Browsing by Author "Chao, Chen"

In recent years, content-based Publish/Subscribe (pub/sub) has become a popular paradigm to decouple content producers and consumers for Internet-scale content services. Many real applications show that the content workloads frequently follow very skewed distribution, and incur unbalanced workloads. To balance the workloads, the current content-based Publish/Subscribe systems normally adopt a migration scheme (Mis) to move (a subset of) subscription filters from overloaded brokers to underloaded brokers. In this way, the publications that successfully match the moved filters are then o oaded, leading to balanced workloads. Unfortunately, the Mis scheme cannot reduce the overall matching workloads. In the worse case, suppose that all brokers su er from heavy workloads. Mis cannot find available brokers to o oad the heavy workloads of those overloaded brokers, and fail to balance the workloads of the overloaded brokers. To overcome the issue, we develop a set of novel load balancing algorithms, namely a similarity-based replication scheme (Sir). The novelty of Sir is that it not only balances the workloads of brokers but also reduces the overall workloads. Based on both simulation and emulation results, the extensive experiments verify that Sir can achieve much better performance than Mis, in terms of 43.10% higher entropy value (i.e., more balanced workloads) and 46.39% lower workloads.