It is of great significance to realize transient stability evaluation accurately and quickly for stable and safe operation of power system. Aiming at the problem of low prediction accuracy in the current transient stability evaluation of grid-connected photovoltaic energy storage systems
a transient stability evaluation method based on integrated deep Random forest algorithm (gcForest-AdaBoost) is proposed by combining deep learning and ensemble learning techniques. Firstly
the initial input features are constructed according to the steady-state components of the grid-connected photovoltaic energy storage system during operation. Secondly
in order to reduce the overfit of the model and ensure that the model still has strong learning ability after the number of cascades increases
a transient stability evaluation method based on gcForest-AdaBoost is proposed by combining deep random forest algorithm and AdaBoost algorithm. Thirdly
the gcForest-AdaBoost model is trained with input feature set
and the transient stability evaluation model of grid-connected PV energy storage system is established. Finally
the IEEE 39-node system is connected to the photovoltaic energy storage unit to build a case system for simulation analysis and data acquisition
and the evaluation results are obtained. Numerical examples show that the proposed model can effectively analyze the transient stability of grid-connected photovoltaic energy storage systems
and it is found that the proposed model has good robustness and generalization ability.
REN C, XU Y.A fully data-driven method based on generative adversarial networks for power system dynamic security assessment with missing data[J]. IEEE transactions on power systems, 2019, 34(6): 5044-5052.
MOVAHEDI A, NIASAR A H, GHAREHPETIAN G B. Designing SSSC, TCSC, and STATCOM controllers using AVURPSO, GSA, and GA for transient stability improvement of a multi-machine power system with PV and wind farms[J]. International journal of electrical power & energy systems, 2019, 106: 455-466.
ZHOU Z H, FENG J.Deep forest: towards an alternative to deep neural networks[C]//Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence. Melbourne, Australia, 2017: 3553-3559.