BOINC: A Platform for Volunteer Computing

@article{Anderson2019BOINCAP,
  title={BOINC: A Platform for Volunteer Computing},
  author={David P. Anderson},
  journal={Journal of Grid Computing},
  year={2019},
  volume={18},
  pages={99-122}
}
  • D. Anderson
  • Published 5 March 2019
  • Computer Science
  • Journal of Grid Computing
“Volunteer computing” is the use of consumer digital devices for high-throughput scientific computing. It can provide large computing capacity at low cost, but presents challenges due to device heterogeneity, unreliability, and churn. BOINC, a widely-used open-source middleware system for volunteer computing, addresses these challenges. We describe BOINC’s features, architecture, implementation, and algorithms. 

Globally Scheduling Volunteer Computing

This work describes the scheduling policy used in Science United, a global manager for volunteer computing, and describes how to dynamically assign devices to projects in a way that satisfies various constraints and that balances various goals.

Pando: A Volunteer Computing Platform for the Web

A command-line version of Pando is implemented that makes it easy to launch volunteer computing projects on the Web as part of a Unix processing pipeline and enables a thousand browser tabs to be used for computation.

Pando: Personal Volunteer Computing in Browsers

It is shown that Pando can provide throughput improvements compared to a single personal device, on a variety of compute-bound applications including animation rendering and image processing, and the flexibility of the approach is shown by deploying Pando on personal devices connected over a local network.

Decentralized Computation Market for Stream Processing Applications

An architecture combining a distributed trusted computing mechanism, such as a blockchain, with an efficient messaging system like Apache Pulsar is introduced, which designs a decentralized computation market where customers and suppliers make offers to deploy and host applications.

Data Processing Model to Perform Big Data Analytics in Hybrid Infrastructures

A data distribution model composed of Cloud Computing and Volunteer Computing environments in a hybrid fashion for Big Data analytics is proposed, indicating the feasibility of using a hybrid infrastructure with up to 35% of unstable machines in the worst-case scenario, without losing performance and a monetary cost lower than 20% in comparison to Classical Cloud Computing.

Start-up and the Results of the Volunteer Computing Project RakeSearch

The experience of setting up a computational infrastructure based on BOINC middleware and running a volunteer computing project on its basis to characterize the space of diagonal Latin squares in the form of an ensemble of orthogonality graphs is described.

Towards Elasticity in Heterogeneous Edge-dense Environments

This paper introduces a densely-distributed edge resource model that leverages capacity-constrained volunteer edge nodes to support elastic computation offloading and enables the use of geo- Distributed edge node nodes to further support elasticity.

Armada: A Robust Latency-Sensitive Edge Cloud in Heterogeneous Edge-Dense Environments

This paper introduces Armada: a denselydistributed edge cloud infrastructure that explores the use of dedicated and volunteer resources to serve geo-distributed users in heterogeneous environments and describes the lightweight Armada architecture and optimization techniques including performance-aware edge selection, auto-scaling and load balancing on the edge, fault tolerance, and in-situ data access.

Research on the Task Assignment Problem with Maximum Benefits in Volunteer Computing Platforms

A list-based task assignment (LTA) strategy is proposed, and it is proved that the LTA strategy could complete the task with a deadline constraint as soon as possible, and a maximum benefit scheduling (MBS) algorithm, which aimed at maximizing the benefits of VCPs is proposed.

Resource Profiling and Performance Modeling for Distributed Scientific Computing Environments

Evaluation results demonstrate that the proposed prediction schemes outperform well-known common approaches in terms of accuracy, and actually can help users in a shared resource environment to run their large-scale applications by effectively forecasting various computing resource capacity and performance.
...

References

SHOWING 1-10 OF 73 REFERENCES

Building a Volunteer Cloud

Volunteer computing provides today many teraflops of contributed processor power to a wide range of scientific and technical projects, and open source middleware enables hundreds of institutes or individual researchers to access large amounts of computing power otherwise unavailable to them.

BOINC: a system for public-resource computing and storage

  • D. Anderson
  • Computer Science
    Fifth IEEE/ACM International Workshop on Grid Computing
  • 2004
The goals of BOINC are described, the design issues that were confronted, and the solutions to these problems are described.

Celebrating Diversity in Volunteer Computing

Diversity in the context of World Community Grid and BOINC is discussed and the techniques used in the BOINC scheduler to efficiently match diverse jobs to diverse hosts are discussed.

High-performance task distribution for volunteer computing

Measurements of the CPU time and disk I/O used by a BOINC server are presented, and it is shown that a server consisting of a single inexpensive computer can distribute on the order of 8.8 million tasks per day.

Security Threats in Volunteer Computing Environments Using the Berkeley Open Infrastructure for Network Computing (BOINC)

The following paper presents a summary of the security threats identified in volunteer computing environments deploying the Berkeley Open Infrastructure for Network Computing (BOINC) and some solutions implementing Sanboxing Techniques on distributed computing environments.

Emulating Volunteer Computing Scheduling Policies

  • D. Anderson
  • Computer Science
    2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum
  • 2011
An emulation-based system that predicts the policies' behavior in specific scenarios is developed that has been useful in the design and evaluation of policies, in software development, and in the resolution of problems occurring in the field.

Pluggable scheduling on an open-source based volunteer computing infrastructure

An attempt to incorporate pluggable scheduling into an existing open-source volunteer computing system named BOINC is presented, as it managed to re-engineer BOINC to support different scheduling applications and interchange between them dynamically, with additional support for thermal-aware scheduling algorithms.

A world-wide databridge supported by a commercial cloud provider

This contribution investigates the provision of a globally distributed databridge implemented upon a commercial cloud provider to span the untrusted and trusted domains of volunteer computing and Grid computing respective.

Expanding the Reach of Grid Computing: Combining Globus- and BOINC-Based Systems

This work states that grid computing is a model of distributed computing that uses geographically and administratively disparate resources and that individual users can access computers and data transparently, without having to consider location, operating system, account administration, and other details.

BOINC-MR: MapReduce in a Volunteer Environment

Volunteer Computing (VC) harnesses computing resources from idle machines around the world to execute independent tasks, following a centralized master/worker model.
...