We devise the Unit Commitment Nearest Neighbor (UCNN) algorithm to be used as a proxy for quickly approximating outcomes of short-term decisions, to make tractable hierarchical long-term assessment and planning for large power systems. Experimental results on updated versions of IEEE-RTS79 and IEEE-RTS96 show high accuracy measured on operational cost, achieved in runtimes that are lower in several orders of magnitude than the traditional approach.
Cite
@article{arxiv.1611.10215,
title = {Unit Commitment using Nearest Neighbor as a Short-Term Proxy},
author = {Gal Dalal and Elad Gilboa and Shie Mannor and Louis Wehenkel},
journal= {arXiv preprint arXiv:1611.10215},
year = {2018}
}