Research focus
Example task
Renewable energy response
Conceptual example
Renewable output falls
Available generation decreases
Dispatch battery
Use stored energy to serve demand
Serve demand
Stay within storage limits
Illustrative task record. It does not represent a published evaluation result.
What the task measures.
Score unmet demand and operating cost while checking power and storage limits. Record each dispatch decision and the resulting grid state.
Using stored energy now changes how much remains for later demand. Following several demand periods tests whether a model can plan beyond the next action.
Discuss energy evaluation.
Evaluation engagements are custom. We agree on the task, inputs, outcomes, and scoring before a run begins.