Publications

Abstract : Cloud service provides everything as a service over the Internet or Intranet. Provisioning and allocation of virtual resource over the network requests based on used demand (pay-as-you-go). Big Data, which has large set of data that are so voluminous and complex that traditional method is not enough to process the data, Hadoop MapReduce framework is used to process the large set of data in a distributed manner. Efficient slave nodes selection is difficult to setup Hadoop cluster in cloud environment which led to more cost. We have proposed an algorithm called Particle Swarm Optimization(PSO) that determines the optimal number of nodes in the Hadoop cluster utilizes based on the data sets which provides efficient job execution on minimal set of DataNodes in cloud environment.