Solving Security Constrained Unit Commitment Problem Using Inductive Learning

Security-Constrained Unit Commitment (SCUC) is a large-scale energy optimization problem solved multiple times a day by independent system operators (ISOs). After receiving offers and bids, ISOs have only few hours to clear the day-ahead electricity market. It requires a lot of computational effort and time to solve a large-scale SCUC problem. However, by exploiting the fact that a UC problem is solved several times a day with only minor changes in the system data, we can improve the computational time by identifying the patterns in the historical data using inductive models. In this research, a 2-stage data-driven based approach is proposed to solve a SCUC problem. The presented algorithm was validated through simulations on IEEE-39 bus system and satisfactory results were obtained. The results were compared with those obtained using CPLEX MIQP solver.