Accessibility navigation

Symmetric Push-Sum Protocol for decentralised aggregation

Blasa, F., Cafiero, S., Fortino, G. and Di Fatta, G. (2011) Symmetric Push-Sum Protocol for decentralised aggregation. In: ThinkMind // AP2PS 2011, The Third International Conference on Advances in P2P Systems , November 20, 2011 to November 25, 2011 , Lisbon, Portugal, pp. 27-32.

Full text not archived in this repository.

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.


Gossip (or Epidemic) protocols have emerged as a communication and computation paradigm for large-scale networked systems. These protocols are based on randomised communication, which provides probabilistic guarantees on convergence speed and accuracy. They also provide robustness, scalability, computational and communication efficiency and high stability under disruption. This work presents a novel Gossip protocol named Symmetric Push-Sum Protocol for the computation of global aggregates (e.g., average) in decentralised and asynchronous systems. The proposed approach combines the simplicity of the push-based approach and the efficiency of the push-pull schemes. The push-pull schemes cannot be directly employed in asynchronous systems as they require synchronous paired communication operations to guarantee their accuracy. Although push schemes guarantee accuracy even with asynchronous communication, they suffer from a slower and unstable convergence. Symmetric Push- Sum Protocol does not require synchronous communication and achieves a convergence speed similar to the push-pull schemes, while keeping the accuracy stability of the push scheme. In the experimental analysis, we focus on computing the global average as an important class of node aggregation problems. The results have confirmed that the proposed method inherits the advantages of both other schemes and outperforms well-known state of the art protocols for decentralized Gossip-based aggregation.

Item Type:Conference or Workshop Item (Paper)
Divisions:Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
ID Code:27055
Uncontrolled Keywords:peer-to-peer computing; distributed aggregation algorithms; gossip protocols; extreme scale computing
Additional Information:ISBN: 9781612081731
Publisher Statement:

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation