Efficient Parallelization of RMCRT for Large Scale LES Combustion Simulations

Abstract

At the high temperatures inherent to combustion systems, radiation is the dominant mode of heat transfer. An accurate simulation of a combustor therefore requires precise treatment of radiative heat transfer. This is accomplished by calculating the radiative-flux divergence at each cell of the discretized domain. Reverse Monte Carlo Ray Tracing (RMCRT) is one of the few numerical techniques that can accurately solve for the radiative-flux divergence while accounting, in an efficient manner, for the effects of participating media. Furthermore, RMCRT lends itself to massive parallelism because the intensities of each ray are mutually exclusive. Therefore, multiple rays can be traced simultaneously at any given time step. We have created a parallelized RMCRT algorithm that solves for the radiative-flux divergence in combustion systems. This algorithm has been verified against a 3D benchmark case involving participating media. The error of this algorithm converges with an increase in the number of rays traced per cell, such that at 700 rays per cell, the L2 error norm of a 41 3 mesh is 0.49%. Our algorithm demonstrates strong scaling when run in parallel on 2 to 1536 processors for domains of 128 3 and 256 3 cells.