Video traffic over the Internet is increasing rapidly, reaching up to 82% of the total Internet traffic by 2022. This enormous growth of video traffic which also include immersive video content (augmented reality and virtual reality streaming) is challenging for the existing network architectures. Mobile edge computing (MEC) is arising as a promising solution to enhance the user experience. However, edge servers have usually limited computational capabilities and may not cope with unplanned sudden spikes in traffic from live streaming of large events or when a video goes viral, known as the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">thundering herd problem</i> . To improve the edge resource utilization, cooperation among edge servers has been proposed earlier. However, such cooperation is not useful in single-server scenario or when the neighboring servers are also fully utilized. Thus, in this article, we propose a novel D2D-MEC collaborative framework called as CODE (Computation Offloading in D2D-Edge) system in which an edge server offloads its computations to the distributed user devices (downlink). Two distinct schemes, i.e., maximal offloading with delay constraint (MOD) and minimum delay offloading (MDO) and a lightweight heuristic, are proposed to solve the computation offloading problem. Our simulation results report that the MOD scheme reduces the network delay up to 65%, whereas the MDO scheme reduces the edge computation load up to 83%.

Muhammad Asif Khan

Emna Baccour

Aiman Erbad

Ridha Hamila

Mounir Hamdi

IEEE Systems Journal

该出版物为面向应用的手稿提供了一个系统级的重点论坛，这些手稿解决了具有国家和全球意义的复杂系统和系统系统。它旨在鼓励和促进具有系统级和系统工程兴趣的 IEEE 学会之间的合作和互动，并吸引来自全球的非 IEEE 贡献者和读者。我们的 IEEE 系统委员会的工作是以新的方式解决现有 IEEE 或其他协会或全球组织的领域无法解决的问题。这些问题不适合传统的等级界限。例如，卡特里娜飓风、海啸或当前的火山爆发引发的灾难响应无法通过纯工程解决方案来解决。我们需要考虑改变和扩大范式以包括系统问题。

The IEEE Systems Journal is a publication that provides a system-level forum for applied manuscripts addressing complex systems and their interrelations of national and global significance. It aims to encourage and facilitate collaboration and interaction among IEEE societies with an interest in systems and systems engineering, while attracting contributors and readers from around the world who are not affiliated with IEEE. Our IEEE Systems Committee works to address problems in innovative ways that existing IEEE or other associations and global organizations cannot resolve. These issues often transcend traditional hierarchical boundaries. For instance, disaster responses to events like Hurricane Katrina, tsunamis, or current volcanic eruptions cannot be addressed solely through pure engineering solutions. We need to reconsider and expand our paradigms to include systemic issues.

IEEE Systems Journal 是一个专注于应用领域的期刊，提供了一个系统级的论坛，旨在解决具有国家和全球意义的复杂系统及其相互关系。该期刊鼓励和促进 IEEE 学会之间的合作与互动，同时吸引来自全球的非 IEEE 贡献者和读者。我们的 IEEE 系统委员会致力于以创新的方式解决传统 IEEE 或其他协会及全球组织无法应对的问题。这些问题往往超越了传统的等级界限。例如，卡特里娜飓风、海啸或当前火山爆发引发的灾难响应，不能仅依靠纯工程解决方案来处理。我们需要重新审视并扩展我们的范式，以全面考虑系统性问题。

CODE: Computation Offloading in D2D-Edge System for Video Streaming

A novel D2D-MEC collaborative framework in which an edge server offloads its computations to the distributed user devices (downlink) and two distinct schemes, i.e., maximal offloading with delay constraint (MOD) and minimum delay offloading (MDO) are proposed to solve the computation offloading problem.

Category	Quartile
计算机科学	3
计算机科学, 计算机信息系统	3
计算机科学, 工程电子与电气	3
计算机科学, 运筹学与管理科学	3
计算机科学, 电信学	3

CODE: Computation Offloading in D2D-Edge System for Video Streaming

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info