Enhanced load balance to predict fast data stream using E-tree MSI method on cloud

Abstract

Cloud computing implements virtualization processing of data service in the internet, where it delivers the conceptual, scalable platforms and applications as on data services. The important problem arises in Cloud infrastructure in storing a very large amount of data and processing on the computational load on the cloud. It is a big challenge to overcome computation complexity on cloud. An effectively predict the data streams process with load factors of ensemble model and data stream are implemented to overcome in cloud. Data stream processes on the cloud infrastructure runs with continuously varying load factors. In this work, we propose an architecture with a load balancing framework for cloud infrastructure by using the Ensemble Tree Metric Space Indexing (E-tree MSI) technique. We developed three techniques to construct our E-tree MSI technique: Fast Predictive Look-ahead Scheduling approach (FPLS) where the scheduling of Spatio-temporal data stream files takes place; Parallel Ensemble Tree Classification (PETC) which performs the process of classification operations on cloud data stream; and a Bilinear quadrilateral Mapping process which adds efficient implementation of cloud infrastructure. We have done an experimental evolution using CloudSim, from which it is achieved that the performance of load balancing factor is increased, the accuracy rate of classification is better and it reduced the execution time for mapping.