Refinery & Cross-Border Pipeline Scheduling Engine with AutoGen
Crude oil distribution between regional refineries in Iraq and export pipelines requires coordinated scheduling between independent pipeline operators and refining teams. Construct a multi-agent pipeline scheduling engine using Microsoft AutoGen. The system coordinates the Pipeline Dispatch Agent, Refinery Intake Agent, and Export Terminal Agent to establish a 90-day pumping schedule that avoids pipeline pressure bottlenecks and terminal storage overflow.
What you are building
Orchestrate pipeline flow and refinery intake schedules across autonomous agents using AutoGen.
How work is evaluated
Evaluates 90-day pipeline flow schedule feasibility and constraint adherence.
Datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
schedule_valid_true
Ensure generated schedule violates zero hard limits.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
capacity_utilization_efficiency
Optimal utilization percentage achieved without overflow. • target: 0.85 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Learning goals
Configure AutoGen multi-agent workflows for multi-node pipeline scheduling.
Implement linear programming tools inside agent tool suites.
Resolve storage tank capacity constraints across 90-day horizon.
Resources
90-day synthetic telemetry and capacity constraints for crude export pipelines.
Challenge setup
Evaluates 90-day pipeline flow schedule feasibility and constraint adherence.
Challenge input
JSON with tank_capacities, pipeline_limits, daily_refinery_intake
AutoGen
Framework for multi-actor collaborative optimization.
Evaluated output
JSON with schedule_valid, max_storage_utilized_pct, bottleneck_detected
- Ensure generated schedule violates zero hard limits.
- Optimal utilization percentage achieved without overflow. • target: 0.85 • range: 0-1
- Benchmark: AutoGen-Ops-Bench
- Capacity Utilization Efficiency target: 0.85
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
Shows the first task, up to three tools, and up to three evidence items.
View technical recipe
Configured tools
- AutoGen · Required
- Microsoft AutoGen · Optional
- Sarvam AI · Optional
Evaluation contract
- schedule_valid_true · Weight 1
- capacity_utilization_efficiency · Weight 1
Metrics
- capacity_utilization_efficiency · Target 0.85
Benchmarks
- AutoGen-Ops-Bench
- energy
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON with tank_capacities, pipeline_limits, daily_refinery_intake
Output: JSON with schedule_valid, max_storage_utilized_pct, bottleneck_detected
Execution harness: Python
Evaluation tools
- AutoGen · Multi-Agent System
Recipe freeze marker
No recipe freeze time is recorded.