Overview
A leading gas distribution company in Indonesia initiated a Gas Network Optimization Program to improve gas delivery reliability, optimize distribution capacity, and enhance operational decision-making across the pipeline network.
The program utilized hydraulic simulation modeling using Synergi Gas by DNV combined with data analytics and predictive modeling to simulate various gas distribution scenarios and predict missing or inaccurate metering data caused by meter malfunction, communication failure, or data interruption.
The solution enabled the operation team to optimize gas allocation, validate network performance, and maintain reliable gas supply to customers under various operating conditions.
1. Business Challenge & Problem Definition
The customer managed a complex natural gas distribution network consisting of multiple pipelines, regulating stations, customer delivery points, and metering systems.
With increasing demand variability and network complexity, the company required better capability to analyze pipeline behavior, optimize gas distribution scenarios, and maintain data accuracy for operational decision-making.
Key Challenges:
- Gas distribution planning was highly dependent on operational experience and historical data.
- The pipeline network required advanced hydraulic analysis to evaluate:
- Pressure profile.
- Flow distribution.
- Network capacity.
- Supply-demand balancing.
- Multiple operational scenarios needed to be evaluated, including:
- Increased customer demand.
- Supply limitation scenarios.
- Pipeline operational changes.
- Emergency operating conditions.
- Metering system data issues occurred due to:
- Communication failure.
- Meter malfunction.
- Missing or frozen data values.
- Inconsistent measurement readings.
- Incorrect or unavailable metering data could impact:
- Gas balancing calculation.
- Customer allocation.
- Operational reporting.
- Decision-making.
- The customer required a predictive approach to estimate actual gas flow values when measurement systems experienced disturbances.
2. Technology Solution
A comprehensive Gas Distribution Digital Optimization Solution was implemented by combining hydraulic simulation, operational data analytics, and predictive modeling.
Solution Components:
1. Hydraulic Network Simulation Using Synergi Gas – DNV
A detailed hydraulic model of the gas distribution network was developed using Synergi Gas by DNV.
The simulation model was used to:
- Represent actual pipeline network configuration.
- Analyze pressure and flow distribution.
- Evaluate pipeline capacity and constraints.
- Perform operational scenario simulation.
- Optimize gas distribution strategies.
Simulation scenarios included:
- Normal operating condition.
- Peak demand condition.
- Supply reduction scenario.
- Customer demand variation.
- Network configuration changes.
The hydraulic model provided engineering-based recommendations to support optimal gas distribution planning.
2. Metering Data Analytics & Prediction Model
A data analytics solution was developed to improve reliability of gas measurement data.
The solution analyzed:
- Historical metering data.
- Flow pattern behavior.
- Pressure and temperature correlation.
- Customer consumption trends.
- Network operating conditions.
When metering data experienced:
- Missing values.
- Frozen values.
- Communication interruption.
- Abnormal measurement behavior.
The predictive model generated estimated gas flow values (taksasi) based on historical patterns and network conditions.
3. Integrated Gas Operation Monitoring Platform
The solution integrated:
- Gas metering system data.
- Pipeline operational data.
- Hydraulic simulation results.
- Prediction model output.
The platform provided:
- Gas distribution performance monitoring.
- Metering health monitoring.
- Data validation.
- Estimated flow calculation during meter failure.
- Operational scenario analysis.
3. Solution Architecture
Gas Supply Source & Customer Metering System
↓
SCADA / Metering Data Collection
↓
Gas Distribution Database
↓
Synergi Gas Hydraulic Simulation Model (DNV)
↓
Data Analytics & Metering Prediction Model
↓
Gas Distribution Optimization Dashboard
↓
Operational Decision Support
4. Result & Business Impact
The implementation improved gas distribution management by combining engineering simulation capability with predictive analytics.
Key Benefits:
✅ Optimized Gas Distribution Planning
The hydraulic simulation model enables the operation team to evaluate multiple scenarios and determine the optimal gas distribution strategy.
✅ Improved Network Reliability
Pipeline pressure and flow behavior can be analyzed proactively to prevent operational constraints and supply issues.
✅ Reliable Operation During Metering Failure
The prediction model provides estimated gas consumption values when metering systems experience errors or communication interruptions.
✅ Improved Gas Balancing Accuracy
Estimated metering values support better gas allocation, reconciliation, and operational reporting.
✅ Faster Operational Decision Making
Simulation-based recommendations allow engineers to evaluate potential operational impacts before implementing changes in the field.
✅ Reduced Operational Risk
Early identification of abnormal metering behavior minimizes the impact of inaccurate measurement data on business operations.
Key Achievement Summary
Area
Pipeline Management
Gas Distribution
Metering Reliability
Data Quality
Operational Planning
Business Continuity
Improvement
Hydraulic simulation-based optimization
Improved flow and pressure management
Prediction during meter disturbance
Improved measurement validation
Scenario-based decision support
Reduced impact of meter failure
Digital Gas Operation Transformation Outcome
From reactive gas distribution management → Intelligent, simulation-based, and predictive gas network optimization.
The implementation established a foundation for advanced Gas Network Digital Twin, enabling PGN pipeline operations to improve distribution efficiency, maintain reliable gas supply, and support future initiatives such as AI-based forecasting, predictive analytics, and autonomous gas network optimization.