A multivariate forecasting method for short-term load using chaotic features and RBF neural network

This paper presents a multivariate forecasting method for electric short-term load using chaos theory and radial basis function (RBF) neural networks. To apply the method, the largest Lyapunov exponent and correlation dimension are firstly calculated which show the electric load series is essentially a chaotic time series. Then, a multivariate chaotic prediction method is proposed taking historical load and temperature into account. Phase space reconstruction of a univariate time series is extended to construct a multivariate time series. Delay time and embedding dimension of the historical load series and temperature series are determined by mutual information and minimal forecasting error, respectively. Finally, a three-layer RBF neural network is employed to forecast the load of one day ahead and one week ahead. Real load data of Chongqing Power Grid are tested. Daily and weekly forecasting results show that the proposed multivariate approach improves the accuracy of forecasting significantly comparing with the univariate methods. Discussion of forecasting error and future work are also presented. As an efficient and effective alternative for STLF, the chaos theory based multivariate forecasting is feasible for potential application. Copyright © 2010 John Wiley & Sons, Ltd.