The Transactions of the Korean Institute of Electrical Engineers P (전기학회논문지P)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지
DOI QR코드

DOI QR Code

Analyzing Smart Grid Energy Data using Hadoop Based Big Data System

하둡기반 빅데이터 시스템을 이용한 스마트그리드 전력데이터 분석

  • Cho, YoungTak (Department of Information and Computer Engineering, Ajou University) ;
  • Lee, WonJin (Department of Computer Science, Kyonggi University) ;
  • Lee, Ingyu (Sorrell College of Business, Troy University) ;
  • On, Byung-Won (Department of Statistics and Computer Science, Kunsan National University) ;
  • Choi, Jung-In (Smart Grid Research Center, Advanced Institutes of Convergence Technology)
  • Received : 2015.02.02
  • Accepted : 2015.05.19
  • Published : 2015.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

With the increasing popularity of Smart Grid infrastructure, it is much easier to collect energy usage data using AMI (Advanced Measuring Instrument) from residential housing, buildings and factories. Several researches have been done to improve an energy efficiency by analyzing the collected energy usage data. However, it is not easy to store and analyze the energy data using a traditional relational database management system since the data size grows exponentially with an increasing popularity of Smart grid infrastructure. In this paper, we are proposing a Hadoop based Big data system to store and analyze energy usage data. Based on our limited experiments, Hadoop based energy data analysis is three times faster than that of a relational database management system based approach with the current system.

Keywords

References

  1. Smartgrid website, http://www.smartgrid.or.kr, Korea smartgrid association, 2013.
  2. Demand Reductions from the Application of Advanced Metering Infrastructure, Pricing Programs, and Customer-Based Systems-Initial Results, SmartGrid.gov, December, 2012.
  3. Demand side management using ICT and technologies, Ministry of Trade, Industry and Energy, August, 2013.
  4. Big data understanding and applications, B. On, KETEP, December, 2012.
  5. Ultra Large-Scale Power System Control Architecture, SmartGrid.gov, October 2012.
  6. Hadoop The Definitive Guide, 3rd Ed. W. Tom, OReilly Media, July 2009.
  7. Hbase: The Definitive Guide, G. Lars, OReilly, August 2011.
  8. Programming Hive, C. Edward, OReilly Media, November 2012.
  9. MapReduce: Simplified Data Processing on Large Clusters, J. Dean and S. Ghemawat, Communications of the ACM, Vol. 51, No. 1, pp. 107-113, 2008. https://doi.org/10.1145/1327452.1327492
  10. A Big Data Management System for Energy Consumption Prediction Models, W. Lee, B. On, I. Lee and J. Choi, Proceedings of International Conference on Digital Information Management (ICDIM), BangKok, Thailand, pp. 156-161, October, 2014.
  11. Simple one-pass algorithm for penalized linear regression with cross-validation on MapReduce, e-Print arXiv:1307.0048 (2013)
  12. Development of Sensor Based Energy Management System, D. Um, J. Choi and I. Lee, Journal of the Korean Institute of Illuminating and Electrical Installation Engineers, Vol. 28, No. 10, pp. 69-74, 2014. https://doi.org/10.5207/JIEIE.2014.28.10.069
  13. A Study on Demand-Side Resource Management Based on Big Data System, J. Yoon, I. Lee and J. Choi, The Transactions of the Korean Institute of Electrical Engineers, Vol. 63, No. 8. pp. 1116:1120, 2014. https://doi.org/10.5370/KIEE.2014.63.8.1116

Cited by

  1. A Study on Prediction Model of Equipment Failure Through Analysis of Big Data Based on RHadoop 2018, https://doi.org/10.1007/s11277-017-4151-1