Controller-Aware Dynamic Network Management for Industry 4.0

In this paper, we consider a cyber-physical manufacturing system (CPMS) scenario containing physical components (robots, sensors, and actuators), operating in a digitally connected, constrained environment to perform industrial tasks. The CPMS has a centralized control plane with digital twins (DTs) of the physical resources, computational resources, and a network manager that allocates network resources. Existing approaches for the allocation of network resources are typically fixed with respect to controller-dependent run-time specifications, which may impact the performance of physical processes. We propose a dynamic network management framework, where the network resource allocation schemes are controller-aware. The information about the controllers of the physical resources is implemented at the DT level, and metrics, such as regret bounds, take the process performance measures into account. The proposed network management schemes optimize physical system performance by balancing the shared resources between the physical assets on the plant floor, and by considering their control requirements, providing a new perspective for dynamic resource allocation. A simulation study is provided to illustrate the performance of the proposed network management approaches and compare their resource allocation performance efficiencies.

I. Introduction

Industrial Cyber-Physical Systems (ICPS) generally involve a layer of coupled mechanical/physical components, and a cyber layer that supports the interactions and data exchange between the components of the physical layer and additionally with the monitoring, remote supervision, and maintenance units [1]. Modern applications of ICPS require sensitive control functionalities across the physical layer, and a reliable and agile cyber layer enabling sustainable and coordinated interactions [2], [3]. Traditionally, the development of ICPS mainly coincided with the development of control architectures, e.g., the progress in deploying distributed control systems for process industries, or advancements in programmable logic controllers (PLC) for discrete manufacturing, while the communication was merely in the form of exchanging predetermined control and actuation command signals via locally installed networks infrastructure mainly for wired channels [4]. Rapid advances in communication technology and the need for higher levels of automation for efficient production led to a huge revolution in industrial manufacturing where devices, machines, and industrial components became interconnected (networked) with the support of a communication and computation network. Efficient resource allocation has been a challenging problem generally in networked control systems [5], [6], and specifically in interconnected industries [7] where quality-of-production is coupled with the quality-of-service.