Resource Management in Fog/Edge Computing

Abstract

Contrary to using distant and centralized cloud data center resources, employing decentralized resources at the edge of a network for processing data closer to user devices, such as smartphones and tablets, is an upcoming computing paradigm, referred to as fog/edge computing. Fog/edge resources are typically resource-constrained, heterogeneous, and dynamic compared to the cloud, thereby making resource management an important challenge that needs to be addressed. This article reviews publications as early as 1991, with 85% of the publications between 2013-2018, to identify and classify the architectures, infrastructure, and underlying algorithms for managing resources in fog/edge computing.

What the Fog? Edge Computing Revisited: Promises, Applications and Future Challenges

“…Our taxonomy in Section II gives a broader overview without restricting the analysis to fog computing or edge computing alone. Hong and Varghese [21] have focused on resource management in edge and fog computing. Other surveys shed light on edge computing from the networking [22] or security [23]- [25] perspective.…”

“…Viitanen et al [162] have presented a rendering scheme for real-time VR gaming that saves energy and computational load on the end device. The rendered views are encoded as HEVC 21 frames and transmitted based on the user's field of vision. In [105], the authors have explored the scalability issue of massively multiplayer games and present a hybrid approach in which changes in the local view of a player are processed at the edge, while global game updates are performed in the cloud.…”

“…Content Delivery Networks (CDN) [165] distribute caches across data centers in different geographic regions to provide highly available and performant content retrieval for users. Ericsson forecasted back in 2013 that in 2019 50% of 21 High Efficiency Video Coding 22 Electroencephalography mobile traffic would be video traffic [166]. Today's content delivery networks hence, to a large extent, serve video traffic [167].…”

Computing in the Blink of an Eye: Current Possibilities for Edge Computing and Hardware-Agnostic Programming

“…In contrast, this paper presents the possibilities of very diverse embedded platforms, ranging from microcontrollers to GPUs, to provide broad guidelines for many different possible applications. The hardware heterogeneity is often subject of study [17], [18], but very few works have considered the use of hardware-agnostic languages [13], [19] that can lead to simple deployment on different platforms. An additional contribution of this work is to provide a quantifiable overview of the tradeoffs in performance that a general hardware-agnostic programming offers when compared to a tailored implementation, as for example, a detailed digital design in the case of FPGAs.…”

Resource Allocation for Edge Computing in IoT Networks via Reinforcement Learning

“…Compared with the cloud server, edge devices can support latency-critical services and a variety of IoT applications. The end devices are in general resource-constrained, for instance, the battery capacity and local CPU computation capacity are limited [3]. Offloading computation tasks to relatively resourcerich edge devices can meet the quality of service (QoS) requirements of applications as well as augment the capabilities of end devices for running resource-demanding applications [4].…”