Construction of a Frequency Compliant Unit Commitment Framework Using an Ensemble Learning Technique

Frequency control is essential to ensure reliability and quality of power systems. North American Electric Reliability Corporation’s (NERC) Control Performance Standard 1 (CPS1) widely adopted by many operating authorities examine the frequency control. The authority would have a strong interest in knowing how frequency-sensitive features affect CPS1 score finding out more effective unit-dispatch schedules for reaching goal. As usually possess multi-variable high-correlated characteristics, this paper employed an ensemble learning technique (the Gradient Boosting Decision Tree algorithm, GBDT) construct Response Model (FRM) Taipower system Taiwan evaluate score. proposed model was then integrated with Unit Commitment (UC) program determine that achieves targeted feasibility effectiveness CPS1-UC platform were validated compared other benchmark model-based UC methods two cases. shows promising results: could be maintained well, especially periods early morning or high renewable penetration.