Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 32 min ago
Peer-reviewedCC BY 4.0PLOS One

A forecast-to-dispatch workflow for day-ahead operation of a regional natural gas transmission network based on station-level load prediction and linepack target setting

  • Ying Liu1
  • Yong Xiao2
  • Zhiping Tang3
  • Simin Zhong4
  • Chenguang Yong5
  • Yuanyuan Tian
5 affiliations
  1. 1Surface Engineering Design Center, PetroChina Southwest Oil & Gasfield Company, Chengdu, China
  2. 2Development and Planning Department, China National Petroleum Corporation, Beijing, China
  3. 3Gas Field Development and Management Department, PetroChina Southwest Oil & Gasfield Company, Chengdu, China
  4. 4Gas Distribution and Transmission Management Department, PetroChina Southwest Oil & Gasfield Company, Chengdu, China
  5. 5Kunlun Digital Technology Co., Ltd., Beijing, China
Open at sourcePDFDOICite

Abstract

Day-ahead operation of regional natural gas transmission networks requires station demand forecasts and their translation into inventory-preparation references. This study evaluated a sequential forecast-to-dispatch workflow for the Chongqing regional gas network. Six forecasting models were assessed under a leakage-controlled 30-day walk-forward protocol. Across nine routine stations, mean station-level MAPE was 8.61% for SARIMAX, 8.95% for XGBoost, and 9.78% for GRU. The corresponding values were 10.93% for LSTM, 11.63% for BPNN, and 11.77% for CNN-BiLSTM-Attention. Station G was assessed separately as a data-quality boundary case; Station K was excluded because only 62 observations were available. An independent archived 18-day hourly dataset reported reconstruction MAPE of 6.7%−8.1% and peak-timing deviations of 1.0–1.5 h. A retrospective West-pipeline case for 22 April 2023 traced historical station forecasts through weighted aggregation, intermediate rounding, hourly reconstruction, and reduced-order linepack calculation. Its LFFX preparation target and the separate NGXDD and DLFX targets were 1.272, 4.702, and 1.571 × 10⁶ m³, respectively. All three targets passed case-specific deterministic inventory checks. The results support station-specific forecast-model selection and an explicit interface between daily prediction and segment-level inventory preparation.

Related

  1. The Noise-Transmission Burden of Diffusion Network: Why Image Prediction Can Outperform Noise Prediction
    Gyeonghun Kang, Pengxi Liu, Bingshuo Qian +1
    arXivPreprintCC BY 4.0Full textStatisticsarXiv
  2. Readiness-Constrained Pre-Islanding Dispatch for Military Microgrids
    Aidan Looney, Annie Weathers, Nicholas Judson
    arXivPreprintarXiv licenceFull textOptimisation & controlarXiv
  3. Fixed Hall-Call Assignments and Floor-Ordered Pair Costs in Elevator Dispatch
    JangHo Seo, Joonwoo Lee
    MathematicsPeer-reviewedCC BY 4.0General mathematicsCrossref
  4. Privacy-Preserving Distributed Online Dispatch of Low-Carbon Microgrids with TCN–BiLSTM Probabilistic Photovoltaic Forecasts
    Chen Zhang, Zhongyuan Zhao
    MathematicsPeer-reviewedCC BY 4.0General mathematicsCrossref
  5. A Memory-Assisted Self-Adaptive Bonobo Optimizer for Economic Dispatch with Valve-Point Effects Including Combined Heat and Power Units
    Ahmed Daeli, Ghareeb Moustafa, Hashim Alnami +3
    MathematicsPeer-reviewedCC BY 4.0General mathematicsCrossref

Cite

BibTeXRIS
BibTeX
@article{liu2026forecasttodispatch,
  title = {{A forecast-to-dispatch workflow for day-ahead operation of a regional natural gas transmission network based on station-level load prediction and linepack target setting}},
  author = {Ying Liu and Yong Xiao and Zhiping Tang and Simin Zhong and Chenguang Yong and Yuanyuan Tian},
  journal = {PLOS One},
  year = {2026},
  month = oct,
  doi = {10.1371/journal.pone.0349981},
  url = {https://doi.org/10.1371/journal.pone.0349981},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - A forecast-to-dispatch workflow for day-ahead operation of a regional natural gas transmission network based on station-level load prediction and linepack target setting
AU  - Ying Liu
AU  - Yong Xiao
AU  - Zhiping Tang
AU  - Simin Zhong
AU  - Chenguang Yong
AU  - Yuanyuan Tian
PY  - 2026
DA  - 2026/10/05
JO  - PLOS One
DO  - 10.1371/journal.pone.0349981
UR  - https://doi.org/10.1371/journal.pone.0349981
AB  - Day-ahead operation of regional natural gas transmission networks requires station demand forecasts and their translation into inventory-preparation references. This study evaluated a sequential forecast-to-dispatch workflow for the Chongqing regional gas network. Six forecasting models were assessed under a leakage-controlled 30-day walk-forward protocol. Across nine routine stations, mean station-level MAPE was 8.61% for SARIMAX, 8.95% for XGBoost, and 9.78% for GRU. The corresponding values were 10.93% for LSTM, 11.63% for BPNN, and 11.77% for CNN-BiLSTM-Attention. Station G was assessed separately as a data-quality boundary case; Station K was excluded because only 62 observations were available. An independent archived 18-day hourly dataset reported reconstruction MAPE of 6.7%−8.1% and peak-timing deviations of 1.0–1.5 h. A retrospective West-pipeline case for 22 April 2023 traced historical station forecasts through weighted aggregation, intermediate rounding, hourly reconstruction, and reduced-order linepack calculation. Its LFFX preparation target and the separate NGXDD and DLFX targets were 1.272, 4.702, and 1.571 × 10⁶ m³, respectively. All three targets passed case-specific deterministic inventory checks. The results support station-specific forecast-model selection and an explicit interface between daily prediction and segment-level inventory preparation.
SN  - 1932-6203
ER  -