Multi-Temporal Hierarchical Natural Gas Demand Forecasting Framework for Power Generation Infrastructure: Integrating Variational Mode Decomposition with Deep Learning

This seed project focuses on developing accurate, multi-scale prediction of natural gas demand for power generation—at the generator unit, power plant, and aggregated city and state levels. Its importance lies in both technical innovation and strategic national relevance.

• Record URL:
  • https://www.ctips.org/projects/details.php?id=671

Language

• English

Project

• Status: Active
• Funding: $204,426.00
• Contract Numbers:

  69A3552348308

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  Center for Transformative Infrastructure Preservation and Sustainability

  North Dakota State University
  Fargo, North Dakota  United States  58108-6050
• Performing Organizations:

  Upper Great Plains Transportation Institute

  North Dakota State University
  1320 Albrecht Boulevard
  Fargo, ND  United States  581052
• Principal Investigators:

  Lu, Pan

  Yang, Xinyi

• Start Date: 20260828
• Expected Completion Date: 20291130
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program
• Source Data: CTIPS-073

Subject/Index Terms

• TRT Terms: Deep learning; Demand; Electric power generation; Natural gas; Predictive models
• Subject Areas: Data and Information Technology; Energy; Planning and Forecasting; Transportation (General);

Filing Info

• Accession Number: 02001759
• Record Type: Research project
• Source Agency: Center for Transformative Infrastructure Preservation and Sustainability
• Contract Numbers: 69A3552348308
• Files: UTC, RIP
• Created Date: Sep 3 2026 4:13PM