Day-ahead scheduling and operating reserves
Improving probabilistic day-ahead energy forecasts by combining numerical weather forecasts with AI/ML models, and reducing the complexity of stochastic unit commitment and economic dispatch models through scenario selection, to mitigate risks of renewable energy curtailment, load shedding, and electricity price volatility.
We introduced a methodology that leverages statistical functional depth metrics to identify the most operationally risky scenarios-those likely to result in high generation costs, reserve shortfalls, load shedding, or renewable curtailment. You can find more information in our publication (Terrén-Serrano & Ludkovski, 2025).
We presented our project at the 2024 ARPA-E Energy Innovation Summit as part of Princeton University PERFORM team.
This work is part of the ORFEUS team at Princeton University.