A Distributed Computing Platform Supporting Power System Security Knowledge Discovery Based on Online Simulation

• Published in: IEEE transactions on smart grid Vol. 8; no. 3; pp. 1513 - 1524
• Main Authors: Huang, Tian-en, Guo, Qinglai, Sun, Hongbin
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.05.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Computational modeling; Computer networks; Computer simulation; Computing time; Cybersecurity; Data analysis; Data management; Data mining; Distributed computing platform; Distributed databases; distributed feature selection; distributed massive sampling simulation; Distributed processing; Electric power distribution; Knowledge discovery; On-line systems; online simulation; Power system security; power system security knowledge discovery; Power system stability; Simulation; System effectiveness; China
• ISSN: 1949-3053; 1949-3061
• DOI: 10.1109/TSG.2016.2571442

Power systems are generating masses of data, including measurement and simulation data. To operate and control power systems more effectively, this paper establishes a distributed platform to store, read, and compute massive amounts of data. Our distributed computing platform can support online simulation based power system security knowledge discovery through big data analysis. First, a framework for a distributed computing platform is designed. Then, distributed algorithms are developed, including a distributed massive sampling simulation method and a distributed feature selection method. Next, the software platform and hardware platform for the distributed computing platform are established. Finally, the platform is applied to the Guangdong Province Power System in China to evaluate its accuracy and efficiency. The simulation results show that the distributed computing platform can improve computing efficiency and perform better than a centralized platform.