Collaborative Task Execution In Volunteer Clouds (or how to choose a sub-reviewer)
1 like1,451 views
The document discusses collaborative task execution in volunteer clouds, highlighting various algorithms for task assignment and review processes among community members. It includes algorithms like random choice, greedy oracle, feedback-based probabilistic routing, and confidence-based pheromones for improving task distribution and review efficiency. Future research directions suggest examining the network structure's impact and exploring reputation-based strategies.
![References
Work-in-progress partially reported in:
“A Computational Field Framework for Collaborative Task
Execution in Volunteer Clouds”, Stefano Sebastio, Michele
Amoretti and Alberto Lluch-Lafuente, draft [PDF]
“Reputation-based Cooperation in the Clouds”, Alessandro
Celestini, Alberto Lluch Lafuente, Philip Mayer,
Stefano Sebastio, and Francesco Tiezzi, draft [PDF]
See also:
The science cloud platform. http://svn.pst.ifi.lmu.de/trac/scp/.
P. Mayer et al. The Autonomic Cloud: A Vision of Voluntary,
Peer-2-Peer Cloud Computing, 3rd Workshop on Challenges
for Achieving Self- Awareness in Autonomic Systems, 2013.](https://image.slidesharecdn.com/slides-cina-bologna2014-140220150032-phpapp02/85/Collaborative-Task-Execution-In-Volunteer-Clouds-or-how-to-choose-a-sub-reviewer-63-320.jpg)
Collaborative Task Execution In Volunteer Clouds (or how to choose a sub-reviewer)
- 1. Collaborative Task Execution In Volunteer Clouds -- Michele Amoretti, PARMA -- Alberto Lluch Lafuente, IMT -- Stefano Sebastio, IMT 2nd General Meeting, Bologna, 18-20 Feb 2014
- 2. Collaborative Task Execution in Volunteer Clouds -- Michele Amoreti, PARMA -- Alberto Lluch Lafuente, IMT -- Stefano Sebastio, IMT
- 3. Collaborative Task Execution in Volunteer Clouds -- Michele Amoreti, PARMA -- Alberto Lluch Lafuente, IMT -- Stefano Sebastio, IMT
- 4. c ho o s e ow to cho ose H ow to H Collaborativeewer Execution in ub-reviiewer s ub-rev Task a s a Volunteer Clouds -- Michele Amoreti, PARMA -- Alberto Lluch Lafuente, IMT -- Stefano Sebastio, IMT
- 6. Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2
- 7. Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 X X X X X X X X X
- 8. Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 X X X X X X X X X
- 9. Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 X X X X X X X X X
- 10. Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 X X X X X X X X X
- 11. Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 X X X X X X X X X
- 12. Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 X X X X X X X X X
- 15. SciFi Community
- 17. SciFi Community 1 Unstructured network 2 All members generate review tasks
- 18. SciFi Community 1 Unstructured network 2 All members generate review tasks 3 All members perform reviews
- 19. SciFi Community 1 Unstructured network 2 All members generate review tasks 3 All members perform reviews 4 Review requests may be forwarded
- 20. SciFi Community 1 Unstructured network 2 All members generate review tasks 3 All members perform reviews 4 Review requests may be forwarded 5 All members apply the same algorithm
- 21. SciFi Reviewers
- 22. SciFi Reviewers 1 No rescheduling, no priorities.
- 23. SciFi Reviewers 1 No rescheduling, no priorities. 2 Accept request iff CoS met.
- 24. SciFi Reviewers 1 No rescheduling, no priorities. 2 Accept request iff CoS met. 3 No delays.
- 25. SciFi Reviewers 1 No rescheduling, no priorities. 2 Accept request iff CoS met. 3 No delays. 4 Reply/Forward requests immediately.
- 26. SciFi Reviewers 1 No rescheduling, no priorities. 2 Accept request iff CoS met. 3 No delays. 4 Reply/Forward requests immediately. 5 Disclose confidence on research topics.
- 28. Algorithm 1: Random Each outgoing arc has the same probability of being chosen during request propagation.
- 29. Algorithm 1: Random Each outgoing arc has the same probability of being chosen during request propagation.
- 30. Algorithm 1: Random Each outgoing arc has the same probability of being chosen during request propagation.
- 33. The Greedy ORACLE The oracle provides the sub-reviewer who will finish earlier.
- 34. The Greedy ORACLE The oracle provides the sub-reviewer who will finish earlier.
- 35. The Greedy ORACLE The oracle provides the sub-reviewer who will finish earlier.
- 38. Probabilistic routing Arcs are labelled with rates to be used in probabilistic choices. 1 1+1 1 1 1 1
- 39. Feedback-based rates Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 1 1+1 1 1 1 1
- 40. Feedback-based rates Paper XXX Due dd/mm/yy CoS: * FM > 3 Can you review? * SE > 2 1 1+1 1 1 1 1
- 41. Feedback-based rates Paper XXX Due dd/mm/yy CoS: * FM > 3 Can you review? * SE > 2 NO 1 1+1 1 1 1 1
- 42. Feedback-based rates Paper XXX Due dd/mm/yy CoS: * FM > 3 Can you review? * SE > 2 NO 1 1+1 1 1 1 1-1
- 43. Feedback-based rates Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 1 Can you review? 1 1+1 1 1 1 1-1
- 44. Feedback-based rates Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 1 Can you review? Can you review? 1 1+1 1 1 1 1-1
- 45. Feedback-based rates Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 1 Can you review? YES Can you review? 1 1+1 1 1 1 1-1
- 46. Feedback-based rates Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 1 Can you review? YES Can you review? 1+1 1+1 1 1 1 1-1
- 50. Feedback-based pheromones Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 FM: 4 FM: 3 SE: 5 SE: 1 Arcs labeled with one rate for each research topic.
- 51. Feedback-based pheromones Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 FM: 4 FM: 3 SE: 5 SE: 1 FM: 3 SE: 1 Arcs labeled with one rate for each research topic.
- 52. Feedback-based pheromones Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 FM: 0 SE: 0 FM: 4 FM: 3 SE: 5 SE: 1 FM: 3 SE: 1 Arcs labeled with one rate for each research topic.
- 53. Feedback-based pheromones Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 FM: 0 SE: 0 FM: 4 SE: 5 FM: 4 FM: 3 SE: 5 SE: 1 FM: 3 SE: 1 Arcs labeled with one rate for each research topic.
- 54. Feedback-based pheromones Paper XXX Due dd/mm/yy CoS: * FM > 3 * SE > 2 FM: 0 SE: 0 FM: 4 SE: 5 FM: 4 SE: 5 FM: 4 FM: 3 SE: 5 SE: 1 FM: 3 SE: 1 Arcs labeled with one rate for each research topic.
- 59. What's next? 1 Study the impact of the structure of the overlay network
- 60. What's next? 1 Study the impact of the structure of the overlay network 2 Study reputation-based strategies
- 61. What's next? 1 Study the impact of the structure of the overlay network 2 Study reputation-based strategies 3 Application to routing of messages in predicate-based communication (cf. SCEL)
- 62. Questions?
- 63. References Work-in-progress partially reported in: “A Computational Field Framework for Collaborative Task Execution in Volunteer Clouds”, Stefano Sebastio, Michele Amoretti and Alberto Lluch-Lafuente, draft [PDF] “Reputation-based Cooperation in the Clouds”, Alessandro Celestini, Alberto Lluch Lafuente, Philip Mayer, Stefano Sebastio, and Francesco Tiezzi, draft [PDF] See also: The science cloud platform. http://svn.pst.ifi.lmu.de/trac/scp/. P. Mayer et al. The Autonomic Cloud: A Vision of Voluntary, Peer-2-Peer Cloud Computing, 3rd Workshop on Challenges for Achieving Self- Awareness in Autonomic Systems, 2013.