Gossip-based asynchronous and robust aggregation protocol &amp;#x2014; A pessimistic approach

Internet and Distributed Computing Systems

2018

In large-scale distributed systems data aggregation is a fundamental task that provides a global synopsis over a distributed set of data values. Epidemic protocols are based on a randomised communication paradigm inspired by biological systems and have been proposed to provide decentralised, scalable and fault-tolerant solutions to the data aggregation problem. However, in epidemic aggregation, nodes failure and churn have a detrimental effect on the accuracy of the local estimates of the global aggregation target. In this paper, a novel approach, the Robust Epidemic Aggregation Protocol (REAP), is proposed to provide robustness in the presence of churn by detecting three distinct phases in the aggregation process. An analysis of the impact of each phase over the estimation accuracy is provided. In particular, a novel mechanism is introduced to improve the phase that is most critical for the protocol accuracy. REAP is validated by means of simulations and is shown to achieve convergence with a good level of accuracy for a reasonable range of node churn rates.

Section: Related Workmentioning

confidence: 99%

Robust Epidemic Aggregation Under Churn

Ayiad

Internet and Distributed Computing Systems

2018

“…Each node starts the randomised communication at the beginning of each cycle. Cycles are time intervals of fixed length and the length is equivalent to the average Round-Trip-Time (RTT ) of the Internet [23,24]. The start of the first cycle at each node is uniformly distributed within a bound offset T start equivalent to maximum drifts among internal clocks in network nodes.…”

Section: Distributed System Modelmentioning

confidence: 99%

Agreement in Epidemic Data Aggregation

Ayiad

2017 IEEE 23rd International Conference on Parallel and Distributed Systems (ICPADS)

2017

Computing and spreading global information in large-scale distributed systems pose significant challenges when scalability, parallelism, resilience and consistency are demanded. Epidemic protocols are a robust and scalable computing and communication paradigm that can be effectively used for information dissemination and data aggregation in a fully decentralised context where each network node requires the local computation of a global synopsis function. Theoretical analysis of epidemic protocols for synchronous and static network models provide guarantees on the convergence to a global target and on the consistency among the network nodes. However, practical applications in real-world networks may require the explicit detection of both local convergence and global agreement (consensus). This work introduces the Epidemic Consensus Protocol (ECP) for the determination of consensus on the convergence of a decentralised data aggregation task. ECP adopts a heuristic method to locally detect convergence of the aggregation task and stochastic phase transitions to detect global agreement and reach consensus. The performance of ECP has been investigated by means of simulations and compared to a tree-based Three-Phase Commit protocol (3PC). Although, as expected, ECP exhibits total communication costs greater than the optimal tree-based protocol, it is shown to have better performance and scalability properties; ECP can achieve faster convergence to consensus for large system sizes and inherits the intrinsic decentralisation, fault-tolerance and robustness properties of epidemic protocols.

“…Apparently, in order to guarantee the mass conservation invariant, the only requirement would be that the two messages (push and pull) are both successfully received within the current Gossip cycle. However, in [26,27] it has been pointed out that this is not the case. In order to conserve the global mass and to guarantee a convergence to the true aggregate value, the two messages used to exchange the local values must be sent and received in an atomic communication operation.…”

Section: Push-pull Gossip Protocolmentioning

confidence: 99%

“…In order to conserve the global mass and to guarantee a convergence to the true aggregate value, the two messages used to exchange the local values must be sent and received in an atomic communication operation. This requirement imposes additional complexity in practical implementations and introduces dependability issues [26,27] in real asynchronous environments.…”

Section: Push-pull Gossip Protocolmentioning

confidence: 99%

Fault tolerant decentralised -Means clustering for asynchronous large-scale networks

Journal of Parallel and Distributed Computing

Blasa

Cafiero

et al. 2013

The K-Means algorithm for cluster analysis is one of the most influential and popular data mining methods. Its straightforward parallel formulation is well suited for distributed memory systems with reliable interconnection networks, such as massively parallel processors and clusters of workstations. However, in large-scale geographically distributed systems the straightforward parallel algorithm can be rendered useless by a single communication failure or high latency in communication paths. The lack of scalable and fault tolerant global communication and synchronisation methods in large-scale systems has hindered the adoption of the K-Means algorithm for applications in large networked systems such as wireless sensor networks, peer-to-peer systems and mobile ad hoc networks. This work proposes a fully distributed K-Means algorithm (Epidemic K-Means) which does not require global communication and is intrinsically fault tolerant. The proposed distributed K-Means algorithm provides a clustering solution which can approximate the solution of an ideal centralised algorithm over the aggregated data as closely as desired. A comparative performance analysis is carried out against the state of the art sampling methods and shows that the proposed method overcomes the limitations of the sampling-based approaches for skewed clusters distributions. The experimental analysis confirms that the proposed algorithm is very accurate and fault tolerant under unreliable network conditions (message loss and node failures) and is suitable for asynchronous networks of very large and extreme scale.