A Parallel Domain Decomposition FDTD Algorithm Based on Cloud Computing

Author

Haiming Lin ; Xiaohu Liu ; Kangyu Jia ; Wei Fu

Author_Institution

Dept. of Mech., Huazhong Univ. of Sci. & Technol., Wuhan, China

fYear

2013

fDate

7-8 Dec. 2013

Firstpage

252

Lastpage

259

Abstract

This paper presents a parallel domain decomposition finite difference time domain (DD-FDTD) algorithm based on MapReduce architectural pattern in a Hadoop cloud computing cluster. The algorithm is implemented on a 6-nodes Hadoop laboratory test cloud computing cluster to compute the electromagnetic fields of lightning in the downtown area in Shanghai city, PR China. The speedup ratio under different numbers of computational sub domains is evaluated. It shows that the maximum speedup ratio of the algorithm implemented on our Hadoop cluster is about 2.4, which will increase with the scale of the mesh model and the nodes of the Hadoop cluster.

Keywords

cloud computing; finite difference time-domain analysis; DD-FDTD algorithm; Hadoop laboratory test cloud computing cluster; MapReduce architectural pattern; computational subdomains; electromagnetic fields; parallel domain decomposition FDTD algorithm; parallel domain decomposition finite difference time domain algorithm; Approximation methods; Boundary conditions; Cloud computing; Clustering algorithms; Finite difference methods; Scientific computing; Time-domain analysis; Cloud computing; Domain Decomposition method; Electromagnetic Fields of Lightning; FDTD method; Hadoop; MapReduce;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Science and Cloud Computing Companion (ISCC-C), 2013 International Conference on

Conference_Location

Guangzhou

Type

conf

DOI

10.1109/ISCC-C.2013.28

Filename

6973601