A Fast Fault Diagnosis Method for Electric Energy Metering Device Based on Spark Streaming

DOI

10.2991/icmcm-16.2016.58How to use a DOI?

Keywords

Spark Streaming; Stream Processing; Fault Diagnosis; Electric Energy Metering Device

Abstract

We present a fast fault diagnosis framework based on Spark Streaming for real-time online monitoring and fault diagnosis of electric energy metering device. In this framework, data collected by the power consumption information collection system is used as experimental in put data, which is simulated as a real-time data stream. The BP neural network is applied to the fault diagnosis of metering device on the Spark Streaming cluster. The experimental results show that the processing speed of this stream processing cluster mode is higher than that of the traditional stand-alone mode, which can satisfy the requirement of fast fault diagnosis of massive data in smart grid.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zeyuan Duan
AU  - Dewen Wang
PY  - 2016/12
DA  - 2016/12
TI  - A Fast Fault Diagnosis Method for Electric Energy Metering Device Based on Spark Streaming
BT  - Proceedings of the 2016 7th International Conference on Mechatronics, Control and Materials (ICMCM 2016)
PB  - Atlantis Press
SP  - 285
EP  - 288
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmcm-16.2016.58
DO  - 10.2991/icmcm-16.2016.58
ID  - Duan2016/12
ER  -