Article
GPU-based Batch LU-Factorization Solver for Concurrent Analysis of Massive Power Flows
IEEE Transactions on Power Systems
Abstract
In many power system applications, such as N-x static security analysis and Monte-Carlo-simulation-based probabilistic power flow (PF) analysis, it is a very time-consuming task to analyze massive number of PFs on identical or similar network topology. This letter presents a novel GPU-accelerated batch LU-factorization solver that achieves higher level of parallelism and better memory-access efficiency through packaging massive number of LU-factorization tasks to formulate a new larger-scale problem. The proposed solver can achieve up to 76 times speedup when compared to KLU library and lays a critical foundation for massive-PFs-solving applications.
Department(s)
Electrical and Computer Engineering
Research Center/Lab(s)
Intelligent Systems Center
Keywords and Phrases
- Computer Graphics,
- Computer Graphics Equipment,
- Electric Load Flow,
- Electric Power Systems,
- Factorization,
- Intelligent Systems,
- Monte Carlo Methods,
- Parallel Processing Systems,
- Program Processors,
- Degree of Parallelism,
- LU Factorization,
- Network Topology,
- Power Flows,
- Power System Applications,
- Probabilistic Power Flow,
- Static Security Analysis,
- Time-Consuming Tasks,
- Graphics Processing Unit,
- Graphics Processing Unit (GPU),
- Parallel Computing,
- Power Flow
Document Type
Article - Journal
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2017 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
Publication Date
11-1-2017
Publication Date
01 Nov 2017
Disciplines
Citation Information
Gan Zhou, Rui Bo, Lungsheng Chien, Xu Zhang, et al.. "GPU-based Batch LU-Factorization Solver for Concurrent Analysis of Massive Power Flows" IEEE Transactions on Power Systems Vol. 32 Iss. 6 (2017) p. 4975 - 4977 ISSN: 0885-8950,15580679 Available at: http://works.bepress.com/rui-bo/33/