ODTRA-Based Task Offload Optimization for Industrial Internet of Things: Improving Efficiency and Performance With Digital Twins and Metaheuristic Optimization

Abstract

The Industrial Internet of Things (IIoT) is the recent innovation that had revolutionized the industries by enabling interconnected devices and systems to exchange intelligent data. However, implementing and operating such IIoT systems have various challenges. This article addresses those challenges pertained to task offloading in IIoT in which the resource-intensive tasks are transmitted and executed on remote cloud servers. To optimize the task offloading decisions this work propose the integration of Digital Twins, which are the computer-generated replicas of physical objects. By using the functionalities of Digital Twins along with real-time monitoring, and metaheuristic optimization algorithms this work presents a task offloading model for IIoT. Through this combined framework, the proposed model attempts to minimize the task execution time by considering the server capacity, bandwidth constraints, and device power consumption. The proposed Offloading with Digital Twins and Raindrop Algorithm (ODTRA) algorithm that is based on the water cycle metaphor and the Probabilistic Recursive Local (PRL) search algorithm had efficiently optimizes offloading performance which was proven through different experiment simulation and analysis.

Keywords

• IIoT
• digital twins
• task offloading
• metaheuristic optimization
• water cycle metaphor
• decision-making system