Large models, renowned for superior performance, outperform smaller ones even without billion-parameter scales. While mobile network servers have ample computational resources to support larger models than client devices, privacy constraints prevent clients from directly sharing their raw data. Federated Learning (FL) enables decentralized clients to collaboratively train a shared model by exchanging model parameters instead of transmitting raw data. Yet, it requires a uniform model architecture and multiple communication rounds, which neglect resource heterogeneity, impose heavy computational demands on clients, and increase communication overhead. To address these challenges, we propose FedOL, to construct a larger and more comprehensive server model in one-shot settings (i.e., in a single communication round). Instead of model parameter sharing, FedOL employs knowledge distillation, where clients only exchange model prediction outputs on an unlabeled public dataset. This reduces communication overhead by transmitting compact predictions instead of full model weights and enables model customization by allowing heterogeneous model architectures. A key challenge in this setting is that client predictions may be biased due to skewed local data distributions, and the lack of ground-truth labels in the public dataset further complicates reliable learning. To mitigate these issues, FedOL introduces a specialized objective function that iteratively refines pseudo-labels and the server model, improving learning reliability. To complement this, FedOL incorporates a tailored pseudo-label generation and knowledge distillation strategy that effectively integrates diverse knowledge. Simulation results show that FedOL significantly outperforms existing baselines, offering a cost-effective solution for mobile networks where clients possess valuable private data but limited computational resources.

The Age of Information (AoI) has emerged as a critical metric for quantifying information freshness; however, its interplay with channel estimation in partially observable wireless systems remains underexplored. This work considers a transmitter-receiver pair communicating over an unreliable channel with time-varying reliability levels. The transmitter observes the instantaneous link reliability through a channel state information acquisition procedure, during which the data transmission is interrupted. This leads to a fundamental trade-off between utilizing limited network resources for either data transmission or channel state information acquisition to combat the channel aging effect. Assuming the wireless channel is modeled as a finite-state Markovian channel, we formulate an optimization problem as a partially observable Markov decision process (POMDP), obtain the optimal policy through the relative value iteration algorithm, and demonstrate the efficiency of our solution through simulations. To the best of our knowledge, this is the first work to aim for an optimal scheduling policy for data transmissions while considering the effect of channel state information aging.

Achieving flexible and efficient wireless resource sharing across diverse applications and services is among the key goals of the sixth-generation of mobile systems (6G). This work investigates the performance of a real-time system coexisting with a broadband service in a frame-based wireless channel. Specifically, we consider a remote tracking device that monitors an information source and transmits updates to a base station (BS) for real-time source reconstruction, and potential remote actuation. We revise the common idealized assumptions in real-time remote tracking studies, such as instantaneous feedback and pervasive wireless resources, as they do not hold in practical scenarios. We consider a monitoring device and a broadband user communicating with the BS via a grant-free access mechanism over wireless resources defined for either orthogonal or non-orthogonal access, with feedback scheduled at the end of each frame. We analyze system performance using goal-oriented performance metrics for real-time remote reconstruction, alongside throughput and energy efficiency for the broadband user. Our results show that the ‘Idealistic’ model considered in conventional studies achieves better performance but incurs disproportionately high overhead compared to the Frame-Based model. Moreover, within the Frame-Based model, orthogonal resource sharing is preferable for maximizing broadband throughput, while non-orthogonal sharing significantly improves energy efficiency.

Control over networks is envisioned to be one of the driving applications of future mobile networks. Networked control systems contain sensors and controllers exchanging time-sensitive information to fulfill a particular control goal. In this work, we consider$N$heterogeneous feedback control loops closed over a wireless star network. A centralized scheduler located at the central node, i.e., base station (BS), determines the transmission schedule of sensor-to-BS and BS-to-controller communication links. We assume that each link can accommodate a single transmission at a time and is prone to data losses with time-varying probability. Moreover, each controller estimates the system state remotely based on available information. In such a setting, we formulate an optimization problem to minimize the network-induced estimation error at the controller. In particular, we determine the optimal transmission schedule on each link that leads to the minimum normalized mean squared error (nMSE) in a given finite horizon (FH). We compare the performance of our proposed FH scheduler to various schedulers from the existing literature. Our simulation results show that by solving the finite horizon problem optimally, we are able to reduce the nMSE by$10\%$when compared to the best performing scheduling policy among the selected policies from the state-of-the-art. Moreover, the linear-quadratic Gaussian (LQG) cost is reduced by more than$13\%$indicating a control performance improvement in the network.

Networked control systems (NCSs) are an example of task-oriented communication systems, where the purpose of communication is real-time control of processes over a network. In the context of NCSs, with the processes sending their state measurements to the remote controllers, the deterioration of control performance due to the network congestion can be partly mitigated by shaping the traffic injected into the network at the transport layer (TL). In this work, we conduct an extensive performance evaluation of selected TL protocols and show that existing approaches from communication and control theories fail to deliver sufficient control performance in realistic network scenarios. Moreover, we propose a new semantic-aware TL policy, which uses the process state information to filter the most relevant updates and the network state information to prevent delays due to network congestion. The proposed mechanism is shown to outperform all the considered TL protocols with respect to control performance.

Goal-oriented communication is a promising approach to tailor the network resource management algorithms to the needs of particular applications, thus enhancing the efficiency of resource utilization and boosting the application performance. In the context of distributed cyber-physical systems and networked control systems, the design of a control-aware transport layer (TL) represents a realistic approach for goaloriented communications since it can be integrated into generic control setups without making assumptions on particular hardware or network technologies and deliver enhanced end-to-end performance. This demo showcases the application performance of different TL schemes used for communication between the sensors and the controllers monitoring and actuating inverted pendulums, i.e., multi-dimensional plants. The nodes of the control loops are realized with Zolertia Re-Mote devices, and multiple control loops communicate over the shared wireless network using IEEE 802.15.4 standard. We use the demonstration testbed to compare the performance of conventional, state-of-the-art, and novel goal-oriented TL schemes by observing the emulated dynamics of inverted pendulums.

In Wireless Networked Control Systems (WNCSs), the feedback control loops are closed over a wireless communication network. The proliferation of WNCSs requires efficient network resource management mechanisms since the control performance is significantly affected by the impairments caused by network limitations. In conventional communication networks, the amount of transmitted data is one of the key performance indicators. In contrast, in WNCSs, the efficiency of the network is measured by its ability to facilitate control applications, and the data transmission rate should be limited to avoid network congestion. In this work, we consider an experimental setup where multiple control loops share a wireless communication network. Our testbed comprises up to five control loops that include Zolertia Re-Mote devices implementing IEEE 802.15.4 standard. We propose a novel relevance- and network-aware transport layer (TL) scheme for WNCSs. The proposed scheme admits the most important measurements for the control process into the network while considering current network conditions. Moreover, we propose a mechanism for the scheme parameters adaptation in dynamic scenarios with unknown network statistics. Unlike the conventional TL mechanisms failing to provide adequate control performance due to either congestion in the network or inefficient utilization of available resources, our method prevents network congestion while keeping the control performance high. We argue that relevance- and network-awareness are critical components of network protocol design to avoid control performance degradation in practice.

5G radio access network (RAN) slicing envisions a solution to flexibly deploy heterogeneous services as slices sharing the same infrastructure. However, this level of flexibility renders slice isolation challenging, mainly due to the stochastic nature of wireless resources. In the state-of-the-art, RAN slicing algorithm’s efficiency with respect to slice isolation is related to the ability of meeting individual slice requirements. However, mostly an aggregated slice performance guarantee is considered instead of per user guarantees. Hence, state-of-the-art approaches might not always provide the satisfaction of all users within a slice. Indeed, our results demonstrate that if user requirements within a slice are not included in the RAN slicing algorithm, the per user quality-of-service (QoS) may not be fulfilled. In this paper, we investigate the definition of slice isolation as the ability to satisfy individual users’ throughput within slices, in a frequency selective, multi-cell wireless scenario with focus on maximizing slices’ throughput. Our problem is tackled with a Lyapunov optimization approach, which proves to always achieve slice isolation. Our results show that our solution does not only achieve 100% user QoS guarantees compared to 50% achieved in the state-of-the-art, but also doubles the throughput with increasing number of BSs.

Cyber-physical systems (CPS) classify the set of applications where a physical, real-time process is monitored and controlled over a communication network. In CPS, providing fresh information is essential to satisfy the requirements imposed by time-critical applications. In order to quantify information freshness, age of information (AoI) has been proposed and employed as a metric for cross-layer design. In contrast to the vast majority of AoI-research, there have been a few attempts to measure AoI in real deployment scenarios. However, those contain either unalterable communication stack or are not publicly available for possible extensions. In this work, we present an open-source, experimental framework that is using software-defined radios for wireless communication. Our implementation contains centralized resource allocation using beacon packets and various conventional packet management policies such as first come first serve and last come first serve. In a case study with multiple inverted pendulums sharing a wireless channel, we show how the communication stack can be tailored to keep the information fresh in the network. We present the performance of feedback control loops in relation to AoI and show the benefit of keeping the information fresh on realistic CPS applications.

Age-of-information (AoI) is a metric quantifying information freshness at the receiver. Since AoI combines packet generation frequency, packet loss, and delay into a single metric, it has received a lot of research attention as an interface between communication network and application. In this work, we apply AoI to the problem of wireless scheduling for multi-loop networked control systems (NCS), i.e., feedback control loops closed over a shared wireless network. We model the scheduling problem as a Markov decision process (MDP) with AoI as its observable states and derive a relation of control system error and AoI. We further derive a stationary scheduling policy to minimize control error over an infinite horizon. We show that our scheduler outperforms the state-of-the-art scheduling policies for NCS. To the best of our knowledge, this is the first work proposing an AoI-based wireless scheduling policy that minimizes the control error over an infinite horizon for multi-loop NCS.

The evolution of the Internet of Things accelerated the development of Cyber-Physical Systems. Among them, Networked Control Systems (NCS) gained notable attention thanks to their application to industrial operations. Experimental NCS require expertise from control, computation, and communication disciplines. This requirement, together with the fragmentation of implementation platforms and experimental investigations, represents a challenge for the reproducibility and comparison of research results. In this paper, we tackle this problem by proposing a novel NCS benchmarking methodology that aids the reproducibility of NCS experiments. Relying on a novel approach to model the architectural elements and the delays of NCS, the methodology defines the experiment parameters and the relevant Key Performance Indicators (KPIs) that need to be observed during its execution. Furthermore, we detail the implementation of the first reproducible benchmarking platform for NCS. The proposed platform is open-source and designed to be easily reproducible and extensible by anyone. Finally, we replicate and evaluate the platform following the proposed NCS benchmarking methodology. The experimental results evaluate and compare the KPIs during the execution of the platform in different benchmarking scenarios, proving the validity of the proposed benchmarking methodology.

Cyber-Physical Systems (CPS) are widely spreading thanks to fast-paced technological breakthroughs of microcontrollers and communication networks. Among them, Networked Control Systems (NCS) gained notable attention thanks to their application in industrial operations. In NCS, the interconnection of a control logic with sensors and actuators used to steer a physical system occurs over a communication network. Despite large research interest on NCS, the reproducibility and comparison of experimental results are difficult to achieve. This is caused by the lack of well-established models and methodologies that combine the theoretical and practical aspects of NCS. We tackle this problem by proposing and demonstrating NCSbench: the first open-source reproducible benchmarking platform for NCS. NCSbench enables the benchmarking of research experiments using a networked two-wheeled inverted pendulum robot. For each benchmarking experiment, a set of values is measured and used to quantify the key performance indicators (KPIs) of the NCS. In our demonstration, we visualize in real-time the evolution of the benchmarking KPIs on a web-based Graphical User Interface.

Age of information (AoI) measures information freshness at the receiver. AoI may provide insights into quality of service in communication systems. For this reason, it has been used as a cross-layer metric for wireless communication protocols. In this work, we employ AoI to calculate penalty functions for a centralized resource scheduling problem. We consider a single wireless link shared by multiple, heterogeneous control systems where each sub-system has a time-varying packet loss probability. Sub-systems are competing for network resources to improve the accuracy of their remote estimation process. In order to cope with the dynamically changing conditions of the wireless link, we define a finite horizon age-penalty minimization problem and propose a scheduler that takes optimal decisions by looking H slots into the future. The proposed algorithm has a worst-case complexity that grows exponentially with H. However, by narrowing down our search space within the constrained set of actions, we are able to decrease the complexity significantly without losing optimality. On the contrary, we show by simulations that the benefit of increasing H w.r.t. remote state estimation performance diminishes after a certain H value.