A RSCMAC Based Forecasting and Wavelet Analysis for Wind power

• Main Authors: Hao-An Jhuang, 莊皓安
• Other Authors: 江青瓚
• Format: Others
• Language: zh-TW
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/20821363707482945646

碩士 === 健行科技大學 === 電機工程所 === 101 === In recent years, due to the Earth''s warming effect, making renewable energy generation systems increasingly occupy a high proportion of the total installed capacity, and this will affect the overall power planning. Wind power is an important renewable energy, so predicting wind generating capacity for the electricity dispatch of wind power generation systems are relatively important. The stability, power allocation and schedule of the grid affect the economy of a country. The intermittent power generation characteristic of a wind power generation system is the major cause of affecting the overall power grid stability. This study has established a Recurrent Simple addressing structure for Cerebellar Model Articulation Controller with General Basis Function (RSCMAC) based wind turbine model and a short-term wind speed forecasting model, the relationship between the wind and the wind power is also built to predict wind power. Wind power forecasting system provides usable information to the overall power allocation and schedule, and improve the stability of the overall grid. For the wind power forecasting, current researches focus on hourly wind forecasting, the purpose of this study is to apply RSCMAC to predict extremely short-term wind power, so it can be used in evaluation of electricity dispatch. Therefore, this study established a RSCMAC based combined with wavelet input state extremely short-term wind power forecasting model and shows its feasibility and high accuracy.