Home >

news Help

Publication Information


Title
Japanese:深層強化学習を用いたダム操作モデルによる 予測情報を活用した事前放流操作に関する検討 
English:STUDY OF PRE-DISCHARGE OPERATION AT RESERVOIRS BY DAM OPERATION MODEL USING DEEP REINFORCEMENT LEARNING 
Author
Japanese: 赤塚 洋介, 瀬戸 里枝, 鼎 信次郎.  
English: Yosuke Akatsuka, Rie Seto, Shinjiro Kanae.  
Language Japanese 
Journal/Book name
Japanese:土木学会論文集B1(水工学) 
English:Journal of Japan Society of Civil Engineers, Ser. B1 (Hydraulic Engineering) 
Volume, Number, Page Vol. 76    No. 2    I823-I828
Published date Nov. 2020 
Publisher
Japanese:公益社団法人土木学会 
English:Japan Society of Civil Engineers 
Conference name
Japanese:第65回水工学講演会 
English:The 65th Conference on Hydraulic Engineering 
Conference site
Japanese:オンライン 
English:Online 
Abstract In recent years, there has been a demand for disaster countermeasures that make use of existing infrastructure. In this study, we develop dam operation models using deep reinforcement learning. To investigate the possibility of pre-discharage operation, we apply this model to pre-discharge operation by considering inflow prediction and precipitation prediction information. From the result of learning and testing with the dam operation model, we revealed that we can apply dam operation model to pre-discharge operation. On the other hand, the action that models select during testing will converge only one action when the predischarge operation and flood control operation are treated as a series of operation. As a result, model can fail in flood control operation.

©2007 Tokyo Institute of Technology All rights reserved.