In order to address the challenges of long-and short-term dependencies in time series forecasting,while capturing both long-term trends and short-term dynamics,and to model the complex interdependencies among variables in multivariate time series,a forecasting method based on the temporal convolutional network (TCN) was proposed. Initially,the TCN was employed to effectively capture the features of sequence variables across time scales,and subsequently,the squeeze-and-excitation block (SE_Block) was applied to the outputs of the TCN. This module was used to enhance the representation of multivariate variables,resolve short-term dependency issues,and improve the model’s ability to capture critical short-term information. Secondly,the Informer model was introduced to enhance the long-sequence processing capability,which not only effectively addressed the computational efficiency issue in long-sequence forecasting but also strengthened the model’s ability to capture global temporal dependencies. Finally,the proposed method was experimentally validated and compared with existing time series models on three datasets: equipment state monitoring(ETTm1),traffic flow (Traffic),and electricity load (Electricity). The results show that the proposed method exhibits lower error rates in both long-and short-term time series forecasting. It is concluded that the proposed method can effectively improve the forecasting performance for multivariate time series in both long-and short-term domains.
LI De-quan, JIANG Tao.
Long-and Short-term Multivariate Time Series Forecasting Based on TCN-Informer[J].
Science Technology and Engineering, 2026, 26(4): 1549-1557 DOI:10.12404/j.issn.1671-1815.2501107
LiJiayuan, WangXiaodong, HeQixue. Application and performance optimization of CNN-enhanced informer model in industrial time series forecasting[J]. Computer Applications, 2024, 44(S2): 79-83.
[7]
WangY, PengJ, WangX, et al. Replacing self-attentions with convolutional layers in multivariate long sequence time-series forecasting[J]. Applied Intelligence, 2024, 54(1): 522-543.
ChenZhenyu, LiuJinbo, LiChen, et al. Ultra short-term power load forecasting based on combined LSTM-XGBoost model[J]. Power System Technology, 2020, 44(2): 614-620.
QinHui, LiWei, LiuWenjiao, et al. Research onshort-term photovoltaic power forecasting technology based on ESMD-SVM[J]. Journal of Engineering for Thermal Energy and Power, 2022, 37(10): 189-197.
[12]
HengS, MinghaoX, RanL. Deep learning for household load forecasting: a novel pooling deep RNN[J]. IEEE Transactions on Smart Grid, 2018, 9(5): 5271-5280.
[13]
WanR, MeiS, WangJ, et al. Multivariate temporal convolutional network: a deep neural networks approach for multivariate time series forecasting[J]. Electronics, 2019, 8(8): 876.
ZhaoXingyu, WuQuanjun, ZhuWei, et al. Short-term power load forecasting based on CEEMDAN and TCN-LSTM model[J]. Science Technology and Engineering, 2023, 23(4): 1557-1564.
[16]
VaswaniA, ShazeerN, ParmarN, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017, 30: 6000-6010.
[17]
Kitaev N, KaiserŁ Levskaya A. Reformer: the efficient transformer[J]. arXiv Preprint, arXiv: 2001.04451, 2020.
SunChao, LüQi, ZhuSitong, et al. Ultra-short-term power load forecasting based on two-layer XGBoost algorithm considering the influence of multiple features[J]. High Voltage Engineering, 2021, 47(8): 2885-2898.
SongRuirong, WangBinjun, TongXin, et al. Traffic flow forecasting model based on multi-dimensional spatial and temporal characteristics[J]. Science Technology and Engineering, 2021, 21(31): 13439-13446.
[24]
ZhouK, ZhangC, XuB, et al. TE-LSTM: a prediction model for temperature based on multivariate time series data[J]. Remote Sensing, 2024, 16(19): 3666.
BaiWenrui, YangYiqiang, ZhuXueqin. Water quality prediction model based on VMDLSTNet[J]. Science Technology and Engineering, 2022, 22(22): 9881-9889.
[27]
LiS, JinX, XuanY, et al. Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting[C]// 32nd Conference on Neural Information Processing Systems. Vancouver: ACM, 2019: 8-14.