FCSTD: Fog-Cloud Smart Task Distribution by Exploiting the Artificial Neural Networks

Abstract

In order to reduce the response time and the Internet bandwidth utilization in combined Fog-Cloud scenarios, we propose Fog-Cloud Smart Task Distribution (FCSTD) method, which intelligently distributes the tasks between the fog and cloud servers with regard to the application requirements. This approach uses Artificial Neural Networks for predicting the response time and the size of the results and then distributes the tasks by considering the predicted amounts. To investigate the performance of FCSTD, we applied it to a real-world case study (which is a delay-sensitive online healthcare application that monitors the health status of people) and analyzed its performance for the distribution of different types of tasks. The achieved results show that FCSTD provides better performance for reducing the Internet bandwidth utilization and response time in comparison to the other proposed methods in the literature.