通过显式建模周期模式，提升长期时间序列预测精度与效率
CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns
- 用可学习的循环结构捕捉数据中的周期性特征
- 在电力、天气等多领域达到顶尖预测效果，参数量减少90%以上
- 可作为插件模块提升现有模型性能，适配性强
时间序列数据中稳定的周期性模式是实现长时序预测的基础。本文首次探索显式建模此类周期性以提升长时序预测（LTSF）模型性能。提出残差周期预测（RCF）技术，利用可学习的递归循环捕捉序列中的固有周期特征，并对建模后的残差分量进行预测。将RCF与线性层或浅层MLP结合，构建出简单而强大的新方法CycleNet。CycleNet在电力、气象、能源等多个领域实现顶尖预测精度，同时参数量减少超过90%。此外，作为新型即插即用技术，RCF能显著提升PatchTST和iTransformer等现有模型的预测能力。源代码已开源：https://github.com/ACAT-SCUT/CycleNet。
原文摘要 · Abstract (English)
The stable periodic patterns present in time series data serve as the foundation for conducting long-horizon forecasts. In this paper, we pioneer the exploration of explicitly modeling this periodicity to enhance the performance of models in long-term time series forecasting (LTSF) tasks. Specifically, we introduce the Residual Cycle Forecasting (RCF) technique, which utilizes learnable recurrent cycles to model the inherent periodic patterns within sequences, and then performs predictions on the residual components of the modeled cycles. Combining RCF with a Linear layer or a shallow MLP forms the simple yet powerful method proposed in this paper, called CycleNet. CycleNet achieves state-of-the-art prediction accuracy in multiple domains including electricity, weather, and energy, while offering significant efficiency advantages by reducing over 90% of the required parameter quantity. Furthermore, as a novel plug-and-play technique, the RCF can also significantly improve the prediction accuracy of existing models, including PatchTST and iTransformer. The source code is available at: https://github.com/ACAT-SCUT/CycleNet.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。