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.

Over the past few years, the concept of Virtual Reality (VR) has attracted increasing interest thanks to its extensive industrial and commercial applications. Currently, the 3D models of the virtual scenes are generally stored in the VR visor itself, which operates as a standalone device. However, applications that entail multi-party interactions will likely require the scene to be processed by an external server and then streamed to the visors. However, the stringent Quality of Service (QoS) constraints imposed by the VR's interactive nature require Network Slicing (NS) solutions, for which profiling the traffic generated by the VR application is crucial. To this end, we collected more than 4 hours of traces in a real setup and analyzed their temporal correlation, focusing on the CBR encoding mode, which should generate more predictable traffic streams. From the collected data, we then distilled two prediction models for future frame size, which can be instrumental in the design of dynamic resource allocation algorithms. Our results show that even the state-of-the-art H.264 CBR mode may have significant frame size fluctuations, impacting NS optimization. We then exploited the models to dynamically determine requirements in an NS scenario, providing the required QoS while minimizing resource usage.

The latest IEEE 802.11 amendments provide support to directional communications in the Millimeter Wave spectrum, thus making it possible to wirelessly approach several emerging use cases, such as eXtended Reality (XR), telepresence, and remote control of industrial facilities. However, these applications require stringent Quality of Service (QoS), that only contention-free scheduling algorithms can guarantee. In this paper, we propose a framework for the joint admission control and scheduling of periodic traffic streams over mmWave Wireless Local Area Networks based on Network Simulator 3 (ns-3), a popular full-stack open-source network simulator. Moreover, we design a baseline algorithm to handle scheduling requests, and evaluate its performance with a full-stack perspective. The algorithm is tested in three scenarios, where we investigated different configurations and features to highlight the trade-offs between contention-based and contention-free access strategies.

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 past few years, eXtended Reality (XR) has attracted increasing interest thanks to its extensive industrial and commercial applications, and its popularity is expected to rise exponentially over the next decade. However, the stringent Quality of Service (QoS) constraints imposed by XR’s interactive nature require Network Slicing (NS) solutions to support its use over wireless connections: in this context, quasi-Constant Bit Rate (CBR) encoding is a promising solution, as it can increase the predictability of the stream, making the network resource allocation easier. However, traffic characterization of XR streams is still a largely unexplored subject, particularly with this encoding. In this work, we characterize XR streams from more than 4 hours of traces captured in a real setup, analyzing their temporal correlation and proposing two prediction models for future frame size. Our results show that even the state-of-the-art H.264 CBR mode can have significant frame size fluctuations, which can impact the NS optimization. Our proposed prediction models can be applied to different traces, and even to different contents, achieving very similar performance. We also show the trade-off between network resource efficiency and XR QoS in a simple NS use case.

In the context of cooperative and automated driving, mmWave-based technologies will have a key role in meeting the requirements of present and future automotive applications, even though channels operating at such high frequencies are characterized by high variability, pathloss and sensitivity to blockage. In this paper we describe how we started to deal with these challenges creating MilliCar, a standard compliant, open-source software for the research community, while also listing the steps required to further advance the state of the art.

3GPP NR V2X represents the new 3GPP standard for next-generation vehicular systems which, among other innovations, supports vehicle-to-vehicle (V2V) operations in the millimeter wave (mmWave) spectrum to address the communication requirements of future intelligent automotive networks. While mmWaves will enable massive data rates and low latency, the propagation characteristics at very high frequencies become very challenging, thereby calling for accurate performance evaluations as a means to properly assess the performance of such systems. Along these lines, in this paper we use MilliCar, the new ns-3 module based on the latest NR V2X specifications, to provide an end-to-end performance evaluation of mmWave V2V networks. We investigate the impact of different propagation scenarios and system parameters, including the inter-vehicle distance, the adopted frame numerology, and the modulation and coding scheme, and provide guidelines towards the most promising V2V deployment configurations.

In the last decades, technological developments in wireless communications have been coupled with an increasing demand of mobile services. From real-time applications with focus on entertainment (e.g., high quality video streaming, virtual and augmented reality), to industrial automation and security scenarios (e.g., video surveillance), the requirements are constantly pushing the limits of communication hardware and software. Communications at millimeter wave frequencies could provide very high throughput and low latency, thanks to the large chunks of available bandwidth, but operating at such high frequencies introduces new challenges in terms of channel reliability, which eventually impact the overall end-to-end performance. In this paper, we introduce a proxy that coordinates the physical and transport layers to seamlessly adapt to the variable channel conditions and avoid performance degradation (i.e., latency spikes or low throughput). We study the performance of the proposed solution using a simulated IEEE 802.11ad-compliant network, with the integration of input traces generated from measurements from real devices, and show that the proposed proxy-based mechanism reduces the latency by up to 50% with respect to TCP CUBIC on a 60 GHz link.