MapReduce: Big Data Maintained Algorithm

EasyChair Preprint no. 10818

Abstract

Big Data Maintained Algorithm is the practice of probing large amounts of data. The challenges include capturing, scrutiny, storage, searching, sharing, exposure, transferring and privacy violations. MapReduce is an uncomplicated, scalable and fault-tolerant data processing framework that enables us to process a substantial amount of data. MapReduce framework has generated a lot of concern in a wide range of areas. It currently is an elegant model for data severe applications due to the easy interface of programming, high scalability and fault tolerance capability. It leads to a new gesture of awareness to large-scale algorithms for data analysis. Algorithms cannot handle the enormous data well, for improving the time competence, for this MapReduce is best solution. So, this paper indicates the MapReduce applications in optimization algorithms and also provides a discussion of differences between its applications as well as some guidelines for future research. MapReduce is presently the most admired programming model for big data processing, and Hadoop is a well-known MapReduce accomplishment platform. To resolve these problems, in this paper, we propose MapReduce programming model for handing out huge datasets in distributed systems; it helps programmers to write programs that process big data. The goal of this paper is to examine MapReduce research trends, and current research efforts for enhancing MapReduce performance and capabilities. This Study accomplished that the research directions of MapReduce concerned with either enhancing MapReduce programming model or adopting MapReduce for deploying accessible algorithm to run with MapReduce programming model.

Keyphrases: Big Data, Combine and Partition, Mapper class, Reducer class and

@Booklet{EasyChair:10818,
  author = {Deepak Uprety and Dyuti Banarjee and Nitish Kumar and Abhimanyu Dhiman},
  title = {MapReduce: Big Data Maintained Algorithm},
  howpublished = {EasyChair Preprint no. 10818},

  year = {EasyChair, 2023}}