Large Markov Decision Processes based management strategy of inland waterways in uncertain context

International audienceInland waterways management is likely to go through heavy changes due to an expected traffic increase in a context of climate change. Those changes are going to requires adaptive and resilient management of the water resource. A representative model of the inland waterway has been proposed, using Markov decision processes to model the dynamic and uncertainties of the waterway. It is used to obtain an optimal plan for the distribution of the water on the network that takes into account the uncertainties arising for the operation of such networks. A subnetwork of the Hauts-de-France is modeled using this approach based on real data of traffic and water levels. The produced plans are tested on different scenarios under expected and unexpected conditions of traffic and climate to observe the quality and resilience of the generated plan during its execution. Simulations will show the advantages and limitations of such a modeling of the inland waterway network