Subnetworks are expected to enhance wireless pervasiveness for critical applications such as wireless control of plants, however, they are interference-limited due to their extreme density. This paper proposes a goal-oriented joint power and multiple sub-bands allocation policy for interference coordination in 6G in-factory subnetworks. Current methods for interference coordination in subnetworks only focus on optimizing communication metrics, such as the block error rate, without considering the goal of the controlled plants. This oversight often leads to inefficient allocation of the limited radio resources. To address this, we devise a novel decentralized inter-subnetwork interference coordination policy optimized using a Bayesian framework to ensure the long-term stability of the subnetwork-controlled plants. Our results show that the proposed decentralized method can support more than twice the density of subnetwork-controlled plants compared to centralized schemes that aim to minimize the block error rate while reducing execution complexity significantly.

The paper examines a scenario wherein sensors are deployed within an Industrial Networked Control System, aiming to construct a digital twin (DT) model for a remotely operated Autonomous Guided Vehicle (AGV). The DT model, situated on a cloud platform, estimates and predicts the system’s state, subsequently formulating the optimal scheduling strategy for execution in the physical world. However, acquiring data crucial for efficient state estimation and control computation poses a significant challenge, primarily due to constraints such as limited network resources, partial observation, and the necessity to maintain a certain confidence level for DT estimation. We propose an algorithm based on Value of Information (VoI), seamlessly integrated with the Extended Kalman Filter to deliver a polynomial-time solution, selecting the most informative subset of sensing agents for data. Additionally, we put forth an alternative solution leveraging a Graph Neural Network to precisely ascertain the AGV’s position with a remarkable accuracy of up to 5 cm. Our experimental validation in an industrial robotic laboratory environment yields promising results, underscoring the potential of high-accuracy DT models in practice.

The setup considered in the paper consists of sensors in a Networked Control System that are used to build a digital twin (DT) model of the system dynamics. The focus is on control, scheduling, and resource allocation for sensory observation to ensure timely delivery to the DT model deployed in the cloud. Low latency and communication timeliness are instrumental in ensuring that the DT model can accurately estimate and predict system states. However, acquiring data for efficient state estimation and control computing poses a non-trivial problem given the limited network resources, partial state vector information, and measurement errors encountered at distributed sensors. We propose the REinforcement learning and Variational Extended Kalman filter with Robust Belief (REVERB), which leverages a reinforcement learning solution combined with a Value of Information-based algorithm for performing optimal control and selecting the most informative sensors to satisfy the prediction accuracy of DT. Numerical results demonstrate that the DT platform can offer satisfactory performance while reducing the communication overhead up to five times.

In this paper, we develop a novel power control solution for subnetworks-enabled distributed control systems in factory settings. We propose a channel-independent control-aware (CICA) policy based on the logistic model and learn the parameters using Bayesian optimization with a multi-objective tree-structured Parzen estimator. The objective is to minimize the control cost of the plants, measured as a finite horizon linear quadratic regulator cost. The proposed policy can be executed in a fully distributed manner and does not require cumbersome measurement of channel gain information, hence it is scalable for large-scale deployment of subnetworks for distributed control applications. With extensive numerical simulation and considering different densities of subnetworks, we show that the proposed method can achieve competitive stability performance and high availability for large-scale distributed control plants with limited radio resources.

In this paper, we elaborate on the frequency resource allocation problem of Wireless Networked Control Systems (WNCS). We consider a multi user wireless environment (e.g., factory) where the users are remote industrial Internet of Things (IIoT) devices competing for network resources and a centralized network base station needs to assign the resources to each device accordingly in order to keep the overall control system stability. We design a joint network and control scheduler solution, where we can estimate the degradation of the control system for a given network state and use this information to assign the frequency resource to each device. We show that the proposed solution outperforms traditional scheduling baselines, including genetic algorithms, assuming polynomial complexity in worst case scenario and generalizing for different control and network configurations.

Joint design of control and communication in Wireless Networked Control Systems (WNCS) is a promising approach for future wireless industrial applications. In this context, Age of Information (AoI) recently has been proposed as a metric that is more representative than communication latency in conduct of systems with a sense-compute-actuate cycle. Nevertheless, AoI is commonly defined for a single communication direction, Downlink or Uplink, which does not capture the closed-loop dynamics. In this paper, we extend the concept of AoI by defining a new metric, Age of Loop (AoL), relevant for closed-loop WNCS problems. The AoL is defined as the time elapsed since the piece of information causing the latest action or state (depending on the selected time origin) was generated. We use the proposed metric to learn the WNCS latency and freshness bounds, and apply such learning methodology to minimize the long-term WNCS cost with the least amount of bandwidth. We show that, using the AoL, we can learn the control system requirement and use this information to optimize network resources.

Real-time wireless networked control of an Autonomous Guided Vehicle (AGV) from an edge cloud controller is an attractive approach to reduce hardware costs of AGVs, e.g., for industrial applications. We specify a networked control protocol for AGV and investigate how system performance and stability are affected by the reliability of the wireless link with fading. Particularly, there is a trade-off between the AGV speed, the control stability, and the channel quality. Our model takes into account end-to-end latency, which includes control loops and communication. Considering the model complexity, we employ a Reinforcement Learning (RL) approach in order to find the optimal speed of AGV to complete a mission path in shortest time. The proposed solution achieves system stability at par with widely used baseline state-of-the-art controllers, while reducing the AGV mission time by more than 30%.