Title: Fault recovery system for smart grid based on machine statistical learning
Authors: Min Zhu; Juncheng Peng; Lixing Zhou
Addresses: School of Computer Software, Weifang University of Science and Technology, Weifang, 262700, China ' Changsha University of Science and Technology, Changsha 410114, China ' Changsha University of Science and Technology, Changsha 410114, China
Abstract: In order to overcome the problems of poor robustness, low-accuracy and long time-consuming when traditional system recovers power grid faults, a fault recovery system based on machine statistical learning is designed. The system framework consists of sensing layer, network layer and application layer. Through the overall framework of the system, the hardware of the system is designed, including data acquisition device block, transmission device, analysis module and display device. In the software part, fault acquisition subroutine, fault location subroutine and fault type identification subroutine are designed to obtain accurate fault data. Finally, machine statistical learning method is used to complete the design of fault recovery subroutine of smart grid, recover the obtained fault data and realise the design of fault recovery system of smart grid. The results show that the robustness, accuracy and time-consumption of the system are improved, and the problems existing in the traditional system are solved.
Keywords: machine statistical learning; smart grid; fault; recovery system.
DOI: 10.1504/IJCIS.2020.10033294
International Journal of Critical Infrastructures, 2021 Vol.17 No.3, pp.271 - 287
Received: 11 Feb 2020
Accepted: 05 Jun 2020
Published online: 15 Oct 2021 *