Collaborative Uploading in Heterogeneous Networks: Optimal and Adaptive Strategies

@article{KhudaBukhsh2018CollaborativeUI,
  title={Collaborative Uploading in Heterogeneous Networks: Optimal and Adaptive Strategies},
  author={Wasiur R. KhudaBukhsh and Bastian Alt and Sounak Kar and Amr Rizk and Heinz Koeppl},
  journal={IEEE INFOCOM 2018 - IEEE Conference on Computer Communications},
  year={2018},
  pages={1-9}
}
Collaborative uploading describes a type of crowd-sourcing scenario in networked environments where a device utilizes multiple paths over neighboring devices to upload content to a centralized processing entity such as a cloud service. Intermediate devices may aggregate and preprocess this data stream. Such scenarios arise in the composition and aggregation of information, e.g., from smart phones or sensors. We use a queuing theoretic description of the collaborative uploading scenario… 

Figures from this paper

Provisioning and Performance Evaluation of Parallel Systems with Output Synchronization

This article establishes a Large Deviations Principle for the steady-state job waiting times in an FJ system based on Markov-additive processes and provides computable bounds on the tail probabilities of the Steady-state waiting times.

User-centric Video in the Future Internet: QoE in Participatory Video Generation and Distribution

A new method based on device context measurements that allows to drastically improve efficiency in such automatic video composition systems by identifying the relevant quality indicators on the device based on derived sensor and network measurements is presented.

Transitions: A Protocol-Independent View of the Future Internet

This paper formalizes the concept of Transitions, i.e., a method to instrumentalize adaptivity at runtime in communication systems and shows how this concept maps intuitively to the Internet model which makes a protocol-independent deployment of applications feasible in the future Internet.

References

SHOWING 1-10 OF 30 REFERENCES

On file delay minimization for content uploading to media cloud via collaborative wireless network

This paper shows that the file delay is penalized by a path-starvation effect, which results from poor packet allocation among different paths, and proposes an iterative algorithm to assign packets into a set of chosen paths to alleviate the path starvation problem.

Enabling crowdsourced live event coverage with adaptive collaborative upload strategies

This paper proposes a set of strategies to collaboratively upload the most relevant streams at high quality by utilizing freed resources, and argues that these strategies can be exchanged during runtime to adapt to user dynamics and network heterogeneity.

Delay comparison of delivery and coding policies in data clusters

A set of evolution equations are developed and explored as a unified model which allows for both efficient simulation and mathematical analysis of several delivery policies under general statistical assumptions and quantifies in what sense a workload aware delivery policy performs better than a workload agnostic policy.

Optimizing stochastic scheduling in fork-join queueing models: Bounds and applications

This paper provides computable stochastic bounds for the waiting and response time distributions for heterogeneous FJ systems under general parallelization benefit and provides optimal scheduling strategies for arbitrary scaling regimes that map to different levels of parallelized benefit.

A Generalized Performance Evaluation Framework for Parallel Systems with Output Synchronization

This work presents a Markov-additive process framework for an FJ system and provides computable bounds on tail probabilities of steady-state waiting times, for both types of servers separately, and calibrates the model with real data traces, and illustrates how its bounds can be used to devise provisions.

Computable Bounds in Fork-Join Queueing Systems

This paper provides the first computable stochastic bounds on the waiting and response time distributions in FJ systems, and shows that, at moderate to high utilizations, multipath routing 'makes sense' from a queueing perspective for two paths only.

Robust scheduling in a flexible fork-join network

This paper proposes a robust scheduling policy for the flexible fork-join network model, and proves that it is rate stable when service rates can be written as products of a task-dependent quantity and a server- dependent quantity.

On Minimum-Delay Data Block Transport over Two-Connected Mesh Networks

  • Yonggang WenJun Sun
  • Computer Science
    2007 IEEE Wireless Communications and Networking Conference
  • 2007
The whole spectrum of optimal packet allocation policies as a function of block sizes are characterized, and it is concluded that the existing rate-based allocation policy is a special case for large data block.

Efficient Redundancy Techniques for Latency Reduction in Cloud Systems

A general redundancy strategy is designed that achieves a good latency-cost trade-off for an arbitrary service time distribution and generalizes and extends some results in the analysis of fork-join queues.