A Novel Deep Learning Mechanism for Workload Balancing in Fog Computing

Authors:

Abstract
In addition to cloud computing, fog computing has recently been developed in order to provide services as a modern distributed paradigm. Using the fog network, storage and computation can be extended to the edge of the system, which besides providing local awareness and support for mobility, can resolve the problem of delay-sensitive applications’ service calculation. Fog networks must maintain a proper load balance in order to avoid the problem with certain fog nodes which are under-loaded or overloaded. As a result of load balancing, Quality of Service (QoS) characteristics such as consumption of resources and bandwidth can be improved. This paper investigates a working charge distribution list in an IoT–fog–cloud collaboration system to reduce job latency and meet the QoS requirements of as many late sensitive IoT applications as possible. Besides, the problem of allocating workloads in such an IoT-based cooperation scheme is first considered, which suggests optimum workload allotment between nearby fog nodes and the cloud in order to reduce work provision delays. The stability is then examined using Lyapunov's drift and penalty theory, which analyzes the steadiness of IoT-fog-cloud queue scheme.

This publication has 15 references indexed in Scilit: