Unit Commitment using Nearest Neighbor as a Short-Term Proxy
This work addresses the computational tractability challenge for power system operators, though it appears incremental as it builds on existing nearest neighbor techniques.
The paper tackled the problem of approximating short-term decisions for hierarchical long-term planning in large power systems by proposing the UCNN algorithm, achieving high accuracy in operational cost with runtimes several orders of magnitude lower than traditional methods on IEEE-RTS79 and IEEE-RTS96 benchmarks.
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.