Fan Power Forecast Based on Sparrow Search Algorithm Optimized Back Propagation Neural Network

Konferenz: ISCTT 2021 - 6th International Conference on Information Science, Computer Technology and Transportation
26.11.2021 - 28.11.2021 in Xishuangbanna, China

Tagungsband: ISCTT 2021

Seiten: 4Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Cui, Xinmiao; Sun, Yuan (School of Mechanical Engineering, Shanghai Dianji University, Shanghai, China)

The power generation of wind turbines directly reflects the power load of wind farms. Effective prediction of wind turbine power is the key to maintaining grid resource dispatch. Therefore, for the power prediction problem of wind turbines, the error back propagation neural network is an effective prediction method, which has strong nonlinear mapping capabilities, high self-learning and adaptive capabilities, and generalization capabilities. But at the same time there is a local minimization problem and the convergence speed is slow. The back propagation neural network optimized by the sparrow search algorithm improves these deficiencies. This article uses the historical wind turbine power data provided by a certain electric power company as reference data for model building and iterative training. Experiments and results show that the error back propagation neural network model optimized by the sparrow search algorithm converges faster and has a better prediction effect.