Prediction of global electricity generation by using least squares support vector regression with sparrow search algorithm

Abstract

In order to accurately predict the development of global electricity generation, this paper presents a prediction model of least squares support vector machine (LS-SVR) based on Sparrow search optimization algorithm (SSA), and obtains the fitting curve through iterative optimization of the hyperparameters. The results show that the prediction accuracy of the least squares support vector regression machine (SSA_LSSVR) based on the sparrow search optimization algorithm is higher, and it can predict the development trend of global power production more accurately.