Large eddy simulation of the wind flow in a realistic full-scale urban community with a scalable parallel algorithm

被引:10
作者
Yan, Zhengzheng [1 ,2 ]
Chen, Rongliang [1 ,2 ]
Cai, Xiao-Chuan [3 ]
机构
[1] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen 518055, Peoples R China
[2] Shenzhen Key Lab Exascale Engn & Sci Comp, Shenzhen 518055, Peoples R China
[3] Univ Macau, Dept Math, Macau, Peoples R China
关键词
Urban wind flow; Parallel computing; Domain decomposition method; Large eddy simulation; Unstructured mesh; COMPUTATIONAL FLUID-DYNAMICS; FIELD POLLUTANT DISPERSION; CFD SIMULATION; K-EPSILON; COOPERATIVE PROJECT; ENVIRONMENT; LES; BUILDINGS; VENTILATION; PREDICTION;
D O I
10.1016/j.cpc.2021.108170
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Turbulence and large computational domains make urban wind flow simulation a computationally challenging problem. To reduce the total simulation time and efficiently use today's new generation of supercomputers with massive processors, scalable parallel solvers are needed. In this work, we present a scalable domain decomposition method based 3D incompressible Navier-Stokes solver for the simulation of unsteady, complex wind flows around urban communities. A large eddy simulation with Smagorinsky modeling is employed for the simulation of the turbulent wind flows. On a fine unstructured grid, we discretize the spatial and temporal dimensions using a stabilized P1 - P1 finite element method and an implicit backward Euler finite difference method, respectively. The resulting large-scale nonlinear algebraic system at each timestep is solved by a Newton-Krylov-Schwarz algorithm in parallel. The solver is first validated by a benchmark case where the numerical results are compared with measured data from a wind tunnel. Then, the wind flow field of a realistic actual-scale urban community with a group of buildings in the downtown area of Shenzhen, China, is studied. The numerical results show that the flow field matches with the experimental data for the benchmark problem, and some reasonable, detailed, and complex flow structures are obtained for the urban community simulation case. The scalability of the solver is studied on the TianHe-2A and Sunway TaihuLight supercomputers, and the solver scales up to 16,384 processor cores for a grid with over 20 million elements, which implies that the solver has the potential to perform fast and high-fidelity simulations of large-scale wind flows in complicated computational domains. (c) 2021 Published by Elsevier B.V.
引用
收藏
页数:14
相关论文
共 55 条
  • [11] Application of computational fluid dynamics in building performance simulation for the outdoor environment: an overview
    Blocken, Bert
    Stathopoulos, Ted
    Carmeliet, Jan
    Hensen, Jan L. M.
    [J]. JOURNAL OF BUILDING PERFORMANCE SIMULATION, 2011, 4 (02) : 157 - 184
  • [12] Cai X.-C., 1994, NUMERICAL METHODS NA, P17
  • [13] A restricted additive Schwarz preconditioner for general sparse linear systems
    Cai, XC
    Sarkis, M
    [J]. SIAM JOURNAL ON SCIENTIFIC COMPUTING, 1999, 21 (02) : 792 - 797
  • [14] Cao M., 2014, J APPL MATH, V2014
  • [15] A parallel non-nested two-level domain decomposition method for simulating blood flows in cerebral artery of stroke patient
    Chen, Rongliang
    Wu, Bokai
    Cheng, Zaiheng
    Shiu, Wen-Shin
    Liu, Jia
    Liu, Liping
    Wang, Yongjun
    Wang, Xinhong
    Cai, Xiao-Chuan
    [J]. INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN BIOMEDICAL ENGINEERING, 2020, 36 (11)
  • [16] Equations for the Drag Force and Aerodynamic Roughness Length of Urban Areas with Random Building Heights
    Crago, Richard D.
    Okello, Winnie
    Jasinski, Michael F.
    [J]. BOUNDARY-LAYER METEOROLOGY, 2012, 145 (03) : 423 - 437
  • [17] Computational evaluation of wind loads on buildings: a review
    Dagnew, Agerneh K.
    Bitsuamlak, Girma T.
    [J]. WIND AND STRUCTURES, 2013, 16 (06) : 629 - 660
  • [18] GLOBALLY CONVERGENT INEXACT NEWTON METHODS
    EISENSTAT, SC
    WALKER, HF
    [J]. SIAM JOURNAL ON OPTIMIZATION, 1994, 4 (02) : 393 - 422
  • [19] Choosing the forcing terms in an inexact Newton method
    Eisenstat, SC
    Walker, HF
    [J]. SIAM JOURNAL ON SCIENTIFIC COMPUTING, 1996, 17 (01) : 16 - 32
  • [20] STABILIZED FINITE-ELEMENT METHODS .2. THE INCOMPRESSIBLE NAVIER-STOKES EQUATIONS
    FRANCA, LP
    FREY, SL
    [J]. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 1992, 99 (2-3) : 209 - 233