Optimal Control for Water Distribution Networks with Unknown Dynamics
- Resource Type
- Authors
- Rafal Wisniewski; Carsten Skovmose Kallesøe; Jorge Val
- Source
- IFAC-PapersOnLine. 53:6577-6582
- Subject
- 0209 industrial biotechnology
Distribution networks
Computer science
020208 electrical & electronic engineering
Control (management)
Complex system
02 engineering and technology
Optimal control
020901 industrial engineering & automation
Control and Systems Engineering
Dynamics (music)
Control theory
0202 electrical engineering, electronic engineering, information engineering
Reinforcement learning
- Language
- ISSN
- 2405-8963
Optimal control for Water Distribution Networks (WDN) is subject to complex system models. Typically, detailed models are not available or the implementation is too expensive for small utilities. Reinforcement Learning (RL) methods are well known techniques for model-free control. This paper proposes a model-free controller for WDNs based on RL methods and presents experimental evidence of the practicality of the design.