Dynamic task scheduling for fog nodes based on deadline constraints and task frequency for smart factories

Abstract

With the integration of Internet in industrial production and in manufacturing, the concept of Industrial Internet of things (IIoT) has become one of the most innovative tools for factories. Since factories generate a huge amount of data and requests that need to be treated quickly, fog computing, as a decentralized computing structure is a powerful complement to the cloud to handle this data because it has an important potential to improve factory production significantly. Fog computing handles the incoming tasks by applying a task scheduling policy in order to achieve a better performance of the factory. In this work, we propose a real time dynamic task scheduler which considers deadline and frequency constraints as an emergency degree, at the fog level, in order to process the incoming tasks correctly. Our approach considers a fog network based on auctions in which tasks rejected by a fog can be accepted at another fog. In terms of the number of rejected tasks, extensive simulations have shown good performance of the proposed task scheduler compared to similar works.