Recently, Transformer-based models have shown remarkable performance in long-term time series forecasting (LTSF) tasks due to their ability to model long-term dependencies. However, the validity of Transformers for LTSF tasks remains debatable, particularly since recent work has shown that simple linear models can outperform numerous Transformer-based approaches. This suggests that there are limitations to the application of Transformer in LTSF. Therefore, this paper investigates three key issues when applying Transformer to LTSF: temporal continuity, information density, and multi-channel relationships. Accordingly, we propose three innovative solutions, including Placeholder Enhancement Technique (PET), Long Sub-sequence Division (LSD), and Multi-channel Separation and Interaction (MSI), which together form a novel model called PETformer. These three key designs introduce prior biases suitable for LTSF tasks. Extensive experiments have demonstrated that PETformer achieves state-of-the-art (SOTA) performance on eight commonly used public datasets for LTSF, outperforming all other models currently available. This demonstrates that Transformer still possesses powerful capabilities in LTSF.

翻译：近期，基于Transformer的模型因能够建模长期依赖关系，在长期时间序列预测（LTSF）任务中展现出卓越性能。然而，Transformer在LTSF任务中的有效性仍存在争议，特别是近期研究表明，简单的线性模型可超越众多基于Transformer的方法。这表明Transformer在LTSF中的应用存在局限性。为此，本文研究了将Transformer应用于LTSF时的三个关键问题：时间连续性、信息密度和多通道关系。据此，我们提出三种创新解决方案，包括占位增强技术（PET）、长序列划分（LSD）和多通道分离与交互（MSI），三者共同构成名为PETformer的新模型。这三个关键设计引入了适用于LTSF任务的先验偏差。大量实验证明，PETformer在八个常用公开LTSF数据集上均达到当前最优（SOTA）性能，优于所有现有模型。这表明Transformer在LTSF领域仍具备强大能力。