This study presents a novel time series prediction model, FPN-fusion,
designed with linear computational complexity, demonstrating superior
predictive performance compared to DLiner without increasing parameter count or
computational demands. Our model introduces two key innovations: first, a
Feature Pyramid Network (FPN) is employed to effectively capture time series
data characteristics, bypassing the traditional decomposition into trend and
seasonal components. Second, a multi-level fusion structure is developed to
integrate deep and shallow features seamlessly. Empirically, FPN-fusion
outperforms DLiner in 31 out of 32 test cases on eight open-source datasets,
with an average reduction of 16.8% in mean squared error (MSE) and 11.8% in
mean absolute error (MAE). Additionally, compared to the transformer-based
PatchTST, FPN-fusion achieves 10 best MSE and 15 best MAE results, using only
8% of PatchTST's total computational load in the 32 test projects.

本研究提出了一种新颖的时间序列预测模型，FPN-fusion，具有线性计算复杂度，相比于 DLiner 具有更优越的预测性能而无需增加参数数量或计算需求。我们的模型引入了两个关键创新：首先，采用特征金字塔网络（FPN）有效地捕捉时间序列数据的特征，避免了传统趋势和季节分解；其次，开发了一个多层融合结构，无缝地整合深层和浅层特征。在八个开源数据集上的 32 个测试案例中，FPN-fusion 在 31 个案例中表现优于 DLiner，平均均方误差 (MSE) 减少 16.8% 和平均绝对误差 (MAE) 减少 11.8%。此外，与基于 Transformer 的 PatchTST 相比，FPN-fusion 在 32 个测试项目中实现了 10 个最佳 MSE 结果和 15 个最佳 MAE 结果，仅使用了 PatchTST 总计算负载的 8%。