An asynchronous solver for systems of ODEs linked by a directed tree structure
An asynchronous solver for systems of ODEs linked by a directed tree structure
复制标题
由有向树结构链接的 ODE 系统的异步求解器
DOI：
10.1016/j.advwatres.2012.10.011
复制
发表时间：
2013
影响因子：
4.7
通讯作者：
W. Krajewski
中科院分区：
文献类型：
--
作者：
S. Small;Laurent O. Jay;R. Mantilla;Rodica Curtu;L. Cunha;M. Fonley;W. Krajewski
本文记录了我们的发展和评估的数值求解系统的稀疏连接的常微分方程，方程之间的连接是由一个有向树。这些类型的系统出现在分布式水文模型。数值求解器基于允许异步积分的密集输出龙格-库塔方法。系统的一个分区用于在不同进程之间分配工作负载，从而实现利用分布式内存系统的并行实现。进程之间的通信是异步执行的。我们通过整合17,000 km 2河流流域的流量输运方程来说明求解器的功能，该流域被细分为305,000个子流域，这些子流域由河流网络相互连接。几个模型的数值实验进行了并行计算机上的运行时间和可扩展性。高效的数值积分器，如这里展示的一个带来更接近现实的目标，实现完全分布式实时洪水预报系统的支持下，基于物理的水文模型和高质量/高分辨率的降雨产品。
This paper documents our development and evaluation of a numerical solver for systems of sparsely linked ordinary differential equations in which the connectivity between equations is determined by a directed tree. These types of systems arise in distributed hydrological models. The numerical solver is based on dense output Runge–Kutta methods that allow for asynchronous integration. A partition of the system 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 ∼17,000km2river basin subdivided into 305,000 sub-watersheds that are interconnected by the river network. Numerical experiments for a few models are performed and the runtimes and scalability on our parallel computer are presented. Efficient numerical integrators such as the one demonstrated here bring closer to reality the goal of implementing fully distributed real-time flood forecasting systems supported by physics based hydrological models and high-quality/high-resolution rainfall products.