Wind and solar power prediction based on improved whale optimization algorithm

Abstract Wind and solar power prediction is crucial for the rational utilization of wind and photovoltaic resources and for ensuring the safety of the power grid. In order to improve the prediction accuracy, this paper constructs a wind-solar power prediction model. Aiming at the shortcomings of the whale optimization algorithm in population initialization and local optimization problems, an improved whale optimization algorithm (MSWOA) is proposed, which combines Cat chaotic mapping and variable spiral position update strategy and is combined with an optimized hybrid extreme learning machine to solve the model. Through comparative experiments with standard WOA, the results show that MSWOA has faster convergence speed and stronger global search ability, demonstrating excellent predictive performance and good generalization ability, and has high application value.