Data-driven Network Reduction for Transmission-Constrained Unit Commitment

The transmission-constrained unit commitment (TC-UC) problem is one of the most relevant problems solved by independent system operators for the daily operation of power systems. Given its computational complexity, this problem is usually not solved to global optimality for real-size power systems. In this paper, we propose a data-driven method that leverages historical information to reduce the computational burden of the TC-UC problem. First, past data on demand and renewable generation throughout the network are used to learn the congestion status of transmission lines. Then, we infer the lines that will not become congested for upcoming operating conditions based on such learning. By disregarding the capacity constraints of potentially uncongested lines we formulate a reduced TC-UC problem that is easier to solve and whose solution is equivalent to the one obtained with the original TC-UC problem. The proposed approach is tested on the IEEE-96 system for different levels of congestion. Numerical results demonstrate that the proposed approach outperforms existing ones by significantly reducing the computational time of the TC-UC problem.