Goal-oriented Communication (GoC) is a new paradigm that activates data transmission only when it is instrumental for the receiver to achieve a certain goal. This leads to the advantage of reducing the frequency of transmissions significantly while maintaining adherence to the receiver’s objectives. However, GoC scheduling also opens a timing-based side channel that an eavesdropper can exploit to estimate the state of the system. This type of attack sidesteps even information-theoretic security, as it exploits the timing of updates rather than their content. In this work, we study such an eavesdropping attack against pull-based goal-oriented scheduling for remote monitoring and control of Markov processes. We provide a theoretical framework for defining the effectiveness of the attack and propose possible countermeasures, including three heuristics that provide a balance between the performance gains offered by GoC and the amount of leaked information. Our results show that, while a naive GoC scheduler allows the eavesdropper to correctly guess the system state about 60% of the time, our heuristic defenses can halve the leakage with a marginal reduction of the benefits of goal-oriented approaches.

Artificial Intelligence (AI) is a key component of$\mathbf{6 G}$networks, as it enables communication and computing services to adapt to end users' requirements and demand patterns. The management of Mobile Edge Computing (MEC) is a meaningful example of AI application: computational resources available at the network edge need to be carefully allocated to users, whose jobs may have different priorities and latency requirements. The research community has developed several AI algorithms to accomplish this goal, but it has neglected a key aspect: learning is itself a computationally demanding task, and considering free training results in idealized conditions and performance in simulations. In this work, we consider a more realistic framework that explicitly accounts for the cost of learning, presenting a new algorithm to dynamically select when to train a Deep Reinforcement Learning (DRL) agent that allocates resources in a MEC facility. Our method is highly general, as it can be directly applied to any scenario involving a training overhead, and it can approach the same performance as an ideal learning agent even under realistic training conditions.

Pragmatic or goal-oriented communication can optimize communication decisions beyond the reliable transmission of data, instead aiming at directly affecting application performance with the minimum channel utilization. In this paper, we develop a general theoretical framework for the remote control of finite-state Markov processes, using pragmatic communication over a costly zero-delay communication channel. To that end, we model a cyber-physical system composed of an encoder, which observes and transmits the states of a process in real-time, and a decoder, which receives that information and controls the behavior of the process. The encoder and the decoder should cooperatively optimize the trade-off between the control performance (i.e., reward) and the communication cost (i.e., channel use). This scenario underscores a pragmatic (i.e., goal-oriented) communication problem, where the purpose is to convey only the data that is most valuable for the underlying task, taking into account the state of the decoder (hence, the pragmatic aspect). We investigate two different decision-making architectures: in pull-based remote control, the decoder is the only decision-maker, while in push-based remote control, the encoder and the decoder constitute two independent decision-makers, leading to a multi-agent scenario. We propose three algorithms to optimize our system (i.e., design the encoder and the decoder policies), discuss the optimality guarantees ofs the algorithms, and shed light on their computational complexity and fundamental limits.

Predictive Quality of Service (PQoS) makes it possible to anticipate QoS changes, e.g., in wireless networks, and trigger appropriate countermeasures to avoid performance degradation. A promising tool for PQoS is given by Reinforcement Learning (RL), a methodology that enables the design of decision-making strategies for stochastic optimization. In this manuscript, we present PRATA, a new simulation framework to enable PRedictive QoS based on AI for Teleoperated driving Applications. PRATA consists of a modular pipeline that includes (i) an end-to-end protocol stack to simulate the 5G Radio Access Network (RAN), (ii) a tool for generating automotive data, and (iii) an Artificial Intelligence (AI) unit to optimize PQoS decisions. To prove its utility, we use PRATA to design an RL unit, named RAN-AI, to optimize the segmentation level of teleoperated driving data in the event of resource saturation or channel degradation. Hence, we show that the RAN-AI entity efficiently balances the trade-off between QoS and Quality of Experience (QoE) that characterize teleoperated driving applications, almost doubling the system performance compared to baseline approaches. In addition, by varying the learning settings of the RAN-AI entity, we investigate the impact of the state space and the relative cost of acquiring network data that are necessary for the implementation of RL.

The Network Slicing (NS) paradigm enables the partition of physical and virtual resources among multiple logical networks, possibly managed by different tenants. In such a scenario, network resources need to be dynamically allocated according to the slice requirements. In this paper, we attack the above problem by exploiting a Deep Reinforcement Learning approach. Our framework is based on a distributed architecture, where multiple agents cooperate towards a common goal. The agent training is carried out following the Advantage Actor Critic algorithm, which permits to handle continuous action spaces. By means of extensive simulations, we show that our approach yields better performance than both a static allocation of system resources and an efficient empirical strategy. At the same time, the proposed system ensures high adaptability to different scenarios without the need for additional training.

Over the last few years, the Deep Reinforcement Learning (DRL) paradigm has been widely adopted for 5G and beyond network optimization because of its extreme adaptability to many different scenarios. However, collecting and processing learning data entail a significant cost in terms of communication and computational resources, which is often disregarded in the networking literature. In this work, we analyze the cost of learning in a resource-constrained system, defining an optimization problem in which training a DRL agent makes it possible to improve the resource allocation strategy but also reduces the number of available resources. Our simulation results show that the cost of learning can be critical when evaluating DRL schemes on the network edge and that assuming a cost-free learning model can lead to significantly overestimating performance.

In recent years, autonomous networks have been designed with Predictive Quality of Service (PQoS) in mind, as a means for applications operating in the industrial and/or automotive sectors to predict unanticipated Quality of Service (QoS) changes and react accordingly. In this context, Reinforce-ment Learning (RL) has come out as a promising approach to perform accurate predictions, and optimize the efficiency and adaptability of wireless networks. Along these lines, in this paper we propose the design of a new entity, integrated at the RAN level that implements PQoS functionalities with the support of an RL framework. Specifically, we focus on the design of the reward function of the learning agent, able to convert QoS estimates into appropriate countermeasures if QoS requirements are not satisfied. We demonstrate via ns-3 simulations that our approach achieves better results in terms of QoS and Quality of Experience (QoE) performance of end users in a teleoperated driving scenario.

Over the last few years, the many uses of Unmanned Aerial Vehicles (UAVs) have captured the interest of both the scientific and the industrial communities. A typical scenario consists in the use of UAVs for surveillance or target-search missions over a wide geographical area. In this case, it is fundamental for the command center to accurately estimate and track the trajectories of the UAVs by exploiting their periodic state reports. In this work, we design anad hoctracking system that exploits the Long Range Wide Area Network (LoRaWAN) standard for communication and an extended version of the Constant Turn Rate and Acceleration (CTRA) motion model to predict drone movements in a 3D environment. We analyze the trade-off in setting the main parameters of the communication system and Adaptive Data Rate (ADR) scheme, showing how our tracking system can handle large swarms of drones at distances up to 4 km. Simulation results on a publicly available dataset show that our system can reliably estimate the position and trajectory of a swarm of UAVs, significantly outperforming baseline tracking approaches.

In this work, we face the issue of achieving an efficient dynamic mapping in vehicular networking scenarios, i.e., obtaining an accurate estimate of the positions and trajectories of connected vehicles in a certain area. State-of-the-art solutions are based on the periodic broadcasting of the position information of the network nodes, with an inter-transmission period set by a congestion control scheme. However, the movements and maneuvers of vehicles can often be erratic, making transmitted data inaccurate or downright misleading. To address this problem, we propose to adopt a dynamic transmission scheme based on the actual positioning error, sending new data when the estimate overcomes a preset error threshold. Furthermore, the proposed method adapts the error threshold to the operational context according to an innovative congestion control algorithm that limits the collision probability among broadcast packet transmissions. This threshold-based strategy can reduce the network load by avoiding the transmission of redundant messages, and is shown to improve the overall positioning accuracy by more than 20% in realistic urban scenarios.

So far, research on Smart Cities and self-organizing networking techniques for fifth-generation (5G) cellular systems has been one-sided: a Smart City relies on 5G to support massive machine-to-machine (M2M) communications, but the actual network is unaware of the information flowing through it. However, a greater synergy between the two would make the relationship mutual, since the insights provided by the massive amount of data gathered by sensors can be exploited to improve the communication performance. In this paper, we concentrate on self-organization techniques to improve handover efficiency using vehicular traffic data gathered in London. Our algorithms exploit mobility patterns between cell coverage areas and road traffic congestion levels to optimize the handover bias in heterogeneous networks and dynamically manage mobility management entity (MME) loads to reduce handover completion times.