干旱区生态环境知识资源中心(Arid): Enabling Efficient Model-Free Control of Large-Scale Canals by Exploiting Domain Knowledge

Arid

DOI	10.1109/TIE.2020.3013778
	Enabling Efficient Model-Free Control of Large-Scale Canals by Exploiting Domain Knowledge
	Ren, Tao; Niu, Jianwei; Shu, Lei; Hancke, Gerhard P.; Wu, Jiyan; Liu, Xuefeng; Xu, Mingliang
通讯作者	Niu, JW (corresponding author), Beihang Univ, Hangzhou Innovat Inst, Hangzhou 310051, Peoples R China. ; Niu, JW (corresponding author), Beihang Univ, Sch Comp Sci & Engn, State Key Lab Virtual Real Technol & Syst, Beijing 100191, Peoples R China. ; Niu, JW (corresponding author), Zhengzhou Univ, Sch Informat Engn, Zhengzhou 450001, Peoples R China. ; Hancke, GP (corresponding author), Nanjing Univ Posts & Telecommun, Nanjing 210023, Peoples R China.
来源期刊	IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
ISSN	0278-0046
EISSN	1557-9948
出版年	2021
卷号	68 期号:9 页码:8730-8742
英文摘要	Canals are constructed worldwidely to divert water from rich to arid areas to mitigate water shortages. Since water resource is fairly limited, it is essential to perform canal control efficiently to improve water-delivery performance. A promising solution is to leverage model predictive control (MPC), which calculates the desired canal action at each time step via reliable predictions of the model. However, the predictive model dependence degrades the practicability and the iterative calculation incurs intensive computations, especially for large-scale canals with high-dimensional state and action spaces (curse of dimensionality). This article presents a new canal control model named efficient model-free canal control (EMCC) that obtains control policies in a model-free way via deep reinforcement learning (DRL) and alleviates the curse of dimensionality via domain knowledge (control experience). EMCC adopts the hidden Markov model with Gaussian mixture densities (GMM-HMM) to model canal system dynamics with control experience, and initializes it according to the actual operation data. Besides, we design a reward generator collaborated with GMM-HMM to supervise the reinforcement learning around control experiences to obtain more efficient control policies. We evaluate EMCC via numerical simulations on Chinese largest water-delivery project (SNWTP). Experimental results show that EMCC leads to significant convergence performances compared with crude applications of DRL on large-scale canals, and achieves desired objectives more satisfactorily than MPC and control-experience under two typical water-delivery tasks.
英文关键词	Irrigation Hidden Markov models Logic gates Predictive models Aerospace electronics Learning (artificial intelligence) Machine learning Control experience deep reinforcement learning (DRL) large-scale canal model-free control simulations on Chinese largest water-delivery project (SNWTP)
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000664002600095
WOS关键词	PREDICTIVE CONTROL
WOS类目	Automation & Control Systems ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS研究方向	Automation & Control Systems ; Engineering ; Instruments & Instrumentation
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/350538
作者单位	[Ren, Tao; Niu, Jianwei] Beihang Univ, Hangzhou Innovat Inst, Hangzhou 310051, Peoples R China; [Ren, Tao; Niu, Jianwei] Beihang Univ, Sch Comp Sci & Engn, State Key Lab Virtual Real Technol & Syst, Beijing 100191, Peoples R China; [Niu, Jianwei; Xu, Mingliang] Zhengzhou Univ, Sch Informat Engn, Zhengzhou 450001, Peoples R China; [Niu, Jianwei] Zhengzhou Univ, Zhengzhou Univ Res Inst Ind Technol, Zhengzhou 450001, Peoples R China; [Shu, Lei] Nanjing Agr Univ, Coll Engn, Nanjing 210031, Peoples R China; [Shu, Lei] Univ Lincoln, Coll Sci, Brayford Pool LN6 7TS, England; [Hancke, Gerhard P.] Nanjing Univ Posts & Telecommun, Nanjing 210023, Peoples R China; [Hancke, Gerhard P.] Univ Pretoria, ZA-0002 Pretoria, South Africa; [Wu, Jiyan; Liu, Xuefeng] Beihang Univ, Sch Comp Sci & Engn, Beijing 100191, Peoples R China
推荐引用方式 GB/T 7714	Ren, Tao,Niu, Jianwei,Shu, Lei,et al. Enabling Efficient Model-Free Control of Large-Scale Canals by Exploiting Domain Knowledge[J],2021,68(9):8730-8742.
APA	Ren, Tao.,Niu, Jianwei.,Shu, Lei.,Hancke, Gerhard P..,Wu, Jiyan.,...&Xu, Mingliang.(2021).Enabling Efficient Model-Free Control of Large-Scale Canals by Exploiting Domain Knowledge.IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS,68(9),8730-8742.
MLA	Ren, Tao,et al."Enabling Efficient Model-Free Control of Large-Scale Canals by Exploiting Domain Knowledge".IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 68.9(2021):8730-8742.