2022 Fiscal Year Final Research Report
Research on Design of Semi Off-Grid with Renewable Energy
| Project/Area Number |
20K04434
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 21010:Power engineering-related
|
|---|
| Research Institution | Chubu University (2021-2022)
Tohoku University (2020) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Keywords | セミオフグリッド / 需要想定 / 設備計画 / 電力システム / LSTM / 蓄電池 / 再生可能エネルギー |
|---|
| Outline of Final Research Achievements |
We used LSTM for semi off-grid demand forecasting and showed that demand can be forecasted with high accuracy by learning time-series power flow information and weather data. We proposed a method to set constraints on the power received from the upper grid for planning to promote local production for local energy consumption and developed an algorithm to adjust the constraint conditions according to weather changes. This method is also useful for mitigating transmission line congestion on the upper system. As part of the cost evaluation, a method for reducing storage battery capacity was studied. It was shown that off-grid operation of multiple customers can reduce the battery capacity due to the demand smoothing effect. We identified the issue of the need for protection control against electrical fault in semi off-grid through this research.
|
| Free Research Field |
電力工学
|
| Academic Significance and Societal Importance of the Research Achievements |
未来の電力システムであるセミオフグリッドを実現するためには必要設備を安価で構成し運用することが求められる。そこで本研究ではセミオフグリッドの設計に焦点を絞り，需要想定と設備計画の両手法を提案したが，多地点多次元のデータ解析に基づいて構築した点に学術的な意義がある。多地点の計測装置から得られる多次元の電気的パラメータと気象データをLSTMに学習させることで，高精度の電力需要予測が可能であることを示した。また，コスト削減のためには蓄電池容量の低減が必須であるが，実測データによる分析により，複数需要家でオフグリッドを構成すると容量削減効果があることを定量的に示せた点に社会的な意義がある。
|
