مشخصات پژوهش

عنوان	Irrigation canal control using enhanced fuzzy SARSA learning
نوع پژوهش	مقاله چاپ‌شده در مجلات علمی
کلیدواژه‌ها	canal control, FSL, reinforcement learning, water management
چکیده	Fuzzy SARSA learning (FSL) is a robust reinforcement learning (RL) technique that represents successful solutions in various industrial problems. Water management in irrigation canals is one of these problems where an FSL agent interacts with the canal environment to control the gates. FSL often requires a large number of interactive experiences and takes a long time in real-life problems. To reduce the iteration and speed up the learning process, an enhanced FSL (EFSL) was developed to accelerate the process of policy learning. A MATLAB program was written, and combined with the irrigation canal conveyance system simulation (ICSS) model. To evaluate the proposed idea, the E1R1 Dez canal, located in the south-west of Iran, was considered as a case study. Standard performance indicators were used for assessing the results based on considered water delivery scenarios, showing a shorter learning time with reasonable performance in controlling water depth changes within the canal.
پژوهشگران	کاظم شاه وردی (نفر اول)، محمد جواد منعم (نفر دوم)