Normalized RBFN with Hierarchical Deterministic Annealing Clustering for Electricity Price Forecasting

In this paper, an efficient artificial neural network (ANN) based method is proposed for electricity price forecasting. ANN is effective for approximating any nonlinear functions. This paper makes use of normalized radial basis function network (NRBFN) that is the extension of RBFN. A clustering technique is used to determine the center of RBFN and NRBFN. In this paper, hierarchical deterministic annealing (HDA) that extends deterministic annealing (DA) is proposed to determine the center of the radial basis function. This paper focuses on the efficient clustering method that globally optimizes the clusters. The proposed method of NRBFN with HDA is compared with other methods in terms of model accuracy and computational time. The effectiveness of the proposed method is demonstrated for real data of hourly electricity price for ISO New England.