Reproduce “An End-to-End Approach for Microgrid Probabilistic Forecasting and Robust Operation via Decision-focused Learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tingwei Cao, Yan Xu
The MED system trains probabilistic forecasts with decision-focused feedback through a differentiable surrogate; the exact robust scheduler is not differentiated. It combines forecast accuracy with operational regret while scheduling storage, controllable demand, and grid exchange under bounded uncertainty. In two modeled networks, it lowers reported net daily cost, including an 18.0% reduction in the 33-bus case versus Forecast + TSRO.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.