Frame an Energy-Storage Dispatch Decision as a Bayesian Decision Problem
Overview
What this challenge is about.
Model dispatch as a Bayesian decision problem with price and wind data, then back-test your policy and earn a verifiable certificate.
The scenario
The operator (around 120 staff, around 1.2 GW of wind and 200 MWh of storage across Denmark) is preparing for a 2x capacity expansion and needs better dispatch policies before storage growth outpaces trading-desk capacity.
The Brief
What you'll do, and what you'll demonstrate.
Outperform the heuristic dispatch policy on revenue per cycle by framing dispatch as a Bayesian decision problem.
Earning criteria — what you'll demonstrate
- Express a real operational decision as a Bayesian decision problem
- Model utility as revenue minus degradation cost explicitly
- Build a posterior over short-horizon price and use it in decision-making
- Communicate Bayesian decision theory to a non-statistical trading team
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Decision Making Under Uncertainty
Master · Reinforcement Learning
Strong alignment
This challenge maps to Decision Making Under Uncertainty at the Master level. It sharpens the same practical skills your coursework expects — but in a real industry context with actual constraints and deliverables.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Bayesian Decision Theory
Apply bayesian decision theory to solve real industry problems and demonstrate production-level capability.
- Price Modeling
Apply price modeling to solve real industry problems and demonstrate production-level capability.
- Back Testing
Apply back testing to solve real industry problems and demonstrate production-level capability.
- Python
Write clean, efficient Python for data processing, automation, and backend services.
- Utility Modeling
Apply utility modeling to solve real industry problems and demonstrate production-level capability.
- Policy Evaluation
Apply policy evaluation to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
Applied AI Scientist
Bayesian decision framings of real operational problems are exactly the kind of work applied AI scientists do at energy, logistics, and trading firms.
This challenge sharpens
- bayesian-decision-theory
- utility-modeling
- policy-evaluation
Data Scientist
Building a posterior on price data and using it in a back-tested policy is a high-leverage data-scientist project in energy markets.
This challenge sharpens
- price-modeling
- back-testing
- python
ML Researcher
Clean Bayesian formulations are the entry point for sequential-decision research; this challenge proves the formulation muscle.
This challenge sharpens
- bayesian-decision-theory
- utility-modeling
- policy-evaluation