Suppr超能文献

通过协作式移动、区域和云计算进行社会大数据管理。

Social big data management through collaborative mobile, regional, and cloud computing.

作者信息

Badshah Afzal, Banjar Ameen, Habibullah Safa, Alharbi Abdullah, Alosaimi Wael, Daud Ali

机构信息

Department of Software Engineering, University of Sargodha, Sargodha, Punjab, Pakistan.

Department of Information Systems and Technology, College of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi Arabia.

出版信息

PeerJ Comput Sci. 2025 Mar 31;11:e2689. doi: 10.7717/peerj-cs.2689. eCollection 2025.

Abstract

The crowd of smart devices surrounds us all the time. These devices popularize social media platforms (SMP), connecting billions of users. The enhanced functionalities of smart devices generate big data that overutilizes the mainstream network, degrading performance and increasing the overall cost, compromising time-sensitive services. Research indicates that about 75% of connections come from local areas, and their workload does not need to be migrated to remote servers in real-time. Collaboration among mobile edge computing (MEC), regional computing (RC), and cloud computing (CC) can effectively fill these gaps. Therefore, we propose a collaborative structure of mobile, regional, and cloud computing to address the issues arising from social big data (SBD). In this model, it may be easily accessed from the nearest device or server rather than downloading a file from the cloud server. Furthermore, instead of transferring each file to the cloud servers during peak hours, they are initially stored on a regional level and subsequently uploaded to the cloud servers during off-peak hours. The outcomes affirm that this approach significantly reduces the impact of substantial SBD on the performance of mainstream and social network platforms, specifically in terms of delay, response time, and cost.

摘要

智能设备群体始终围绕着我们。这些设备使社交媒体平台(SMP)得以普及,连接了数十亿用户。智能设备增强的功能产生了大量数据,这些数据过度占用主流网络,导致性能下降和总成本增加,危及对时间敏感的服务。研究表明,约75%的连接来自本地,其工作负载无需实时迁移到远程服务器。移动边缘计算(MEC)、区域计算(RC)和云计算(CC)之间的协作可以有效填补这些空白。因此,我们提出一种移动、区域和云计算的协作架构,以解决社会大数据(SBD)引发的问题。在该模型中,文件可能更容易从最近的设备或服务器获取,而不是从云服务器下载。此外,在高峰时段,文件不是逐个传输到云服务器,而是先存储在区域级别,随后在非高峰时段上传到云服务器。结果证实,这种方法显著降低了大量社会大数据对主流和社交网络平台性能的影响,特别是在延迟、响应时间和成本方面。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e26d/12190470/7e947c215ef8/peerj-cs-11-2689-g001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验