An Optimized IWOA and MECC based MapReduce Framework for Big data

Main Article Content

Mr. Vishal Kumar, Prof. Kamaljit Singh Saini

Abstract

New participants in the cloud ecosystem are large MapReduce clusters, often managing petabytes of unstructured and semi-structured data. Increasing the use of these MapReduce clusters is a big problem. This work considers a subset of production workloads that consist of independent MapReduce jobs. The order in which these activities are executed has a considerable impact on overall processing time and cluster resource use, according to our findings. Our goal is to automate the creation of  work plans that reduce the  time it takes to complete a series of MapReduce processes (span creation).This work present Balanced Pools, a novel abstraction framework and algorithm for building an optimum task schedule based on the performance features of MapReduce processes in a given workload. Simulations of a realistic workload show that simply processing the jobs in the appropriate order can enhance make span by 15% to 38%. The data supplied to the cloud is the responsibility of the Cloud Services Provider (CSP). The main disincentive to using cloud services is the risk of strangers seeing stored data and using sensitive raw data. As a result, Data Security (DS) and privacy are the primary concerns that obstruct the adoption of the CC. There are numerous strategies for ensuring data secrecy, but none of them totally protect the data. To overcome these shortcomings, this paper provides a Modified Elliptic Curve Cryptography (MECC) technique to protect your data from hostile attacks

Article Details

Section
Articles