Skip to main content
Back to challenges
Challenge

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.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Orchestrate role-playing energy planning agents with CrewAI to model regional power demand trajectories.

Delivery guide

How work is evaluated

Evaluation

Evaluates CrewAI agent team load forecasting accuracy against historical Rystad growth baseline.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

forecast_bounds_check

Ensures predicted load growth is greater than base load and mathematically consistent

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

forecast_accuracy

Mean absolute percentage error against benchmark growth projection • target: 0.95 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • 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 and assets

Reference links and supporting material

Dataset notes

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

Evaluation checks
  • 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
Configured evaluation evidence
  • Benchmark: Multi-Agent Forecasting Bench
  • Forecast Accuracy target: 0.95
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • 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

  1. 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.

Frequently Asked Questions about Build a Regional Power Grid Forecasting Multi-Agent System with CrewAI