Simulation of a Distributed Flood Control System using a Parallel Asynchronous Solver for Systems of ODEs

Ricardo Mantilla, Luciana K. Cunha, Witold F. Krajewski, Scott J. Small, Laurent O. Jay, Morgan Fonley, and Rodica Curtu


Rainfall Runoff Models, asynchronous solver, floods, reservoirs, river networks


A recently developed parallel asynchronous solver for systems of ordinary differential equations (ODEs) is used to simulate flows along the channels in a river network. In our model, precipitation is applied over the hillslopes adjacent to the river network links and water movement from hillsope to link and along the river network is represented as a system of ODEs. The numerical solver is based on dense output Runge-Kutta methods that allow for asynchronous integration. A static partition method is used to distribute the workload among different processes, enabling a parallel implementation that capitalizes on a distributed memory system. Communication between processes is performed asynchronously. We illustrate the solver capabilities by integrating flow transport equations for a ~32,000 km2 river basin subdivided into 574,000 sub-watersheds that are interconnected by the river network. We show that the runtime for an eight month-long simulation forced by 1-km resolution NEXRAD rainfall is completed in under 4 minutes using 64 computing nodes. In addition, we include equations to simulate small reservoirs spread throughout the river network and estimate changes in hydrographs at multiple locations. Our results provide a firm theoretical basis for the concept of distributed flood control systems.

Important Links:

Go Back