A Hybrid Workflow Offloading Scheme Based on the IIOT

With the rapid advancement of the new generation of the industrial revolution, the Industrial Internet of Things (IIOT) has placed higher demands on multidimensional indicators such as reliability, processing delay, energy consumption, and user experience in industrial applications. Mobile Edge Computing (MEC), as an important technology of IIOT, can satisfy the enormous resource demands of industrial mobile devices, including storage capacity, computing power, network bandwidth, and battery power. This can further provide corresponding solutions for the industrial Internet in terms of network performance, such as low latency, high reliability, and high security. Currently, there are many studies on independent task offloading in MEC. However, in the actual industrial Internet of Things scenarios, computing tasks typically consist of several interdependent subtasks. Therefore, we introduce hybrid workflows into the system model by considering the interdependence between computing tasks. The goal is to decrease the MEC system's computational time and resource consumption. This paper proposes an offloading method based on the Improved Bald Eagle Search Algorithm (IBES) to maximize system revenue. Simulation results show that compared with existing optimization algorithms, IBES can significantly reduce task completion time while consuming less energy. Therefore, it can significantly enhance user experience.