EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamic Cost Prediction for State Grid Engineering Projects Based on Multi-Source Business Data Fusion and Data-Driven Methods

Weiqiong Wang, Qidong Xu, Tianyu Zhao, Fang Fang

Information · 16.07.2026 · 17 (7) · 691

DOI: 10.3390/info17070691 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 16.07.2026. Verfasst von Weiqiong Wang und 3 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Research Base Projects of Humanities and Social Sciences in Jiangxi Provincial Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate dynamic cost prediction is essential for budget optimization and risk mitigation in State Grid projects. However, traditional models and even recent deep learning approaches fall short, as they treat cost drivers independently, adopt simplistic concatenation that destroys sourcewise structure, or fail to handle irregularly sampled and partially missing multi-source data. This paper proposes a novel data-driven framework that integrates multi-source business data through a hierarchical tensor fusion mechanism and a hybrid spatiotemporal architecture. The problem is formalized as multivariate time-series prediction with irregular sampling and missing modalities. The framework comprises three synergistic innovations: a differentiable low-rank CANDECOMP/PARAFAC (CP) decomposition layer with adaptive attention weights that preserves cross-source structure while enabling compact dimensionality reduction; a spatiotemporal attention-based bidirectional gated recurrent unit (Bi-GRU) that captures long-range temporal dependencies; and a graph convolutional network (GCN) that explicitly learns interrelations among cost drivers, a capability absent in most existing forecasting methods. The entire system is trained end to end with a customized loss combining mean squared error, quantile loss, and temporal consistency regularization. Extensive experiments on three State Grid substation projects demonstrate that the proposed method outperforms state-of-the-art baselines by 12.7–18.4% in MAPE and maintains robust performance with up to 40% of data missing. These results confirm that explicitly modeling both temporal evolution and driver interdependencies within a unified fusion framework is the key to reliable cost forecasting in large-scale infrastructure projects.

Förderung

  • National Natural Science Foundation of China
  • Key Research Base Projects of Humanities and Social Sciences in Jiangxi Provincial Universities

Zitieren

APA

Wang, W., Xu, Q., Zhao, T., & Fang, F. (2026). Dynamic Cost Prediction for State Grid Engineering Projects Based on Multi-Source Business Data Fusion and Data-Driven Methods. Information, 17(7), 691. https://doi.org/10.3390/info17070691

Vancouver

Wang W, Xu Q, Zhao T, Fang F. Dynamic Cost Prediction for State Grid Engineering Projects Based on Multi-Source Business Data Fusion and Data-Driven Methods. Information. 2026;17(7):691. doi:10.3390/info17070691

BibTeX
@article{Wang2026,
  author = {Wang, Weiqiong and Xu, Qidong and Zhao, Tianyu and Fang, Fang},
  title = {Dynamic Cost Prediction for State Grid Engineering Projects Based on Multi-Source Business Data Fusion and Data-Driven Methods},
  journal = {Information},
  year = {2026},
  volume = {17},
  number = {7},
  pages = {691},
  doi = {10.3390/info17070691}
}
Kostenlos starten →