EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Encoder-Enhanced Autoformer for Multi-Scale Parking Availability Forecasting

Chao Zeng, Changhao Zhao, Xiaoting Huang, Changxi Ma

Systems · 23.07.2026 · 14 (8) · 888

DOI: 10.3390/systems14080888 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Systems, online erschienen am 23.07.2026. Verfasst von Chao Zeng und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chongqing Social Science Planning Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Parking space availability forecasting is challenging due to noise contamination, non-stationary dynamics, and complex multi-scale temporal dependencies. This study proposes a wavelet-enhanced Autoformer with dynamic multi-kernel decomposition for parking space availability forecasting. Discrete wavelet transform is used to enhance the input sequence by suppressing high-frequency disturbances while preserving the dominant temporal structure. Within the Autoformer framework, a dynamic multi-kernel decomposition module is developed by introducing multiple moving-average kernels with different scales and an input-dependent dynamic weighting mechanism, enabling the adaptive decomposition and fusion of trend and fluctuation components and thereby improving the representation of complex multi-scale temporal patterns. The proposed framework is evaluated using real parking operation data collected from the Liangshan Jingyuan parking lot in Chongqing, China, including 1248 observations with a 2 h sampling interval. Multi-step forecasting experiments are conducted under short-, medium-, and long-term prediction settings with different label-length configurations. Across different forecasting horizons and label-length settings, the proposed model consistently outperforms the original Autoformer, PatchTST, and a range of conventional and recent forecasting baselines. In particular, under the 24-step forecasting setting, the proposed method reduces MAE, RMSE, and WMAPE by approximately 10% relative to the original Autoformer. Moreover, the results suggest that the dynamic multi-kernel mechanism improves the model’s ability to adaptively capture scale-dependent temporal patterns across different forecasting tasks.

Förderung

  • Chongqing Social Science Planning Project

Zitieren

APA

Zeng, C., Zhao, C., Huang, X., & Ma, C. (2026). An Encoder-Enhanced Autoformer for Multi-Scale Parking Availability Forecasting. Systems, 14(8), 888. https://doi.org/10.3390/systems14080888

Vancouver

Zeng C, Zhao C, Huang X, Ma C. An Encoder-Enhanced Autoformer for Multi-Scale Parking Availability Forecasting. Systems. 2026;14(8):888. doi:10.3390/systems14080888

BibTeX
@article{Zeng2026,
  author = {Zeng, Chao and Zhao, Changhao and Huang, Xiaoting and Ma, Changxi},
  title = {An Encoder-Enhanced Autoformer for Multi-Scale Parking Availability Forecasting},
  journal = {Systems},
  year = {2026},
  volume = {14},
  number = {8},
  pages = {888},
  doi = {10.3390/systems14080888}
}
Kostenlos starten →