Data-driven Identification of Active Conditional Transmission Section Limits in SCUC

A Conditional Transmission Section Limit (CTSL) becomes active only under specific operating conditions. Such limits do not only depend on but also affect solutions to the Security Constrained Unit Commitment (SCUC) problem. To predetermine active CTSLs before the solution process of SCUC, this paper develops a data-driven identification method of active CTSLs. At first, a mixed-integer programming model for SCUC that considers CTSLs is presented. A data-driven identification method of active CTSLs is then established based on probabilistic classification via random forest. Numerical results on the modified IEEE 39-bus system with historical data validate the effectiveness of our method through comparison with other classification algorithms and settings.