DALBFog: Deadline-Aware and Load-Balanced Task Scheduling for the Internet of Things in Fog Computing

Abstract

The fog computing paradigm has evolved in the last few years to provide task-scheduling solutions for delay-sensitive Internet of Things (IoT) data. As the resources in fog computing are limited, the challenge is to utilize these computing resources in an efficient way while preserving the deadline requirements of delay-sensitive IoT applications. Various task-scheduling approaches have been introduced in the literature that deal with the various aspects of task scheduling in fog computing, like reducing response time, load imbalance, energy efficiency, minimizing execution time, etc. Considering the deadline requirements and efficient use of the limited resources, this work contributes a delay-aware and load-balanced scheduling mechanism for deadline-constrained IoT applications in fog computing. The proposed scheduling approach aims to schedule the user’s delay-sensitive IoT tasks in such a way that it minimizes the delay, maximizes the acceptance rate of the tasks, minimizes the load imbalance, and improves the utilization of the fog resources with a lower average response time (ART).