Overview
What this challenge is about.
You receive a wind-speed-and-direction time series for the lease area, the polygon boundary, a minimum inter-turbine spacing constraint, and a Jensen wake model. Implement a real-coded genetic algorithm with tournament selection, a custom crossover that respects the polygon constraint, and a Gaussian-mutation operator. Compare it against the developer's grid heuristic and a simulated-annealing baseline on expected Annual Energy Production (AEP) over 50 GA runs. Report mean AEP uplift, run-time, and convergence behavior. Write a 2-page memo with a clear recommendation.
The Brief
What you'll do, and what you'll demonstrate.
Evaluate whether a genetic algorithm meaningfully beats the current grid layout heuristic on expected annual energy production for a 40-turbine offshore wind farm.
Earning criteria — what you'll demonstrate
- Implement a real-coded GA with custom genetic operators
- Handle hard geometric constraints in evolutionary search
- Compare metaheuristics fairly on a real-world objective
- Communicate stochastic-search results to a non-AI engineering audience
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Applied AI Scientist
Translating an evolutionary algorithm into a quantified AEP recommendation for a real engineering team is exactly the day-one work of an applied AI scientist at any renewable-energy or industrial-AI firm.
This challenge sharpens
- genetic-algorithms
- optimization
- simulation
Data Scientist
Fair, seeded benchmarks on a business KPI with stakeholder-ready memos transfer directly to data-science roles in operations or planning teams.
This challenge sharpens
- optimization
- python
- simulation
ML Researcher
Designing genetic operators that respect hard constraints and ablating them is the kind of methodology work ML researchers do in industrial-research settings.
This challenge sharpens
- genetic-algorithms
- constraint-handling
- metaheuristics