| *商品について |
|
表紙はついていません（本文のみ中綴じ製本です）。
号単位でも購入できます。
すべてモノクロ印刷です。
Extended Summaryはついていません。
|
 |
| ・会員価格 ¥550 |
| ・一般価格 ¥770 |
|
|
| こちらはBookPark「電気学会 電子図書館（IEEJ Electronic Library）」による文献紹介ページです。 |
|
 |
 |
電気学会会員の方はこちらから一旦ログインのうえ、マイページからお入りください。
会員価格で購入することができます。
|
|
| 非会員の方はログインの必要はありません。このまま お進みください。 |
|
|
| ■論文No. |
|
| ■ページ数 |
8ページ |
■発行日
|
2022/11/01 |
| ■タイトル |
Insolation Forecasting by using Image-processed Satellite Images Data and Forecasting of Cloud Imageries |
| ■タイトル(英語) |
Insolation Forecasting by using Image-processed Satellite Images Data and Forecasting of Cloud Imageries |
| ■著者名 |
Shoji Kawasaki (Department of Electronics and Bioinformatics, School of Science and Technology, Meiji University), Qingkun Wang (Department of Electronics and Bioinformatics, School of Science and Technology, Meiji University) |
| ■著者名(英語) |
Shoji Kawasaki (Department of Electronics and Bioinformatics, School of Science and Technology, Meiji University), Qingkun Wang (Department of Electronics and Bioinformatics, School of Science and Technology, Meiji University) |
| ■価格 |
会員 ¥550 一般 ¥770 |
| ■書籍種類 |
論文誌(論文単位) |
| ■グループ名 |
【B】電力・エネルギー部門 |
| ■本誌 |
電気学会論文誌B（電力・エネルギー部門誌） Vol.142 No.11 （2022） 特集：気象情報の利活用に基づく新しい電力系統運用技術
|
| ■本誌掲載ページ |
525-532ページ |
| ■原稿種別 |
論文／英語 |
| ■電子版へのリンク |
https://www.jstage.jst.go.jp/article/ieejpes/142/11/142_525/_article/-char/ja/
|
| ■キーワード |
insolation forecasting，photovoltaic generation，satellite image，neural network，ConvLSTM |
| ■要約(日本語) |
|
| ■要約(英語) |
Recently, there is a movement aimed at realizing distributed energy systems, especially photovoltaic power generation (PV) is expected in Japan, and it is expected that the number of interconnections of PV will increase in the future. Insolation is easily affected by the weather and the supply of electricity becomes unstable. Therefore, it is important to forecast the amount of insolation. In this study, the main purpose of this research is to develop a highly accurate and practical method for insolation forecasting, based on satellite image data provided by the Himawari-8 satellite and past actual measurement data released by the Japan Meteorological Agency. In this paper, the authors propose an amount of insolation forecasting method by using neural network and carry out the accuracy verification by case study. In addition, the authors also use the ConvLSTM (Convolutional Long Short-Term Memory) model to forecast the cloud imageries for the insolation forecasting. In order to verify the usefulness of the proposed method, the forecast results by the proposed method were compared with the forecast results without using satellite image data and the forecast results with latest satellite image data. In conclusion, by using the satellite image data and forecasting the cloud imageries, it was possible to grasp the characteristics of the insolation, prevent erroneous prediction, and improve the prediction accuracy. |
| ■版 型 |
|
|
|
|
