Problem
Research questions and friction points this paper is trying to address.
gate control
safety requirements
water level management
conflicting objectives
coastal infrastructure
Safe and Near-Optimal Gate Control: A Case Study from the Danish West Coast
🤖 AI Summary
This study addresses the multi-objective control conflicts inherent in operating the sluice gates of Ringkøbing Fjord, Denmark, where competing demands include water level safety, navigational access, and fish migration. To resolve these tensions, the authors propose a novel safe adaptive control framework that integrates online reinforcement learning with formal verification. A digital twin model, implemented in Uppaal Stratego, leverages real-time sea-level and wind-speed forecasts to learn near-optimal control policies that provably satisfy safety constraints. This work represents the first application of an online reinforcement learning approach combined with formal verification to the domain of safety-critical infrastructure with multiple, often conflicting, operational objectives. Experimental results demonstrate that the learned controller consistently adheres to safety requirements across diverse sea-level scenarios while achieving performance on par with established baseline methods in other metrics.
📝 Abstract
Ringkoebing Fjord is an inland water basin on the Danish west coast separated from the North Sea by a set of gates used to control the amount of water entering and leaving the fjord. Currently, human operators decide when and how many gates to open or close for controlling the fjord's water level, with the goal to satisfy a range of conflicting safety and performance requirements such as keeping the water level in a target range, allowing maritime traffic, and enabling fish migration. Uppaal Stratego. We then use this digital twin along with forecasts of the sea level and the wind speed to learn a gate controller in an online fashion. We evaluate the learned controllers under different sea-level scenarios, representing normal tidal behavior, high waters, and low waters. Our evaluation demonstrates that, unlike a baseline controller, the learned controllers satisfy the safety requirements, while performing similarly regarding the other requirements.
Innovation
Methods, ideas, or system contributions that make the work stand out.
digital twin
online learning
safe control
Uppaal Stratego
near-optimal policy
🔎 Similar Papers
No similar papers found.
