In order to predict short-term load accurately and effectively, a short-term load forecasting model (PSO-SVM) based on particle swarm optimization (PSO) and support vector machine (SVM) is proposed. The parameters of the support vector machine are regarded as the velocity and position of a particle, and the optimal support vector machine parameters are found through continuous updating of the speed and position of the example. It can overcome support vector machine algorithm’s shortcoming. The model of short-term load forecasting of the Red River power grid is established according to the optimal parameters, and the model performance is simulated. Try. The simulation results show that, compared with the SVM prediction model, PSO-SVM not only speeds up the optimization speed of SVM, but also improves the precision of load forecasting, and is more suitable for the need of short-term load forecasting in regional power grid.
CITATION STYLE
Hua, J., Xiong, W., Niu, L., & Cao, L. (2020). Application of Support Vector Machine Based on Particle Swarm Optimization in Short-Term Load Forecasting of Honghe Power Network. In Advances in Intelligent Systems and Computing (Vol. 928, pp. 437–443). Springer Verlag. https://doi.org/10.1007/978-3-030-15235-2_65
Mendeley helps you to discover research relevant for your work.