Quality of Service Provision in Fog Computing: Network-Aware Scheduling of Containers

Abstract

State-of-the-art scenarios, such as Internet of Things (IoT) and Smart Cities, have recently arisen. They involve the processing of huge data sets under strict time requirements, rendering the use of cloud resources unfeasible. For this reason, Fog computing has been proposed as a solution; however, there remains a need for intelligent allocation decisions, in order to make it a fully usable solution in such contexts. In this paper, a network-aware scheduling algorithm is presented, which aims to select the fog node most suitable for the execution of an application within a given deadline. This decision is made taking the status of the network into account. This scheduling algorithm was implemented as an extension to the Kubernetes default scheduler, and compared with existing proposals in the literature. The comparison shows that our proposal is the only one that can execute all the submitted jobs within their deadlines (i.e., no job is rejected or executed exceeding its deadline) with certain configurations in some of the scenarios tested, thus obtaining an optimal solution in such scenarios.

Mayfly Taylor Optimisation-Based Scheduling Algorithm with Deep Reinforcement Learning for Dynamic Scheduling in Fog-Cloud Computing

“…It uses a goal programming approach to select the best solution. Caminero et al [30] proposed a network-aware scheduling algorithm for the execution of the application in the selected fog node, which is suitable to be executed within a deadline.…”

Dynamic Scheduling of Contextually Categorised Internet of Things Services in Fog Computing Environment

“…Caminero et al present a similar approach in [8], where they propose a network-aware scheduling algorithm, which aims to select the fog node most suitable for the execution of an application within a given deadline. To implement network awareness, the authors utilized the iperf tool that calculates the network status.…”

“…As fog computing widens the processing plane to different execution environments, the challenge now is to detect the most appropriate place where a particular service component should be deployed to deliver the best quality of service. Across the scientific literature, different algorithms that tackle this problem can be found, and the majority of them utilize Kubernetes as the operational base of their approaches [8,9].…”

Modeling of a Generic Edge Computing Application Design

“…Fog deployments have been implemented in many fields where processing a vast amount of data with strict time constraints renders cloud computing unfit [65]. One scenario may be the analysis of physiological data from wearable devices (the concept of smart health), where such devices obtain relevant health-related data from a patient, and in turn, pass them on to fog servers to undertake the processing and respond within a restricted time interval, whilst having cloud servers for backup purposes [66].…”