Empirical mode decomposition based hybrid ensemble model for electrical energy consumption forecasting of the cement grinding process

Abstract

Forecasting the electrical energy consumption of the cement grinding process remains a difficult task due to the intrinsic complexity and irregularity of its time series. To solve this difficulty and improve the prediction accuracy, a novel hybrid model is proposed based on the “decomposition-prediction-integration” methodology. The hybrid model integrates empirical mode decomposition (EMD), moving average filter (MAF), least squares support vector regression (LSSVR), and quadratic exponential smoothing (QES). And it is suitable for non-stationary time series. The proposed model is tested using hourly electrical energy consumption data of one cement grinding process in China. EMD is first applied to decompose the original data series into a limited number of independent intrinsic mode functions (IMFs) and a trend component. Then, MAF is used to reduce the high frequency noises in the IMFs. Next LSSVR is adopted to predict different IMFs, and QES is utilized to predict the trend component. At last, the predicted IMFs and trend component are summed to formulate an ensemble forecast for the original series. The performance of the EMD-LSSVR&QES hybrid model is compared with five other forecasting models. Experiment results indicate that the proposed hybrid ensemble model can give full play to the advantages of each algorithm and outperform other forecasting models.