A novel ensemble deep learning model with dynamic error correction and multi-objective ensemble pruning for time series forecasting

In the past decade, deep learning models have shown to be promising tools for time series forecasting. However, owing to significant differences in the volatility characteristics among different types of time series data, it is difficult for an individual deep learning model to maintain robust forecasting performance. In this study, a novel ensemble deep learning model is proposed to achieve accurate and stable time series forecasting. First, a boosting deep learning method based on extended AdaBoost algorithm is proposed for generating various basic predictors. These basic predictors are further enhanced through a new dynamic error correction method. A stacking-based ensemble method that employs kernel ridge regression as the meta-predictor is then used to combine the basic predictors to produce the ultimate forecasting results. To increase forecasting accuracy and stability, an enhanced multi-population non-dominated sorting genetic algorithm-II is proposed for ensemble pruning. Finally, the forecasting performance of the proposed model is verified through the use of three different types of real-world time series data (i.e., PM2.5 concentration, wind speed, and electricity price). The experimental results showed that the proposed model is superior to other baseline models in dealing with time series forecasting tasks. (C) 2020 Elsevier Inc. All rights reserved.

Automated summary

In this study, a novel ensemble deep learning model is proposed for accurate and stable time series forecasting by generating various basic predictors and enhancing them through a new dynamic error correction method. The model combines basic predictors using a stacking-based ensemble method with kernel ridge regression as the meta-predictor, and an enhanced genetic algorithm is used for ensemble pruning to increase forecasting accuracy and stability. Experimental results showed the superiority of the proposed model in dealing with time series forecasting tasks.