Accurate wind power data prediction is crucial to increase wind energy usage since wind power data are characterized by uncertainty and randomness, which present significant obstacles to the scheduling of power grids. This paper proposes a hybrid model for wind power prediction based on complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN), sample entropy (SE), bidirectional long short-term memory network (BiLSTM), and Markov chain (MC). First, CEEMDAN is used to decompose the wind power series into a series of subsequences at various frequencies, and then SE is employed to reconstruct the wind power series subsequences to reduce the model’s complexity. Second, the long short-term memory (LSTM) network is optimized, the BiLSTM neural network prediction method is used to predict each reconstruction component, and the results of the different component predictions are superimposed to acquire the total prediction results. Finally, MC is used to correct the model’s total prediction results to increase the accuracy of the predictions. Experimental validation with measured data from wind farms in a region of Xinjiang, and computational results demonstrate that the proposed model can better fit wind power data than other prediction models and has greater prediction accuracy and generalizability for enhancing wind power prediction performance.

Currently, the integration of distributed power supply into the power grid is steadily increasing. The grid’s carrying capacity serves as a crucial metric for evaluating the grid’s resilience following the widespread integration of distributed power supply. During typhoon conditions, if the power grid experiences line breakage and load loss faults, the grid’s framework is altered, rendering the conventional carrying capacity assessment method obsolete. This study introduces a method for assessing the risk of line carrying capacity and an index for line overload probability under typhoon conditions, integrating line and transformer capacity constraints to evaluate the grid’s carrying capacity risk. The probability of line failure is modeled during typhoon events, and a modified IEEE39 node example is employed to simulate a high-penetration grid in a typhoon scenario. Addressing the issue of inadequate intraday dispatch capability under insufficient carrying capacity, we propose a multi-timescale dispatch method and derive the optimal grid dispatch strategy using the viscous bacteria algorithm. The efficacy of the multi-timescale dispatch strategy in addressing the grid’s carrying capacity risk is validated through simulation, while the economic cost of mitigating the grid’s carrying capacity risk and the line overload probability is assessed across varying parameter values.