Cross-Layer Optimization for Industrial Internet of Things in Real Scene Digital Twins

The development of the Industrial Internet of Things (IIoT) and digital twins (DTs) technology brings new opportunities and challenges to all walks of life. The work aims to study the cross-layer optimization of DTs in IIoT. The specific application scenarios of hazardous gas leakage boundary tracking in the industry is explored. The work proposes an industrial hazardous gas tracking algorithm based on a parallel optimization framework, establishes a three-layer network of distributed edge computing based on IIoT, and develops a two-stage industrial hazardous gas tracking algorithm based on a state transition model. The performance of different algorithms is analyzed. The results indicate that the tracking state transition and target wake-up module can effectively track the gas boundary and reduce the network energy consumption. The task success rate of the parallel optimization algorithm exceeds 0.9 in 5 s. When the number of network nodes in the state transition algorithm is N = 600, the energy consumption is only 2.11 J. The minimum tracking error is 0.31, which is at least 1.33 lower than that of the exact conditional tracking algorithm. Therefore, the three-layer network edge computing architecture proposed here has an excellent performance in industrial gas diffusion boundary tracking.

I. Introduction

Internet of Things (IoT) is changing the way people interact with things around them. The emergence of low-cost microsensors and high-bandwidth wireless networks in the Industrial IoT (IIoT) means that even the smallest devices can be connected as long as there is a certain level of digital intelligence [1]. Shen et al. [2] reported that virtual reality had become a feasible alternative to traditional learning methods in various knowledge fields. Besides, there were usually some toxic gases harmful to the human body used as production raw materials in the manufacturing environment of an intelligent factory, which could pose a significant threat to the life safety of front-line workers if they were not correctly stored and leaked [3]. It is necessary to predict and locate the gas diffusion boundary and evacuate the staff in time. Edge computing can significantly improve the Quality of Service (QoS) of IIoT [4]. The term edge has taken on a new definition in the world of the IoT, referring to somewhere near the device end. Therefore, according to the literal definition, edge computing is the computing generated near the device end. Edge computing solves significant problems, including high latency, network instability, and low bandwidth in traditional cloud computing or central computing mode.