| Project/Area Number |
15K00048
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Statistical science
|
|---|
| Research Institution | The University of Tokushima |
|---|
Principal Investigator |
Yasuno Takashi 徳島大学, 大学院社会産業理工学研究部(理工学域), 教授 (50263869)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
北島 孝弘 徳島大学, 技術支援部常三島技術部門, 技術支援職員 (90724104)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2016: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2015: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 風速・風向予測 / 風力発電 / 最大出力制御 / 機械学習 / 深層学習 / ニューラルネットワーク / 統計的予測・制御 / ソフトコンピューティング |
|---|
| Outline of Final Research Achievements |
In this research, for the purpose of improving efficiency in maximum power control of small wind power generator, we proposed a control method using wind speed prediction value and examined its usefulness. In order to obtain good control performance, it is necessary to improve prediction accuracy of wind speed / wind direction, we investigated about various wind speed / wind direction prediction models (complex-valued neural network, support vector machine, 1 dimensional convolution neural network) based on statistical method. In addition, a simulation model of a maximum power control system using a chopper circuit was constructed and high efficiency improvement based on the wind speed prediction value was examined. However, it is necessary to further improve the wind speed prediction accuracy because the dependency of the wind speed prediction value is high.
|
