Build a Regional Power Grid Forecasting Multi-Agent System with CrewAI
Middle East power demand is projected to double by 2050, requiring multi-decade capacity planning and thermal dynamics forecasting. Build a collaborative multi-agent system using CrewAI to simulate regional grid load growth, peak demand periods, and solar/gas generation ratios with high precision.
What you are building
Orchestrate role-playing energy planning agents with CrewAI to model regional power demand trajectories.
How work is evaluated
Evaluates CrewAI agent team load forecasting accuracy against historical Rystad growth baseline.
Datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
forecast_bounds_check
Ensures predicted load growth is greater than base load and mathematically consistent
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
forecast_accuracy
Mean absolute percentage error against benchmark growth projection • target: 0.95 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Learning goals
Define specialized CrewAI roles: Grid Data Analyst, Renewable Energy Specialist, Econometric Forecaster
Establish Crew tasks and delegation flows for 2030-2050 Middle East electricity expansion
Synthesize demographic growth, cooling load multipliers, and industrial AI data center power demand
Generate localized generation capacity expansion roadmaps
Resources
Regional peak load growth series and seasonal temperature data for GCC countries 2020-2050.
Challenge setup
Evaluates CrewAI agent team load forecasting accuracy against historical Rystad growth baseline.
Challenge input
JSON containing base_load_gw, annual_pop_growth_rate, industrial_cdd_factor
CrewAI
Role-playing collaborative crew management
Evaluated output
JSON containing forecast_2035_gw, required_solar_capacity_gw, thermal_backup_gw
- Ensures predicted load growth is greater than base load and mathematically consistent
- Mean absolute percentage error against benchmark growth projection • target: 0.95 • range: 0-1
- Benchmark: Multi-Agent Forecasting Bench
- Forecast Accuracy target: 0.95
- 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
- CrewAI · Required
- crewAI · Optional
- Dagster · Optional
Evaluation contract
- forecast_bounds_check · Weight 1
- forecast_accuracy · Weight 1
Metrics
- forecast_accuracy · Target 0.95
Benchmarks
- Multi-Agent Forecasting Bench
- energy
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON containing base_load_gw, annual_pop_growth_rate, industrial_cdd_factor
Output: JSON containing forecast_2035_gw, required_solar_capacity_gw, thermal_backup_gw
Execution harness: Python
Evaluation tools
- CrewAI · Multi-Agent Orchestrator
Recipe freeze marker
No recipe freeze time is recorded.