System Equivalent Inertia Evaluation Method Based on Steady-State Operational Data and Machine Learning

Aiming at the problem that it is difficult to accurately quantify the virtual inertia of wind turbines, a system equivalent inertia assessment method based on the steady-state operation data of a high percentage of new energy power systems is proposed. Firstly, the inertia composition of the new energy system is analyzed, the turbine virtual inertia and load inertia are fully considered, the equivalent inertia response model of the new energy system is established, and the actual inertia in the power system is calculated by using the conventional definition method. Then, the equivalent inertia assessment model based on a neural network is constructed based on the steady-state operation data of the power grid under different wind power penetration rates. At the same time, the model's training can be based entirely on historical steady-state operation data, which can realize the accurate assessment of system equivalent inertia without additional perturbation and improve the inertia assessment system.