Deep Learning for Service Function Chain Provisioning in Fog Computing

Abstract

Cloud and fog computing along with network function virtualization technology have significantly shifted the development of network architectures. They yield in reduced capital and operating expenditures, while achieving network flexibility and scalability to accommodate the massive growth in data traffic volumes from user terminals requesting various services and applications. Now cloud solutions here offer abundant computing and storage resources, at the detriment of high end-to-end delays, hence limiting quality of service for delay-sensitive applications. Meanwhile, fog solutions offer reduced delays, at the detriment of limited resources. Existing efforts focus on merging the two solutions and propose multi-tier hybrid fog-cloud architectures to leverage their both saliencies. However, these approaches can be inefficient when the applications are delay-sensitive and require high resources. Hence this work proposes a novel standalone heterogeneous fog architecture that is composed of high-capacity and low-capacity fog nodes, both located at the terminals proximity. Thereby, realizing a substrate network that offers reduced delays and high resources, without the need to relay to the cloud nodes. Moreover, the work here leverages and deploys a deep learning network to propose a service function chain provisioning scheme implemented on this architecture. The scheme predicts the popular network functions, and maps them on the high-capacity nodes, whereas it predicts the unpopular network functions and maps them on the low-capacity nodes. The goal is to predict the next incoming function and prefetch it on the node. Hence, when a future request demands the same function, it can be cached directly from the node, at reduced resources consumption, processing times, cost, and energy consumption. Also, this yields in higher number of satisfied requests and increased capacity. The deep learning network yields reduced loss model and high success rates.

A Comprehensive Study of Caching Effects on Fog Computing Performance

“…After that, there's paper. In research [24], the authors proposed an everyday utility for a fog computing situation. An optimal caching resource allocation technique integrating global and local decision-making is used.…”

“…Retaining a lower ECHR and allocating more traffic to the cloud is superior. N.JASIM et al [24] This research provides a freestanding heterogeneous fog architecture comprised of high-capacity and low-capacity fog nodes near the terminal. As a result, without having to relay to cloud nodes, a substrate network with low latency and enormous resources can be established.…”

“…The Internet of Things (IoT) is a system in which we are surrounded by billions of intelligent objects that affect numerous aspects of our lives [23]. Using the fog computing paradigm, data processing for a resource-hungry mobile application can be transferred from resourceconstrained terminal devices to a powerful mobile cloud-assisted platform [24,25].…”

“…The challenges stem primarily from the need to re-design the south-bound, north-bound, and east-westbound APIs to include fog computing primitives [64]. The design goals for latency and efficiency may not be met with an essential integration [24,64].  Security and Privacy: At every level of the fog computing platform design, security and privacy should be considered [65].…”

A Comprehensive Survey on Auction Mechanism Design for Cloud/Edge Resource Management and Pricing

“…The concept of Fog Computing has been proposed by Cisco, which is a generalized form of MEC enabling computation at the edge of the network through billions of smart connected devices [55], [57], [58]. Further, Fog Computing has also been identified as a suitable platform for network function virtualization (VNF) for delay-sensitive applications [59]- [61]. Finally the concept of Cloudlets has been introduced by Satyanarayanan et al [62] which aim at providing computing resources available within the local network.…”