Epidemic Algorithms for Reliable Content-Based Publish-Subscribe: An Evaluation

Distributed content-based publish-subscribe middleware is emerging as a promising answer to the demands of modern distributed computing. Nevertheless, currently available systems usually do not provide reliability guarantees, which hampers their use in dynamic and unreliable scenarios, notably including mobile ones. In this paper, we evaluate the effectiveness of an approach based on epidemic algorithms. We proposed and thoroughly evaluated through simulation three algorithms in a challenging unreliable setting. The results show that our use of epidemic algorithms improves significantly event delivery, is scalable, and introduces only limited overhead.