A method for solving sparse linear equations of power systems based on GPU

被引：1
|
作者：
Key Laboratory of Control of Power Transmission and Conversion , Ministry of Education, Shanghai [1 ]
200240, China
不详 [2 ]
100192, China
机构：
[1] Key Laboratory of Control of Power Transmission and Conversion (Shanghai Jiao Tong University), Ministry of Education, Shanghai
[2] China Electric Power Research Institute, Beijing
来源：
Dianli Xitong Zidonghue | / 2卷 / 74-80期
关键词：
Graphics processing unit (GPU); Parallel computation; Power systems; Sparsity technology; Speed-up ratio; Transient stability computation;
D O I：
10.7500/AEPS20131115005
中图分类号：
学科分类号：
摘要：
In view of the sparsity of large-scale system of linear equations of power systems, a direct method for solving the sparse system of equations based on graphics processing units (GPUs) is proposed. In this method, the coefficient matrix of equations are partitioned by the ordering-first block bordered diagonal form (BBDF) partition method so that two levels of parallel structure are formed for solving the sparse linear equations with Blocks and Threads of GPUs in succession. The partition results are applied to the power system transient stability calculation, and the speed-up ratio performance of the method proposed is tested. The test results show that the proposed method is able to achieve a 3~4-fold speed-up ratio in currently used devices, and a prospective 7~8-fold speed-up ratio in the high-end devices. ©, 2015 State Grid Electric Power Research Institute Press.
引用
收藏
页码：74 / 80
页数：6
相关论文
共 12 条
  • [1] Ji X., A comparative study on parallel processing applied in power system, Power System Technology, 27, 4, pp. 22-26, (2003)
  • [2] Su X., Mao C., Lu J., Parallel load flow calculation of block bordered model, Power System Technology, 26, 1, pp. 22-25, (2002)
  • [3] Zhao W., Fang X., Yan Z., Nested BBDF partitioning algorithm in power system parallel computation, Proceedings of the CSEE, 30, 25, pp. 66-73, (2010)
  • [4] Xue W., Shu J., Wang X., Et al., Advance of parallel algorithm for power system transient stability simulation, Journal of System Simulation, 14, 2, pp. 177-182, (2004)
  • [5] Lu J., Yu L., Zhu Y., Application of PC cluster system to transient stability analysis of electric power system, Journal of North China Electric Power University, 32, 2, pp. 25-28, (2006)
  • [6] Zhou T., Yan Z., Tang C., Et al., A parallel algorithm for transient stability computing based on multi-core processor technology, Automation of Electric Power Systems, 37, 8, pp. 70-75, (2013)
  • [7] Jiang H., Jiang Q., A parallel transient stability algorithm for large-scale power system based on GPU platform, Power System Protection and Control, 41, 4, pp. 13-20, (2013)
  • [8] Tang C., Yan Z., Zhou T., Application of graph processing unit-based generalized minimal residual iteration in power system transient simulation, Power System Technology, 37, 5, pp. 1365-1371, (2013)
  • [9] Zhang N., Gao S., Zhao X., A fine granularity parallel algorithm for electromechanical transient stability simulation based on graphic processing unit, Automation of Electric Power Systems, 36, 9, pp. 54-60, (2012)
  • [10] Tomov S., Nath R., Ltaief H., Et al., Dense linear algebra solvers for multicore with GPU accelerators, 24th IEEE International Symposium on Parallel and Distributed Processing (IPDPS 2010)
12