Guo Chen, Kang Xumin, Xiong Jianping, Wu Jianhua
School of Information Engineering, Nanchang University, Nanchang, 330031 China.
Industrial Center, Shenzhen Polytechnic, Shenzhen, 518055 China.
Neural Process Lett. 2022 Oct 7:1-21. doi: 10.1007/s11063-022-11046-7.
In this paper, a new hybrid time series forecasting model based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and a temporal convolutional network (TCN) (CEEMDAN-TCN) is proposed. The CEEMDAN is used to decompose the time series data and the TCN is used to obtain a good prediction accuracy. The effectiveness of the model is verified in univariate and multivariate time series forecasting tasks. The experimental results indicate that compared with the long short-term memory model and other hybrid models, the proposed CEEMDAN-TCN model shows a better performance in both univariate and multivariate prediction tasks.
本文提出了一种基于自适应噪声完备总体经验模态分解（CEEMDAN）和时间卷积网络（TCN）的新型混合时间序列预测模型（CEEMDAN-TCN）。CEEMDAN用于分解时间序列数据，TCN用于获得良好的预测精度。该模型的有效性在单变量和多变量时间序列预测任务中得到了验证。实验结果表明，与长短期记忆模型和其他混合模型相比，所提出的CEEMDAN-TCN模型在单变量和多变量预测任务中均表现出更好的性能。
