Journal
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
Volume 121, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.engappai.2023.106042
Keywords
Time series forecasting; Time series decomposition; Causal convolution; Locally grouped auto-correlation; Transformer
Ask authors/readers for more resources
Improving the performance of long-term time series forecasting is crucial for real-world applications. In this paper, we propose a Transformer-based model called CLformer, which integrates a time series decomposition method to extract short and long-term time patterns in more predictable components. Experimental results show that CLformer outperforms models using global autocorrelation and self-attention mechanisms in terms of efficiency and accuracy.
Improving the performance of long-term time series forecasting is important for real-world applications. Recently, Transformer-based models have achieved significant performance gains in long-term time series prediction. However, these models are memory-intensive and cannot capture temporal patterns at multiple scales. To this end, we propose to integrate the time series decomposition method in the Transformer framework to enable the model to extract short-and long-term time patterns in more predictable seasonal and trend components. In this paper, we propose a Transformer-based model named CLformer. Different from previous methods, we exploit dilated convolutional networks to capture and refine multiple temporally repeated patterns in time series before time series decomposition. To enable the model to capture the depen-dencies at multiple scales, we propose a local group autocorrelation (LGAC) mechanism. The LGAC mechanism calculates autocorrelation within time series segments, strengthening the model's ability to capture the local temporal dynamics of series. The stacking of multiple LGAC layers enables the model to capture multi-scale dependencies, which in turn improves the model's predictive performance. The CLformer outperforms models using the global autocorrelation mechanism and self-attention in both efficiency and accuracy. Experimental results on six benchmark datasets show that our model obtains a relative performance improvement of 11.75% compared to the state-of-the-art methods. In addition, CLformer achieves a relative performance improvement of 18.89% on two datasets without apparent periodicity, demonstrating the effectiveness of our model on time series without significant periodicity.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available