Design analysis for real-time video transcoding on cloud systems

  • Authors:
  • Seungcheol Ko;Seongsoo Park;Hwansoo Han

  • Affiliations:
  • Sungkyunkwan University, Suwon, Korea;Sungkyunkwan University, Suwon, Korea;Sungkyunkwan University, Suwon, Korea

  • Venue:
  • Proceedings of the 28th Annual ACM Symposium on Applied Computing
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

The same video contents tend to exist in various formats depending on encodings and resolutions, as there are many different codecs and devices of various screen sizes. Particularly, when videos are consumed by a viewer on multiple screens, such as digital TVs, smartphones and tablets, appropriate formats of videos need to be delivered to client viewers. Video transcoding is inevitable to handle such cases. Since real-time video transcoding requires enormous computing power, cloud computing has emerged as a strong candidate to process many transcoding requests. However, resource provision for cloud computing is an essential part in cloud transcoding systems. With a given video request, we need to estimate how many machines will suffice the requests and how much cache space is appropriate for real-time transcoding. In this paper, we provide an analytic simulation for cloud transcoding systems with cache capability and explore a required number of machines and amount of cache size to handle given video transcoding requests.