Objective To address issues such as insufficient utilization of peak-valley electricity price, strong reliance on manual experience, and lagged response to sudden load changes in the scheduling of LNG terminal pipeline networks, an intelligent optimal scheduling model based on real-time data is developed to reduce output costs and enhance gas supply stability.

Method By thoroughly studying the operational characteristics of LNG terminal pipeline network systems, an optimal scheduling model has been established with the objective of minimizing daily electricity costs for high-pressure pumps. The model comprehensively considers network capacity constraints, equipment operational characteristics, and the peak-valley electricity price differences in the power market, and has been solved using nonlinear optimization algorithms. Leveraging the Intelligent Agent Platform from Gongshu Technology to interface with DCS and SCADA systems, a three-level optimization strategy has been implemented, including planned scheduling (24-hour cycle), real-time scheduling (5-minute response), and medium-term scheduling (multi-day coordinated optimization).

Result Validation under typical operating conditions in Fujian showed that the optimal scheduling scheme increased the number of high-pressure pumps operating during off-peak periods (0:00—8:00) by 33.33% and reduced electricity consumption during peak periods (9:00—12:00, 15:00—18:00) by 10.71%. Actual operational data indicated a daily electricity cost saving of 5.81%, with network pressure fluctuations controlled within ±0.5 MPa and sudden load response time shortened to 5 minutes.

Conclusion The proposed intelligent scheduling model overcomes the limitations of traditional experience-based scheduling. Through multi-time-scale coordinated optimization, it achieves a balance between safety and economic efficiency. This technology can be extended to similar LNG terminals, with an estimated annual electricity cost saving of over 3 million yuan per terminal, providing a model for the intelligent transformation of energy facilities under the "dual-carbon" goals.