieved for the flicker prediction based on the proposed method.