Susanna Schwarzmann

Modern telecommunications networks are no longer required to perform only traffic management and connection establishment functions, but are increasingly evolving into general-purpose processing engines. This is facilitated by InNetwork Computing (INC), which has emerged as a key enabling paradigm in this direction. This shift in vision, however, requires a complete redesign of network infrastructures, with a strong emphasis on deep integration between networking and artificial intelligence capabilities. In the wake of these considerations, in this work we introduce an INC framework for the 3GPP 6G architecture to offload processing from the user device to the processing instances of the 6G mobile system, based on service requirements and constraints of individual user sessions, and delve into 3GPP Control Plane (CP) and User Plane (UP) aspects. Furthermore, we provide an experimental evaluation of the advantages of our INC framework in saving processing resources and energy in the user device while meeting the performance requirements of an AI-powered application.

The growing need for remote immersive collaboration across various societal fields like education, healthcare, and training has given rise to the emergence of Networked Collaborative Virtual Reality (NCVR), where users interact in shared virtual spaces over the network. In such context, the effectiveness of the collaboration will be determined by the quality of the interaction among the users and their perceived quality. However, understanding the user perception in NCVR is complex due to the interplay between network conditions, especially latency and individual user responses. Thus, there is a need for accurate modeling of user perception that could provide fast assessments of the user perception during the collaborative session. Traditionally, assessing user perception has been performed either by subjective studies, where users rank the perceived quality of the content after the session, or by objective metrics, which provide a measure of the quality of the content as compared to the original counterpart. These approaches fall short with NCVR, where not only the quality of the content, but of the interaction and the user’s well-being will be key. Physiological signals offer a promising pathway to capture the nuances of the user experience, yet their analysis is challenging due to their inherent complexity and individual variability. This paper makes two key contributions: first, it presents a thorough correlation analysis between user perception and physiological signals. Second, it introduces a novel machine learning method that integrates network performance metrics with physiological data to predict user perception in NCVR environments. The proposed approach was evaluated using an experimental dataset comprising heart activity and network performance data collected from users engaged in a collaborative VR task in the presence of latency-related impairments. Results indicated that combining network data with physiological signals improves prediction accuracy, achieving up to 84% accuracy for latency perception.

Artificial Intelligence/Machine Learning (AI/ML) methods for network automation have been widely adopted by the standardization community since 5G, due to its capability to learn patterns from continuously changing network data. Presently, AI in 3GPP is specified to be deployed as an overlay or add-on feature on top of conventional Network Functions (NFs), emitting a few limitations. First, NFs need to request the AI-overlay to derive intelligent actions, thereby lacking intelligent autonomy, that may degrade system and AI performance. Second, the capability of NFs and NF instances to added or removed based on changing network conditions is severely hindered, resulting in limited flexibility of NF deployment. To mitigate these limitations, this article explores architectural enablers for standards evolution from AI-overlay in 5G to native AI in 6G, where AI processing and communication is considered part of 6G system and architecture design. Via envisioned enablers – 6G-NF as an automated, intelligent entity, AI data and AI control – we conceive an Integrated Distributed AI Automation Layer (INTDAI), where each 6G-NF is equipped with the capabilities of an Intelligent Agent (IA) – independent data collection, intelligent decision-making and independent action execution. A special 6G-NF, the AI Controller, controls and manages a group of IAs to ensure overall system performance. The behavior and benefits of INTDAI are illustrated using a dedicated network automation use case, Dynamic User Plane Task Migration. By means of numerical analysis, we demonstrate the gain of INTDAI, motivating the need for future standardization work for AI-native 6G.

The future of human interaction is virtual. Thus it will require effective collaboration on tasks among users in remote settings. eXtended Reality (XR) is playing a leading role in this transition, offering a realm where virtual collaboration becomes not just possible but essential in situations where physical presence is limited by risk, cost, or complexity. However, while networks are continuously evolving, they can still introduce unexpected impairments that potentially degrade the user perception, i.e., the Quality-of-Experience (QoE), of such Collaborative Virtual Reality (CVR) scenarios. In response to this challenge, this paper presents a demonstrator designed to explicitly showcase the effects of network conditions on CVR. Our platform, centered around a pizza-making game, allows for exploration of the real-time impact of different network parameters, such as packet delay, loss, and throttling on the user engagement and perception in CVR. The framework employs a combination of subjective, objective, and physiological assessments, including the capture of heart rate and skin conductivity, to gain comprehensive insights into user experiences. Our platform not only allows users to directly experience the impact of network impairments on CVR interactions but also provides initial evidence of how such distortions affect both subjective perceptions and objective performance metrics.

Interactive, multi-user experiences are meant to define the present and future of Virtual Reality (VR). Such immersive experiences will typically consist of remote collaborations where content is streamed and/or synchronized over a network connection. Thus, real-time collaboration will be key. In this light, the responsiveness of the system and the network will define the overall experience. As such, understanding the effect of network distortions, especially related to time delay, on end-user’s perception (in terms of Quality-of-Experience (QoE)), performance, and collaboration becomes crucial. The existing literature, however, has mostly focused on network requirements from a system point-of-view, where the key performance parameters are only provided in the form of Quality-of-Service (QoS) parameters (such as end-to-end latency). However, the translation of these network impairments to the end-user experience is often omitted. The purpose of this paper is to fill the gap by providing a thorough investigation of the impact of latency on the perception of users while performing collaborative tasks in multi-user VR. To this end, an experimental framework was designed, developed, and tested. It is based on a multi-device synchronizing architecture, enabling two simultaneous users to work together in a gamified virtual environment. The developed test environment also allows for the identification of the most prominent network requirements and objective analysis for each traffic link. To experimentally investigate the impact of latency on user perception, a user study was conducted. Participants were paired and asked to perform the collaborative task under different latency-prone scenarios. The results show that users are able to easily distinguish between distorted and non-distorted network configurations. However, making a distinction between different manifestations of latency is much less straightforward. Moreover, factors such as the user’s role in the experience and the required task, and the level of interactivity and movement have an important influence on the subjective level of perception, the strength of the user’s preferences, and the occurrence of cybersickness. In contrast, no significant differences in objective metrics, such as system performance and user completion time were observed. These results can support the creation of collective QoE metrics that model the group as a whole rather than each individual separately. As such, this work provides an important step to dynamically counteract any drops in group dynamics and performance by means of smart interventions in the transmission system and/or virtual environment.

In future 6G networks, the deployment of network elements is expected to be highly distributed, going beyond the level of distribution of existing 5G deployments. To fully exploit the benefits of such a distributed architecture, there needs to be a paradigm shift from centralized to distributed management. To enable distributed management, Reinforcement Learning (RL) is a promising choice, due to its ability to learn dynamic changes in environments and to deal with complex problems. However, the deployment of highly distributed RL – termed massive distribution of intelligence – still faces a few unsolved challenges. Existing RL solutions, based on Q-Learning (QL) and Deep Q-Network (DQN) do not scale with the number of agents. Therefore, current limitations, i.e., convergence, system performance and training stability, need to be addressed, to facilitate a practical deployment of massive distribution. To this end, we propose improved Double Deep Q-Network (IDDQN), addressing the long-term stability of the agents’ training behavior. We evaluate the effectiveness of IDDQN for a beyond 5G/6G use case: auto-scaling virtual resources in a network slice. Simulation results show that IDDQN improves the training stability over DQN and converges at least 2 times sooner than QL. In terms of the number of users served by a slice, IDDQN shows good performance and only deviates on average 8% from the optimal solution. Further, IDDQN is robust and resource-efficient after convergence. We argue that IDDQN is a better alternative than QL and DQN, and holds immense potential for efficiently managing 6G networks.

In-Network Computing (INC) is a currently emerging paradigm. Realizing INC in 6G networks could mean that user plane entities (UPEs) carry out computations on packets while transmitting them. These computations may have specific requirements in terms of their completion time. In case of high compute pressure at one UPE, migrating computations to another UPE may be beneficial, in order to avoid exceeding the completion time requirement. Centralized migration approaches suffer from increased signaling and are prone to react too slow. Therefore, this paper investigates the applicability of distributed intelligence to tackle the problem of compute task migration in the 6G user plane. Each UPE is equipped with an intelligent agent, enabling autonomous decisions on whether computations should be migrated to another UPE. To enable the intelligent agents to learn and apply an optimal task migration policy, we investigate and compare of two state-of-the-art Deep Reinforcement Learning (DRL) approaches: Advantage Actor-Critic (A2C) and Double Deep Q-Network (DDQN). We show, via simulations, that the performance of both solutions, in terms of the percentage of tasks exceeding their completion time requirement, is near-optimal and training A2C is at least 60% faster.Â

Our solution evaluation is based on synthetic data-sets generated by our internally-developed simulation platform. This means we do not use any stand-alone, external or internal data-sets. Our platform code is not public, but we describe in detail the design of the platform and the data-set generator module, for other researchers to reproduce our results. The code is written in 100% Python, leveraging object-oriented approaches for code reusability.  This article has been accepted for publication in IEEE Transactions on Network and Service Management. This is the author’s version which has not been fully edited and content may change prior to final publication. Citation information: DOI 10.1109/TNSM.2023.3333875 © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.

Monitoring and providing customers with a satisfying Quality of Experience (QoE) is a crucial business incentive for mobile network operators (MNOs). While the MNO is capable of monitoring a vast amount of network-related key performance indicators (KPIs), it typically does not have access to application-specific performance metrics. Among others, this is due to practical obstacles, such as missing standardized interfaces between the network and the application. Existing QoE models allow to map collected KPIs to the user-perceived quality. However, they are not dynamic, cumbersome to obtain, and often rely on application-level information, such as the stalling duration in the case of video streaming. The 5G networking architecture provides new features which can potentially overcome current limitations of in-network QoE monitoring. More specifically, the Application Function (AF) provides a standardized interface for communicating between 5G systems and third parties, such as application providers. The Network Data Analytics Function (NWDAF) is capable of collecting a vast number of network statistics from other 5G network functions and is dedicated to training and deploying Machine Learning (ML) models. This opens new possibilities, unimaginable for earlier mobile network generations, to dynamically learn the relationship between network KPIs and QoE by utilizing ML. Besides elaborating on how the new capabilities introduced with 5G can support an ML-based QoE estimation, we perform a simulation-based feasibility study which evaluates the estimation accuracy of different state-of-the-art regression techniques. In addition, we discuss them with respect to various qualitative aspects from an MNO’s point of view.