Live Data Migration Strategy with Stream Processing Framework

Live data migration in the cloud is responsible to migrate blocks of data of emigration node to severalimmigration node. However, live data migration strategy is a NP-hard problem like task scheduling. Recently,in-stream processing is the immediate need in many practical applications. Therefore, we explore a real-time livedata migration strategy with stream processing framework in this paper. First, the migration cost and balancemodel is introduced as the metrics to evaluate data migration strategy. Subsequently, a live data migration strategywith particle swarm optimization is proposed. Afterwards, we implement this method using stream processingframework. The experimental results show the best performance of our method in all