Efficient Hybrid framework for parallel Resource and task scheduling in the Map reduce programming
S. Hemalatha, S. Valarmathi · 2016
The applications that are data intensive and large-scale is run by data centers based on Map Reduce implementation. Map Reduce runs on large clusters which needs vast amounts of energy which parallel increase cost of the data centers, Energy reduction has to be incorporated into the map reduce implementation to improve the efficiency of the data center. In order to achieve the good performance, model a framework based on Service Level Agreement (SLA) and its strategies. The parallel scheduler is modeled for resource and task using particle swarm optimization to manage the assignments of map and reduce task. The Resource management is carried to manage a resource slot, which reduces the consumption of energy when running the application achieves optimal schedules. Performance evaluation of the frameworks is compared with state of approaches, which concludes that the proposed framework outperforms in terms of efficiency and effectiveness.