Wind speed forecasting of genetic neural model based on rough set theory
| Autor: | Shifan Guo, Yansong Li, Sheng Xiao |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Engineering
Mathematical optimization Wind power Artificial neural network business.industry Wind power forecasting Machine learning computer.software_genre Backpropagation Wind speed Genetic algorithm Artificial intelligence Rough set Hybrid power business computer Physics::Atmospheric and Oceanic Physics |
| Zdroj: | 2010 5th International Conference on Critical Infrastructure (CRIS). |
| DOI: | 10.1109/cris.2010.5617533 |
| Popis: | As wind power penetrations increase dramatically, wind power forecasting is increasingly becoming one of the fundamental strategies in hybrid power systems. In order to obtain higher accuracy, a new method—genetic algorithm neural network based on rough set theory is proposed in the paper. Considering many factors that influence wind speed forecasting, reduction algorithm of rough set theory is introduced to choose the neural network's input parameters. Parameters which have higher correlation with forecasting are used as input to reduce the work and calculation time of neural network. And the genetic algorithm with global searching capability is used to optimize the initial weights of the neural network to overcome slow convergence speed and easy to fall into the local minimum of BP algorithm. The forecasting values agree well with the data which measured in a wind farm. The calculation examples show that the new method can improve the speed and the accuracy of prediction, which prove the feasibility and validity of the new method in the wind speed forecasting. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|