Forecasting the hourly Ontario energy price by local linear wavelet neural network and ARMA models

Abstract

Price forecasting has become one of the main focus of electric power market research efforts since price is the key index to evaluate the market competition efficiency and reflects the operation condition of electricity market decision making. The work presented in this paper makes use of local linear wavelet neural networks (LLWNN) & ARMA to find the market price for a given period, with a certain confidence level. The results of the new method show significant improvement in the price forecasting process.