An analysis of live streaming workloads on the internet

@inproceedings{Sripanidkulchai2004AnAO,
  title={An analysis of live streaming workloads on the internet},
  author={Kunwadee Sripanidkulchai and Bruce M. Maggs and Hui Zhang},
  booktitle={IMC '04},
  year={2004}
}
In this paper, we study the live streaming workload from a large content delivery network. Our data, collected over a 3 month period, contains over 70 million requests for 5,000 distinct URLs from clients in over 200 countries. To our knowledge, this is the most extensive data of live streaming on the Internet that has been studied to date. Our contributions are two-fold. First, we present a macroscopic analysis of the workload, characterizing popularity, arrival process, session duration, and… 

Analysis of multimedia workloads with implications for internet streaming

TLDR
The design of AutoStream is proposed, an innovative system that can provide additional previewing and streaming services automatically for media objects hosted on standard Web sites in server farms at the client's will.

A Workload Analysis of Live Event Broadcast Service in Cloud

Streaming media over the Internet: Flow based analysis in live access networks

TLDR
This paper investigates multimedia streaming services over the Internet using live access fiber-to-the-home networks and studies parameters like traffic volume and flow characteristics for selected services, especially the Swedish P2P video service Voddler and the Swedish music service Spotify.

The stretched exponential distribution of internet media access patterns

TLDR
This study provides an analytical basis for applying a P2P model rather than a client-server model to build large scale Internet media delivery systems and analyzes the effectiveness of media caching with a mathematical model.

Deploying P2P networks for large-scale live video-streaming service [Peer-to-Peer Multimedia Streaming]

TLDR
This article mainly presents the experience on a practical P2P-based live video- streaming system called GridMedia, which was employed to broadcast live the Chinese Spring Festival Gala show over the Internet.

Deploying P2P networks for large-scale live video-streaming service [Peer-to-Peer Multimedia Streaming]

TLDR
This article mainly presents the experience on a practical P2P-based live videostreaming system called GridMedia, which was employed to broadcast live the Chinese Spring Festival Gala show over the Internet.

A trace study for characteristics of packet arrivals

TLDR
An analysis of four traces collected by NLANR is presented, uncovering the characteristics of their packet arrival processes and investigates the variations of packet arriving bit rate for long-lived streams (flows) and finds that high speed streams are more likely to be accumulated and exhibit high level of burstiness.

An Analysis of User Dynamics in P2P Live Streaming Services

TLDR
This work collects massive user traces from the largest P2P live streaming site in Korea, namely, Afreeca, and analyzes user dynamics in the service in terms of three criteria: long-stay users, short-stay Users, and user churn.

An Access Pattern Model Analysis for Online VoD Multimedia Flow for Bigdata

  • Zhijie HanJiao MaHui Zhao
  • Computer Science
    2018 IEEE 4th International Conference on Big Data Security on Cloud (BigDataSecurity), IEEE International Conference on High Performance and Smart Computing, (HPSC) and IEEE International Conference on Intelligent Data and Security (IDS)
  • 2018
TLDR
Through extensive analysis and modeling, it is found the object reference ranks of all these workloads follow the logistic distribution despite their different media systems and delivery methods, This mean it does not follow long tail effect; and the effectiveness of media caching with a mathematical model is analyzed.
...

References

SHOWING 1-10 OF 25 REFERENCES

A hierarchical characterization of a live streaming media workload

TLDR
A thorough characterization of what is believed to be the first significant live Internet streaming media workload in the scientific literature is presented, and a model for live media workload generation is presented that incorporates many of the findings, and which is implemented in GISMO.

Measurement and Analysis of a Streaming Media Workload

TLDR
A client-based streaming- media workload generated by a large organization is presented, media workload characteristics are compared to traditional Web-object workloads, and the effectiveness of performance optimizations on streaming-media workloads are explored.

Distributing streaming media content using cooperative networking

TLDR
This work considers the problem that arises when the server is overwhelmed by the volume of requests from its clients, and proposes Cooperative Networking (CoopNet), where clients cooperate to distribute content, thereby alleviating the load on the server.

Characteristics of WWW Client-based Traces

TLDR
This paper presents a descriptive statistical summary of the traces of actual executions of NCSA Mosaic, and shows that many characteristics of WWW use can be modelled using power-law distributions, including the distribution of document sizes, the popularity of documents as a function of size, and the Distribution of user requests for documents.

Measurement, modeling, and analysis of a peer-to-peer file-sharing workload

TLDR
Unlike the Web, whose workload is driven by document change, it is demonstrated that clients' fetch-at-most-once behavior, the creation of new objects, and the addition of new clients to the system are the primary forces that drive multimedia workloads such as Kazaa.

Designing overlay multicast networks for streaming

TLDR
A polynomial time approximation algorithm for designing a multicast overlay network that satisfies capacity and reliability constraints to within a constant factor of optimal, and cost to within alogarithmic factor is presented.

The feasibility of supporting large-scale live streaming applications with dynamic application end-points

TLDR
This paper looks at three key requirements for feasibility of supporting large-scale live streaming using an application end-point architecture, and shows that simple algorithms have the potential to meet these requirements in practice.

An empirical study of realvideo performance across the internet

TLDR
Analysis from a wide-scale empirical study of RealVideo traffic from several Internet servers to many geographically diverse users finds typical RealVideos to have high quality, achieving an average frame rate of 10 frames per second and very smooth playout, but very few videos achieve full-motion frame rates.

Web caching and Zipf-like distributions: evidence and implications

  • L. BreslauP. CaoLi FanGraham PhillipsS. Shenker
  • Computer Science
    IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320)
  • 1999
TLDR
This paper investigates the page request distribution seen by Web proxy caches using traces from a variety of sources and considers a simple model where the Web accesses are independent and the reference probability of the documents follows a Zipf-like distribution, suggesting that the various observed properties of hit-ratios and temporal locality are indeed inherent to Web accesse observed by proxies.

Characterizing reference locality in the WWW

TLDR
The authors propose models for both temporal and spatial locality of reference in streams of requests arriving at Web servers and show that temporal locality can be characterized by the marginal distribution of the stack distance trace, and proposed models for typical distributions and compare their cache performance to the traces.