Scalable and fault-tolerant algorithms for big data processing in distributed cloud architectures
Data Engineer Staff, Move Inc.
Research Article
World Journal of Advanced Research and Reviews, 2024, 24(03), 3329-3338
Article DOI: 10.30574/wjarr.2024.24.3.3664
Publication history:
Received on 22 October 2024; revised on 14 December 2024; accepted on 18 December 2024
Abstract:
The coming of enormous information has significantly changed the scene of information preparation, requiring headways in computational calculations to handle the scale and complexity of cutting edge datasets viably. This paper presents a comprehensive survey of cutting-edge calculations planned to optimize enormous information preparation in cloud computing situations. We look at state-of-the-art procedures in disseminated preparation systems, counting Hadoop MapReduce and Apache Start, and assess their viability in overseeing enormous information volumes. Moreover, we investigate imaginative information dividing procedures and optimization techniques that improve execution measurements such as versatility, throughput, and asset utilization.
Through thorough experimentation and investigation, we highlight the qualities and impediments of different calculations, advertising experiences into their down to earth applications and effect on real-world cloud situations. Our comes about uncovering critical progressions in handling proficiency, with outstanding changes in idleness lessening and asset administration. We moreover examine developing patterns and future inquire about bearings, emphasizing the requirement for versatile calculations that can powerfully optimize execution in assorted cloud scenarios.
The exponential development of information has required the improvement of productive calculations for handling huge datasets in cloud situations. This investigation presents novel calculations that altogether outflank existing strategies in terms of computational productivity, versatility, and asset utilization. By leveraging the conveyed nature of cloud foundations, our calculations empower quick examination of enormous datasets, opening profitable bits of knowledge that would otherwise be unattainable.
This idea gives a basic asset for analysts and specialists pointing to use progressed calculations for upgraded enormous information handling in cloud foundations. By joining hypothetical experiences with observational proof, we offer a nuanced viewpoint on optimizing cloud-based information frameworks, clearing the way for future advancements in this quickly advancing field.
Keywords:
Big Data; Cloud Computing; Distributed Algorithms; Scalable Data Processing; Data Partitioning; MapReduce; Hadoop; Spark; Elastic Computing; Data Sharding; Parallel Processing; Cluster Computing; High-Performance Computing (HPC); Resource Allocation; Load Balancing; Fault Tolerance; Data Storage Optimization; Cost-Efficient Cloud Solutions; Data Analytics in the Cloud; Stream Processing; Data Migration; Cloud-Based Machine Learning; Real-Time Processing; Task Scheduling; Energy-Efficient Algorithms
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0