Use of regional computing to minimize the social big data effects. (September 2022)

• Record Type: Journal Article
• Authors: Badshah, Afzal; Iwendi, Celestine; Jalal, Ateeqa; Hasan, Syed Shabih Ul; Said, Ghawar; Band, Shahab S.; Chang, Arthur
• Is Part Of: Computers & industrial engineering. Volume 171(2022)
• Publication Date: 2022-09
• Subjects: Edge computing -- Social media -- Cloud computing -- Smart cities -- Performance -- Cost; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2022.108433
• Languages: English
• ISSNs: 0360-8352

Abstract

Abstract: Smart devices are commonly used these days, especially in smart cities, resulting in massive social media engagement and heavy workload generation. Statistics show that over 4.41 billion people will subscribe to social media by 2025, which covers the majority of the world's population. Its versatility and enriched features allow users to upload and download large data (e.g, High Definition (HD)) videos and HD live streaming). This heavy workload overburdens the mainstream network and social media cloud, increasing the delay and costs for instant communications. To cope with the aforementioned challenges, this paper aims to minimize the social big data effects on the mainstream network and the social media cloud servers. In connection with these objectives, a survey result shows that 75% of social connections originate from the local region, and their data has no need for instant migration to the remote cloud servers. We extended the Edge/Fog computing concept to create Regional Computing (RC) for Social Media Platforms (SMP). These servers are created at the regional level. Initially, the data is stored and processed at regional computing servers and later on, in off-peak hours, migrated to the cloud servers. The initial result shows that the regional computing servers filter the content regionally and minimize the burden on the mainstream network. It also reduces the cloud server's workload, resulting in minimal delays and costs. Highlights: Minimizing the social big data effects on the mainstream networks. Regional computing servers to keep the regional data at regional servers. Increasing the performance of social media platforms by using the regional servers.