A Hybrid Method of Clipping and Artificial Neural Network for Electricity Price Zone Forecasting

This paper proposes a new method for electricity price zone forecasting. The proposed method makes use of the clipping technique that is one of data mining techniques for simplifying the relationship between input and output variables. It expresses an output variable in binary number. Electricity price forecasting is difficult to handle due to the nonlinearity of time series. This paper predicts the one-step-ahead price zone. In this paper, the normalized radial basis function network is used as an artificial neural network (ANN) to evaluate the predicted price. The proposed method is tested for the electricity price in the New England power market