Method for Scheduling Power Generators Based on Optimal Configurations and Approximate Dynamic Programming

摘要

A unit commitment problem is solved for a set of generators with a set of configurations having a set of 2^N.T schedules, wherein N is a number of generators i and T is a number of decision time steps. A reduced set of configurations is determined, and then a functional metric to measure a similarity of all possible pairs of the configurations is defined. Dynamic programming is applied to the reduced set of configurations using the similarity metric to determine an optimal configuration.