A Calculation Method for the International Benchmark Problem of TEAM 7 Based on Elastic Cluster in Cloud Computing

作者：Jin Liang; Wang Dongmei; Qiu Yuntao^*; Yang Qingxin; Niu Pingjuan

来源：Transactions of China Electrotechnical Society, 2017, 32(8): 144-150.

• Cloud computing platforms
• Eddy current fields
• Finite element simulations
• High performance computing
• High performance parallel computing
• Large scale computing problems
• Message passing interface
• Parallel programming model

Different development models of cloud computing were comparatively analyzed for intelligent manufacturing in this paper, focusing on large-scale computing problems. A kind of compute-intensive cloud architecture has been chosen, and then an elastic computing platform containing nine computing nodes has been set up. Taken the international benchmark problem of TEAM 7 in the electromagnetic field as a case, the parallel computing program of the typical eddy current field was written by the open source parallel programming model OpenMpi, based on the message passing interface. The parallel computing cases, with hundreds of large-scale computing nodes, have been carried out. Accordingly, the distribution graphs of computational time and rate under different computational scales and different nodes were painted. It is proved that the parallelization of the large-scale finite element simulation of typical electrical equipment can be achieved in the elastic computing cluster, which is deployed in the cloud-computing platform. Compared with the traditional high-performance parallel computing method, the elastic computing cluster in cloud computing has a series of merits, such as low investing cost, dynamic distribution, obtain on demand. Thus a flexible and convenient new computing scheme is provided for upgrading from pure traditional manufacturing industry to intelligent manufacturing industry impelled by innovation.

• 出版日期2017
• 单位天津工业大学