Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2506.12800 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908408587747328 |
|---|---|
| author | Huang, Shaoyuan Zhang, Tiancheng Zhang, Zhongtian Wang, Xiaofei Wang, Lanjun Wang, Xin |
| author_facet | Huang, Shaoyuan Zhang, Tiancheng Zhang, Zhongtian Wang, Xiaofei Wang, Lanjun Wang, Xin |
| contents | Time series forecasting is a critical and practical problem in many real-world applications, especially for industrial scenarios, where load forecasting underpins the intelligent operation of modern systems like clouds, power grids and traffic networks.However, the inherent complexity and dynamics of these systems present significant challenges. Despite advances in methods such as pattern recognition and anti-non-stationarity have led to performance gains, current methods fail to consistently ensure effectiveness across various system scenarios due to the intertwined issues of complex patterns, concept-drift, and few-shot problems. To address these challenges simultaneously, we introduce a novel scheme centered on fundamental waveform, a.k.a., meta-pattern. Specifically, we develop a unique Meta-pattern Pooling mechanism to purify and maintain meta-patterns, capturing the nuanced nature of system loads. Complementing this, the proposed Echo mechanism adaptively leverages the meta-patterns, enabling a flexible and precise pattern reconstruction. Our Meta-pattern Echo transformer (MetaEformer) seamlessly incorporates these mechanisms with the transformer-based predictor, offering end-to-end efficiency and interpretability of core processes. Demonstrating superior performance across eight benchmarks under three system scenarios, MetaEformer marks a significant advantage in accuracy, with a 37% relative improvement on fifteen state-of-the-art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12800 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MetaEformer: Unveiling and Leveraging Meta-patterns for Complex and Dynamic Systems Load Forecasting Huang, Shaoyuan Zhang, Tiancheng Zhang, Zhongtian Wang, Xiaofei Wang, Lanjun Wang, Xin Machine Learning Time series forecasting is a critical and practical problem in many real-world applications, especially for industrial scenarios, where load forecasting underpins the intelligent operation of modern systems like clouds, power grids and traffic networks.However, the inherent complexity and dynamics of these systems present significant challenges. Despite advances in methods such as pattern recognition and anti-non-stationarity have led to performance gains, current methods fail to consistently ensure effectiveness across various system scenarios due to the intertwined issues of complex patterns, concept-drift, and few-shot problems. To address these challenges simultaneously, we introduce a novel scheme centered on fundamental waveform, a.k.a., meta-pattern. Specifically, we develop a unique Meta-pattern Pooling mechanism to purify and maintain meta-patterns, capturing the nuanced nature of system loads. Complementing this, the proposed Echo mechanism adaptively leverages the meta-patterns, enabling a flexible and precise pattern reconstruction. Our Meta-pattern Echo transformer (MetaEformer) seamlessly incorporates these mechanisms with the transformer-based predictor, offering end-to-end efficiency and interpretability of core processes. Demonstrating superior performance across eight benchmarks under three system scenarios, MetaEformer marks a significant advantage in accuracy, with a 37% relative improvement on fifteen state-of-the-art baselines. |
| title | MetaEformer: Unveiling and Leveraging Meta-patterns for Complex and Dynamic Systems Load Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.12800 |