Mutual-Information Maximizing Finite-Alphabet (MIM-FA) decoders have been introduced as an approach to reduce the decoding complexity of Low Density Parity Check codes while maintaining performance close to that of Floating-Point (FP) Belief-Propagation (BP) decoders. The applicability of these low-complexity decoders to practically relevant systems with higher-order modulated signals transmitted over multicarrier systems like Orthogonal Frequency Division Multiplexing (OFDM) is crucial for their application in 5G and 6G systems. We propose a pragmatic approach for the design of a receiver structure for a MIM-FA decoders that can deal with the varying reliabilities of OFDM subcarriers and being agnostic to the modulation scheme. The simulation results indicate that the proposed scheme in combination with a 3-bit MIM-FA decoder exploits the full frequency diversity and performs close to FP-BP decoder.

This paper highlights key areas in which AI/ML can play a transformative role in 6G, with an emphasis on energy-efficient solutions. Contextualized within Germany’s national 6G research initiative, "6G Access, Network of Networks, Automation and Simplification" (6G-ANNA) emerges as the lighthouse project, providing a holistic vision that sets the direction for numerous specialized research efforts. Within this context, this paper aims to present ideas relevant to both academia and industry by identifying key research directions for AI/ML. We begin by reviewing the latest developments in using AI/ML for the Fifth Generation (5G) New Radio (NR) air interface as discussed in 3rd Generation Partnership Project (3GPP) Releases 18 and 19, and examine how these advancements pave the way for a native and energy-efficient AI/ML air interface in 6G. Key results are presented on AI/ML-driven optimization of radio frequency (RF) frontends, along with a strong focus on the role of AI/ML in diverse signal processing tasks and energy saving mechanisms, which demonstrate the potential of AI/ML in improving spectral efficiency and reducing energy consumption. The discussion further introduces methodologies for testing AI/ML-based signal processing tailored for the 6G physical layer, addressing practical challenges relevant to industry stakeholders and standard development organizations. Finally, we discuss the standardization aspects critical for realizing a future AI-native air interface in 6G, aligning our findings with ongoing and upcoming global standardization activities.

In this article, we introduce a Reinforcement Learning (RL)–driven framework for Information Bottleneck (IB)–based distributed Joint Source–Channel Coding (JSCC) that operates reliably when the forward channels are unknown, non-differentiable, stochastic, or entirely black-box. Current state-of-the-art deep variational IB methods require differentiable end-to-end models and full knowledge of the forward channels’ statistics, which renders them ineffective in many practical scenarios involving hidden channel states, human-in-the-loop setups, or proprietary simulators. To overcome these limitations, we reformulate the IB-based JSCC design problem as a sequential decision-making task. This enables the use of deep Multi-Agent Reinforcement Learning (MARL). We first revisit the single-terminal setup and show that the encoder can be treated as a policy in a contextual bandit whose sampled reward is set as the decoder reconstruction term, while the compression penalty is applied directly as an analytic actor regularizer derived from a variational surrogate of the IB objective. This yields a model-free compressor that learns to preserve relevance while respecting the rate constraint, without requiring gradients through the channel. We then extend the framework to the multiterminal setting, where multiple encoders observe noisy versions of a common source and must coordinate implicitly through the environment. Two retrieval strategies are considered: a parallel scheme, which ignores the side-information at the decoder, and a successive scheme, which exploits the side-information at the decoder via conditional priors. For both scenarios, we derive RL-compatible variational lower-bounds on the original IB objectives, enabling Centralized Training with Decentralized Execution (CTDE). By this, we generalize state-of-the-art distributed data-driven IB-based JSCC schemes to arbitrary forward channels while retaining the scalability and sample efficiency. As the main highlight, this work demonstrates that MARL provides a principled foundation for learning distributed compressors in environments where model- or gradient-based approaches are fundamentally inapplicable.

The sixth generation (6G) of wireless networks is envisioned to achieve far beyond the capabilities of fifth generation (5G), necessitating significant innovations at the physical layer (PHY). These include exploration of several fundamental trade-offs between spectral efficiency, reliability, and energy consumption, and enhancing the performance of key enablers for 6G PHY. This paper synthesizes key insights from the 6G-ANNA research initiative on emerging PHY technologies for 6G to provide a holistic exploration of the ongoing trends in the 6G research. The investigations span novel waveform and channel coding techniques for improved energy efficiency, the “Gearbox PHY” concept for adaptive transceiver operations, and optimized radio transceiver designs that balance complexity and power consumption. The study also examines advanced multiple access schemes and cell-free massive multiple-input multiple-output (MIMO) architectures to enhance spectral efficiency and uniform coverage. Integrated artificial intelligence (AI) solutions at the PHY layer and insights to security and trustworthiness challenges in 6G networks are also provided. The findings offer insights into the fundamental trade-offs and provide several key PHY innovations that address sustainability, capacity, and resiliency challenges of future 6G wireless systems.

We consider a generic two-hop transmission setup. Explicitly, a source signal is transmitted over an imperfect channel, yielding a noisy observation. This signal shall then be compressed at a relay node before getting transmitted further over an error-prone and rate-limited channel to the sink, where the source signal is decoded/reconstructed. In [1], [2], we presented a data-driven Information Bottleneck-based quantization scheme called Deep FAVIB. For that, we derived a tractable variational lower-bound of the original objective functional that could be optimized using samples and utilized Deep Neural Networks (DNNs) to realize both the quantizer/encoder at the relay node and the decoder at the sink. Based on this work, we now provide further investigations, showcasing the excellent generalization capabilities of Deep FAVIB by several Symbol-Error-Rate (SER) simulation results. Specifically, we apply the pretrained Deep FAVIB to different environments that have not been present in the training, and show that yet, it yields promising results. This gives clear evidence to the fact that Deep FAVIB can be considered as a practically efficient scheme to be utilized, especially when dealing with the highly dynamic and challenging environments.

Satellite-based communications are expected to be a substantial future market in 6G networks. As satellite constellations grow denser and transmission resources remain limited, frequency reuse plays an increasingly important role in managing inter-user interference. In the multi-user downlink, precoding enables the reuse of frequencies across spatially separated users, greatly improving spectral efficiency. The analytical calculation of suitable precodings for perfect channel information is well studied, however, their performance can quickly deteriorate when faced with, e.g., outdated channel state information or, as is particularly relevant for satellite channels, when position estimates are erroneous. Deriving robust precoders under imperfect channel state information is not only analytically intractable in general but often requires substantial relaxations of the optimization problem or heuristic constraints to obtain feasible solutions. Instead, in this paper we flexibly derive robust precoding algorithms from given data using reinforcement learning. We describe how we adapt the applied Soft Actor-Critic learning algorithm to the problem of downlink satellite beamforming and show numerically that the resulting precoding algorithm adjusts to all investigated scenarios. The considered scenarios cover both single satellite and cooperative multi-satellite beamforming, using either global or local channel state information, and two error models that represent increasing levels of uncertainty. We show that the learned algorithms match or markedly outperform two analytical baselines in sum rate performance, adapting to the required level of robustness. We also analyze the mechanisms that the learned algorithms leverage to achieve robustness. The implementation is publicly available for use and reproduction of the results.

Non-Terrestrial Networks (NTNs) are critical enablers of ubiquitous connectivity in future 6 G systems, but they also face challenges such as long propagation delays, significant Doppler effects, and diverse channel conditions. Developing and testing communication technologies for NTNs requires realistic and flexible simulation tools. In this work, OpenNTN is presented as an open-source software framework for simulating NTN channel models based on the 3GPP TR38.811 standard. OpenNTN is designed as an extension to the Python-based Sionna ${ }^{\text {TM }}$ framework, providing channel models compatible with existing interfaces, enabling the use of the powerful tools found in Sionna ${ }^{\text{TM}}$. The framework offers a flexible user interface, enabling researchers to investigate diverse scenarios. As an open-source implementation, OpenNTN empowers the research community to fully use and adapt the framework, offering a solution for both fast and easy NTN research using realistic channel models, while also providing the opportunity to extend the model for custom research interests beyond the current state of the standards.

The rapid growth of non-terrestrial communication necessitates its integration with existing terrestrial networks, as highlighted in 3GPP Releases 16 and 17. This paper analyses the concept of functional splits in 3D-Networks. To manage this complex structure effectively, the adoption of a Radio Access Network (RAN) architecture with Functional Split (FS) offers advantages in flexibility, scalability, and cost-efficiency. RAN achieves this by disaggregating functionalities into three separate units. Analogous to the terrestrial network approach, 3GPP is extending this concept to non-terrestrial platforms as well. This work presents a general analysis of the requested Fronthaul (FH) data rate on feeder link between a non-terrestrial platform and the ground-station. Each split option is a trade-of between FH data rate and the respected complexity. Since flying nodes face more limitations regarding power consumption and complexity on board in comparison to terrestrial ones, we are investigating the split options between lower and higher physical layer.

In the Cell-Free massive Multiple-Input MultipleOutput (CF-mMIMO) systems, a large number of distributed users are simultaneously served by multiple Radio Access Points (RAPs). In the uplink, each RAP receives noisy observations from several users and must locally compress these signals before forwarding them to the corresponding Central Processing Unit (CPU) via multiple fronthaul channels, each subject to a rate limitation. The challenge is to design the compressed signals at the RAPs such that the received signals at the CPU retain as much information as possible about the users (to be retrieved). To address this, we adopt compression techniques based on the Information Bottleneck (IB) principle to design local quantizers at the RAPs by ensuring an efficient balance between the informativity and compactness of the compressed signals. We discuss here two different compression schemes: one that processes the signals independently across fronthaul links and another that leverages the side information from previously retrieved signals at the CPU. By using side information, the latter generally provides a better tradeoff between the compression efficiency and performance, albeit with an increased complexity. Through numerical simulations, we demonstrate the effectiveness of both IB-based schemes compared to the conventional compression methods, showing their potential for improving fronthaul rate efficiency and overall system performance in typical digital transmission scenarios.

The integration of conventional terrestrial wireless communication networks and non-terrestrial networks (NTNs) is the main prerequisite for achieving global connectivity in the next generation (6G) wireless communications. Such integrated communication networks are usually referred to as the unified 3D networks. These networks need to meet the requirements for 6G communications in terms of higher data rates, as well as enhanced reliability, security and network reconfigurability. To achieve these goals, new technologies and components have to be developed. This work introduces the German project 6G-TakeOff, aimed at the development of innovative solutions for unified 3D networks. The project consortium brings together leading academic and industrial partners, covering the entire value chain from design of electronics to applications. In this work, the focus is on the development of key hardware components to support the wireless communication in 3D unified networks. The design concept for each component and the planned demonstrators are presented.

In this article, we concentrate on a generic multiterminal joint source-channel coding scenario, appearing in a wide variety of real-world applications. Specifically, several noisy observations from a source signal must be compressed at some intermediate nodes, before getting forwarded over multiple error-prone and rate-limited channels towards a (remote) processing unit. The imperfections of the forward channels should be integrated into the design of (local) compressor units. By following the Information Bottleneck principle, the Mutual Information is selected here as the fidelity criterion, and a novel (data-driven) design approach is presented for two distinct types of processing flow / strategy at the remote unit. To that end, tractable objective functions are developed, together with the pertinent learning architectures, generalizing the concepts of Variational Auto-Encoders and (Distributed) Deep Variational Information Bottleneck for (remote) source coding to the context of distributed joint source-channel coding. Unlike the conventional approaches, the proposed schemes here work based upon a finite sample set, thereby obviating the call for full prior knowledge of the joint statistics of input signals. The effectiveness of these novel sample-based compression schemes is substantiated as well by a couple of simulations over typical transmission setups.

The very new evolution towards 6G networks necessitates a paradigm shift towards unified 3D network architectures, encompassing space, air, and ground segments. This paper outlines the conceptualization, challenges, and prospects of such a transformative architecture. We outline the foundational principles, drawn from standardization endeavors and cutting-edge research initiatives, to articulate the envisioned architecture poised to redefine network capabilities. Driven by the need to enhance capacity, increase data rates, support diverse mobility models, and facilitate heterogeneous connectivity, the conceptual framework of a unified 3D network is presented. The focus is on seamlessly integrating diverse network segments and fostering holistic network orchestration. In examining the technical challenges inherent to the realization of a unified 3D network, we outline our strategies to address mobility management, handover optimization, interference mitigation, and the integration of distributed physical layer concepts. Proposals encompass federated learning mechanisms, advanced beamforming techniques, and energy-efficient computational offloading strategies, aimed at enhancing network performance and resilience. Moreover, we outline compelling utilization scenarios and highlighted promising avenues for future research.

We propose a novel approach for downlink transmission from a satellite swarm towards a very small aperture terminal (VSAT). These swarms have the benefit of much higher spatial separation in the transmit antennas than traditional satellites with antenna arrays, promising a massive increase in spectral efficiency. The resulting precoder and equalizer have only low demands on computational complexity, inter-satellite coordination and channel estimation. This is achieved by taking knowledge about the geometry between satellites and VSAT into account. Due to the position based transceiver design, only slowly changing long-term statistics of the channel coefficient are considered. The necessity of accurate positional information is further relaxed by considering stochastic knowledge about the relative positions between satellites and VSAT rather than exact knowledge. Specifically, each satellite needs only stochastic information about the VSATs’ relative positions to calculate its precoding vector. Similarly, the VSAT requires only stochastic knowledge of the satellites’ relative positions for equalization. Furthermore, we evaluate the impact the inter-satellite distance has on the achievable data rate. Based on that, an analytic approach to arrange the satellites in a satellite swarm to maximize the rate is provided. The combination of the low complexity transceiver with suitable inter-satellite distances is proven to be capacity achieving in specific scenarios. The simulation results provide evidence that the proposed inter-satellite distance in combination with the proposed transceiver enables close-to-optimal rates in practical applications.

In this article, we focus on a generic multiterminal (remote) source coding scenario in which, via a joint design, several intermediate nodes must locally compress their noisy observations from various sets of user / source signals ahead of forwarding them through multiple error-free and rate-limited channels to a (remote) processing unit. Although different local compressors might receive noisy observations from a / several common source signal(s), each local quantizer should also compress noisy observations from its own, i.e., uncommon source signal(s). This, in turn, yields a highly generalized scheme with most flexibility w.r.t. the assignment of users to the serving nodes, compared to the State-of-the-Art techniques designed exclusively for a common source signal. Following the Information Bottleneck (IB) philosophy, we choose the Mutual Information as the fidelity criterion here, and, by taking advantage of the Variational Calculus, we characterize the form of stationary solutions for two different types of processing flow / strategy. We utilize the derived solutions as the core of our devised algorithmic approach, the GEneralized Multivariate IB (GEMIB), to (efficiently) address the corresponding design problems. We further provide the respective convergence proofs of GEMIB to a stationary point of the pertinent objective functionals and substantiate its effectiveness by means of numerical investigations over a couple of (typical) digital transmission scenarios.

Consider a user equipment in a Cell-Free massive Multiple-Input Multiple-Output (CF-mMIMO) system that is served by several Radio Access Points (RAPs). In the uplink of this setup, these RAPs receive noisy observations of the user/source signal and must locally compress their signals before forwarding them to the Central Processing Unit (CPU) through multiple rate-limited fronthaul channels. To retrieve the source signal at CPU, we are interested in maximizing the Mutual Information (MI) between the received signals at CPU and the user/source signal, and purposefully choose the Information Bottleneck (IB)-based compression techniques to design the quantizers at RAPs. We consider both separate and joint designs of the local compressors by establishing basic trade-offs between the informativity and compactness of the outcomes. For the joint design, two different schemes are presented, based on whether to leverage the side-information at CPU. Finally, the effectiveness of both compression schemes will be shown as well by means of numerical investigations over typical digital data transmission scenarios.

Low Earth Orbit (LEO) satellite-to-handheld connections herald a new era in satellite communications. Space-Division Multiple Access (SDMA) precoding is a method that mitigates interference among satellite beams, boosting spectral efficiency. While optimal SDMA precoding solutions have been proposed for ideal channel knowledge in various scenarios, addressing robust precoding with imperfect channel information has primarily been limited to simplified models. However, these models might not capture the complexity of LEO satellite applications. We use the Soft Actor-Critic (SAC) deep Reinforcement Learning (RL) method to learn robust precoding strategies without the need for explicit insights into the system conditions and imperfections. Our results show flexibility to adapt to arbitrary system configurations while performing strongly in terms of achievable rate and robustness to disruptive influences compared to analytical benchmark precoders.

This paper investigates energy-efficient communication within an integrated sensing and communication system. The system employs a dual-function radar-communication base station. This base station concurrently serves multiple mobile users for communication purposes while also performing target sensing within a designated range cell. An active reconfigurable intelligent surface (RIS) is utilized to enhance communication efficiency. The focus of this work is to optimize the communication energy efficiency by jointly allocating the transmit power and configuring the RIS elements. This optimization is achieved while satisfying constraints on both the probing power required for target sensing and the quality-of-service demands of the communication users. Two novel optimization methods are proposed, combining techniques from alternating optimization, sequential programming, and fractional programming. Through numerical simulations, the effectiveness of the developed algorithms is validated. Additionally, the performance of the system utilizing an active RIS is compared to that of a system with a passive RIS, specifically in terms of their respective communication energy efficiencies.

Non-orthogonal multiple access (NOMA) has been introduced as a promising scheme to allow for superposition of signals, such as the transmission of multiple services in the same resource block (time and frequency). In this paper, we propose the application of Deep Learning (DL) in an Autoencoder (AE) framework for simultaneous usage in multi-service NOMA transmission. While classical NOMA simultaneously incorporates locally separated user equipments (UEs), we focus on the simultaneous transmission of services within a single UE. Our scheme achieves improved performance compared to classical NOMA schemes and is capable of performing optimal estimation of the superimposed transmit signals. The scheme utilizes an equidistant power allocation scheme. The results show the potential of using DL to enhance the performance of NOMA systems and improve their adaptability and flexibility to different scenarios.

We consider a two-hop transmission setup in the context of Non-Terrestrial Networks (NTNs). Explicitly, a noisy source signal should be compressed at an on-ground relay node before getting forwarded over an error-prone and rate-limited channel to a satellite transponder. The impacts of this imperfect forwarding should be integrated into the compressor’s design formulation. In full harmony with the Information Bottleneck (IB) principle, we choose the Mutual Information (MI) as the fidelity criterion and devise a data-driven algorithm, the Deep Forward-Aware Vector Information Bottleneck (Deep FAVIB), to tackle the design problem, when solely a finite sample set is available. To this end, first we derive a tractable objective function and, later on, utilize it to train the encoder and decoder Deep Neural Networks (DNNs) in the introduced learning architecture. Our approach here, that is based on (generative) latent variable models, extends the well-known concepts of Variational Auto-Encoders (VAEs) and Deep Variational Information Bottleneck (Deep VIB) from remote source coding to joint source-channel coding. To corroborate the effectiveness of our data-driven approach, we also present several numerical results over a typical transmission scenario for NTNs.