Energy Optimization-based Optimal Trade-off Scheme for Job Scheduling in Fog Computing

Fog computing is designed to expand the cloud-based storage, computing, and networking features that involve the concept of data processing on the end devices of the network and not in the cloud. In this article, an energy optimization based optimal tradeoff scheme for job scheduling in fog computing platforms using Artificial Bee Colony (ABC) as an optimization technique with Artificial Neural Network (ANN) is proposed. This research is designed to solve the challenges faced by researchers in the field of fog computing during job scheduling in terms of energy consumption, job completion time and successfully task allocation to a Virtual Machine (VM). The experimental results demonstrate that the proposed scheme using ABC with ANN achieved a far better result as compare to the other existing work based on the job completion time. Where we find out the task completion time is reduced by 40.67% as compare to the work with a Genetic Algorithm based model. Also, the successful task allocation and energy computing rate are improved by using the concept of ABC-ANN and other Qualities of Service (QoS) parameters are also contrasted in terms of task completion time and successfully task allocation.