Evaluation of wind turbine power generation by using an adaptive neuro fuzzy inference system
Renewable energy is rapidly emerging as one of the most viable alternative source of power generation due to the following advantages of the wind turbine. Firstly, the wind turbine is cost-effective and eco-friendly. Secondly, the turbine is useful as efficient as possible for the changeable power g...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Institute of Physics
2013
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/24516/ http://irep.iium.edu.my/24516/ http://irep.iium.edu.my/24516/1/Wind_turbine__JRSE-MS_-_RE_-_110486-Accepted_Copy-2012.pdf |
| Summary: | Renewable energy is rapidly emerging as one of the most viable alternative source of power generation due to the following advantages of the wind turbine. Firstly, the wind turbine is cost-effective and eco-friendly. Secondly, the turbine is useful as efficient as possible for the changeable power generation based on the wind velocity. However, the efficiency of the wind turbine can be achieved by using optimum turbine parameters in which energy is produced, used and saved. There are several techniques reported in literature to reach an optimum performance such as fuzzy expert system. However, in application, correct selection of turbine parameters is critical to estimate wind power generation by using FES since it depends only on expert’s knowledge. Hence, there is a need for a more efficient and simple system that could be employed to predict wind power generation. In this work, an adaptive neuro-fuzzy inference system (ANFIS) was developed with Reynolds number and wind velocity used as inputs to estimate wind power generation. The results obtained from experimental power generation were in good agreement with that obtained by ANFIS simulation i.e. with an average percentage deviation of 4.55% in power generation and a goodness of fit of 0.95 were obtained. This work has demonstrated the viability of modeling a wind turbine-power mechanics using an adaptive neuro-fuzzy inference system. |
|---|