基于分解和频域特征提取的多变量长时间序列预测模型

Multivariate long-term series forecasting model based on decomposition and frequency domain feature extraction

针对现有基于Transformer的多变量长时间序列预测(MLTSF)模型主要从时域中提取特征,难以直接从长时间序列分散的时间点中找出可靠依赖关系的问题,提出一种新的基于分解和频域特征提取的模型。首先,提出基于频域的周期项-趋势项的分解方法,以降低分解过程的时间复杂度;其次,在利用周期项-趋势项分解提取序列趋势性特征的基础上,利用基于Gabor变换进行频域特征提取的Transformer网络捕捉周期性的依赖,提高预测的稳定性和鲁棒性。在5个基准数据集上的实验结果显示,与现有的先进方法相比,所提模型在MLTSF上的均方误差(MSE)平均减小了7.6%,最多减小了18.9%,有效提升了预测精度。

In response to the problems that the existing Transformer-based Multivariate Long-Term Series Forecasting(MLTSF)models mainly extract features from the time domain,and it is difficult to find out reliable dependencies directly from the dispersed time points of the long-term series,a new decomposition and frequency domain feature extraction model was proposed.Firstly,a periodic term-trend term decomposition method based on the frequency domain was proposed,which reduced the time complexity of the decomposition process.Then,based on the extraction of trend features using periodic term-trend term decomposition,a Transformer network performing frequency domain feature extraction based on Gabor transform was utilized to capture periodic dependencies,which enhanced the stability and robustness of forecasting.Experimental results on five benchmark datasets show that compared with the current state-of-the-art methods,the proposed model has the Mean Squared Error(MSE)in MLTSF is reduced by an average of 7.6%with a maximum reduction of 18.9%,which demonstrates that the proposed model improves forecasting accuracy effectively.