In view of the low prediction accuracy of short-term wind speed, for ELM, the connection weight and hidden layer threshold of input layer and hidden layer were randomly generated, which led to the decrease of network generalization ability and the distortion of evaluation result caused by over-fitting, a forecasting method based on particle swarm combined extremely learning machine (PSO-ELM) was proposed. The example analysis showed that the model had high prediction accuracy and could effectively track the variation of wind speed.
CITATION STYLE
Li, A., & Wei, X. (2020). Short-Term Wind Speed Forecasting Based on PSO-ELM. In Lecture Notes in Electrical Engineering (Vol. 675, pp. 1059–1063). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-15-5959-4_130
Mendeley helps you to discover research relevant for your work.