Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Grid Computing System based on Web Worker for Smart TV Environments

스마트 TV환경에 적합한 Web Worker 기반의 그리드 컴퓨팅 시스템

  • Kim, Hyun-Sik (Dept. of Computer and Information Engineering, Inha University) ;
  • Jo, Geun-Sik (Dept. of Computer and Information Engineering, Inha University)
  • 김현식 (인하대학교 컴퓨터정보공학과) ;
  • 조근식 (인하대학교 컴퓨터정보공학과)
  • Received : 2011.09.28
  • Accepted : 2011.10.13
  • Published : 2012.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

In recent years, there has been a popularity rose up on Smart TV (Smart Television) usage at home. Therefore, it is also have increase the demand on grid computing system. Smart TV has a variety of platform and usage compare to PC (Personal computer). Base on this, it is difficult to apply a traditional grid system on Smart TV. One major reason are concerning the small idle time compare to PC. To overcome this problem, this paper will propose a Javascript grid system and introducing a new scheduling policy that best suit for a smart TV. We have conduct an experiment on the proposed method. The result provides an average of 1.78 percent, which is improved compare to the traditional method which is only provides an average of 0.09 percent.

스마트TV의 보급이 확대되면서 스마트TV의 여유연산능력을 활용한 그리드 컴퓨팅시스템에 대한 수요가 증가할 것으로 예측하고 있다. 그러나 스마트TV는 PC와 달리 다양한 플랫폼이 존재하고, 또한 사용자들의 스마트 TV사용 패턴이 기존 PC 사용 패턴과 크게 다르기 때문에 PC기반의 그리드 시스템을 적용하기에는 어려움이 있다. 즉, 유휴 상태에서 동작하던 기존 그리드 에이전트가 스마트TV 환경에서는 동작할 기회를 보장 받을 수 없는 상황이 된 것이다. 본 논문에서는 이러한 문제를 극복하기 위하여 스마트TV에 적합한 자바스크립트 기반의 그리드 시스템 및 콘텐츠 시청 중에 남는 CPU자원을 활용하는 에이전트 스케줄링 정책을 제안하고 구현하였다. 그리고 기존 그리드 방식과 제안하는 방식을 비교 실험하여, 그 결과 기존의 그리드가 0.09%, 제안하는 방식은 평균 1.78%의 자원을 제공함을 보였다.

Keywords

References

  1. DisplaySearch Quarterly TV Design and Features Report, "DisplaySearch Connected TV Forecast," 2011.
  2. C. H. Noh, K. C. Cho, Y. B. Ma, and J. S. Lee, "Grid Resource Selection System Using Decision Tree Method," The Korea Society of Computer and Information, Vol. 13, No. 1 pp. 1-10, 2008.
  3. J. Y. Choe, W. J. Lee, and C. H. Jeon, "Real-Time Job Scheduling Strategy for Grid Computing," The Korea Society of Computer and Information, Vol. 15, No. 2, pp. 1-8, 2010.
  4. M. Baker, "Cluster Computing White Paper," University of Portsmouth, UK, pp. 3-12, 2000.
  5. O. Nov, D. Anderson, and O. Arazy, "Volunteer Com puting: A Model of the Factors Determining Contribution to Community-based Scientific Research," Proceedings of the 19th international conference on World wide web. pp. 741-750. 2010.
  6. D. P. Anderson, "SETI@home: an experiment in publ ic-resource computing," Communications of the ACM, Vol. 45, Issue 11, pp. 56-61, 2002.
  7. Google TV Features, http://www.google.com/tv/features.html
  8. Web Browse on Apple TV With Safari HD, http://gizmodo.com/357626/web-browse-on-apple-tv-with-safari-hd-out-now
  9. A. Welc, R. L. Hudson, T. Shpeisman, and A. Adl-Tabatabai, "Generic Workers - Towards Unified Distributed and Parellel JavaScript Programming Model," Programming Support Innovations for Emerging Distributed Applications, ACM New York, pp. 1-25. 2010.
  10. Web Worker, http://caniuse.com
  11. S. Okamoto, "Load Distribution by Using Web Wor kers for a Real-Time Web Application," iiWAS2010, pp. 592-597, 2010.
  12. Samsung Electronics, "Cable business development in the Smart TV environment," Samsung Electronics, http://goo.gl/pSPWY, p. 4, 2011.
  13. ECMAScript Language Specification, http://www.ecma-international.org/publications/files/ECMA-ST/ECMA-262.pdf
  14. Weekly ratings report, http://home.tnms.tv/rating
  15. Watch pattern survey for each household, http://www.reportshop.co.kr/dview/506775