Integrating Pre-Trained Language Model with Physical Layer Communications

The burgeoning field of on-device AI communication, where devices exchange information directly through embedded foundation models, such as language models (LMs), requires robust, efficient, and generalizable communication frameworks. However, integrating these frameworks with existing wireless systems and effectively managing noise and bit errors pose significant challenges. In this work, we introduce a practical on-device AI communication framework, integrated with physical layer (PHY) communication functions, demonstrated through its performance on a link-level simulator. Our framework incorporates end-to-end training with channel noise to enhance resilience, incorporates vector quantized variational autoencoders (VQ-VAE) for efficient and robust communication, and utilizes pre-trained encoder-decoder transformers for improved generalization capabilities. Simulations, across various communication scenarios, reveal that our framework achieves a 50% reduction in transmission size while demonstrating substantial generalization ability and noise robustness under standardized 3GPP channel models.

Interference-Aware Emergent Random Access Protocol for Downlink LEO Satellite Networks

In this article, we propose a multi-agent deep reinforcement learning (MADRL) framework to train a multiple access protocol for downlink low earth orbit (LEO) satellite networks. By improving the existing learned protocol, emergent random access channel (eRACH), our proposed method, coined centralized and compressed emergent signaling for eRACH (Ce2RACH), can mitigate inter-satellite interference by exchanging additional signaling messages jointly learned through the MADRL training process. Simulations demonstrate that Ce2RACH achieves up to 36.65% higher network throughput compared to eRACH, while the cost of signaling messages increase linearly with the number of users.

A Scalable and Generalizable Pathloss Map Prediction

Large-scale channel prediction, i.e., estimation of the pathloss from geographical/morphological/building maps, is an essential component of wireless network planning. Ray tracing (RT)-based methods have been widely used for many years, but they require significant computational effort that may become prohibitive with the increased network densification and/or use of higher frequencies in B5G/6G systems. In this paper, we propose a data-driven, model-free pathloss map prediction (PMP) method, called PMNet. PMNet uses a supervised learning approach: it is trained on a limited amount of RT (or channel measurement) data and map data. Once trained, PMNet can predict pathloss over location with high accuracy (an RMSE level of $10^{-2}$) in a few milliseconds. We further extend PMNet by employing transfer learning (TL). TL allows PMNet to learn a new network scenario quickly (x5.6 faster training) and efficiently (using x4.5 less data) by transferring knowledge from a pre-trained model, while retaining accuracy. Our results demonstrate that PMNet is a scalable and generalizable ML-based PMP method, showing its potential to be used in several network optimization applications.

Handover Protocol Learning for LEO Satellite Networks: Access Delay and Collision Minimization

This study presents a novel deep reinforcement learning (DRL)-based handover (HO) protocol, called DHO, specifically designed to address the persistent challenge of long propagation delays in low-Earth orbit (LEO) satellite networks' HO procedures. DHO skips the Measurement Report (MR) in the HO procedure by leveraging its predictive capabilities after being trained with a pre-determined LEO satellite orbital pattern. This simplification eliminates the propagation delay incurred during the MR phase, while still providing effective HO decisions. The proposed DHO outperforms the legacy HO protocol across diverse network conditions in terms of access delay, collision rate, and handover success rate, demonstrating the practical applicability of DHO in real-world networks. Furthermore, the study examines the trade-off between access delay and collision rate and also evaluates the training performance and convergence of DHO using various DRL algorithms.

Simple and Effective Augmentation Methods for CSI Based Indoor Localization

Indoor localization is a challenging task. There is no robust and almost-universal approach, in contrast to outdoor environments where GPS is dominant. Recently, machine learning (ML) has emerged as the most promising approach for achieving accurate indoor localization, yet its main challenge is the requirement for large datasets to train the neural networks. The data collection procedure is costly and laborious as the procedure requires extensive measurements and labeling processes for different indoor environments. The situation can be improved by Data Augmentation (DA), which is a general framework to enlarge the datasets for ML, making ML systems more robust and increases their generalization capabilities. In this paper, we propose two simple yet surprisingly effective DA algorithms for channel state information (CSI) based indoor localization motivated by physical considerations. We show that the required number of measurements for a given accuracy requirement may be decreased by an order of magnitude. Specifically, we demonstrate the algorithms' effectiveness by experiments conducted with a measured indoor WiFi measurement dataset: as little as 10% of the original dataset size is enough to get the same performance of the original dataset. We also showed that, if we further augment the dataset with proposed techniques we get better test accuracy more than three-fold.

PMNet: Robust Pathloss Map Prediction via Supervised Learning

Pathloss prediction is an essential component of wireless network planning. While ray-tracing based methods have been successfully used for many years, they require significant computational effort that may become prohibitive with the increased network densification and/or use of higher frequencies in 5G/B5G (beyond 5 G) systems. In this paper, we propose and evaluate a data-driven and model-free pathloss prediction method, dubbed PMNet. This method uses a supervised learning approach: training a neural network (NN) with a limited amount of ray tracing (or channel measurement) data and map data and then predicting the pathloss over location with no ray tracing data with a high level of accuracy. Our proposed pathloss map prediction-oriented NN architecture, which is empowered by state-of-the-art computer vision techniques, outperforms other architectures that have been previously proposed (e.g., UNet, RadioUNet) in terms of accuracy while showing generalization capability. Moreover, PMNet trained on a 4-fold smaller dataset surpasses the other baselines (trained on a 4-fold larger dataset), corroborating the potential of PMNet.

Seq2Seq-SC: End-to-End Semantic Communication Systems with Pre-trained Language Model

While semantic communication is expected to bring unprecedented communication efficiency in comparison to classical communication, many challenges must be resolved to realize its potential. In this work, we provide a realistic semantic network dubbed seq2seq-SC, which is compatible to 5G NR and can work with generalized text dataset utilizing pre-trained language model. We also utilize a performance metric (SBERT) which can accurately measure semantic similarity and show that seq2seq-SC achieves superior performance while extracting semantically meaningful information.

Learning Emergent Random Access Protocol for LEO Satellite Networks

A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems. LEO SAT networks exhibit extremely long link distances of many users under time-varying SAT network topology. This makes existing multiple access protocols, such as random access channel (RACH) based cellular protocol designed for fixed terrestrial network topology, ill-suited. To overcome this issue, in this paper, we propose a novel grant-free random access solution for LEO SAT networks, dubbed emergent random access channel protocol (eRACH). In stark contrast to existing model-based and standardized protocols, eRACH is a model-free approach that emerges through interaction with the non-stationary network environment, using multi-agent deep reinforcement learning (MADRL). Furthermore, by exploiting known SAT orbiting patterns, eRACH does not require central coordination or additional communication across users, while training convergence is stabilized through the regular orbiting patterns. Compared to RACH, we show from various simulations that our proposed eRACH yields 54.6% higher average network throughput with around two times lower average access delay while achieving 0.989 Jain's fairness index.

Joint Association and Resource Allocation for Multi-Hop Integrated Access and Backhaul (IAB) Network

Integrated access and backhaul (IAB) network is envisioned as a novel network architecture for increasing the network capacity and coverage. To facilitate the IAB network, the appropriate methods of wireless link association and resource management are required. In this paper, we investigate the joint optimization problem of association and resource allocation in terms of subchannel and power for IAB network. In particular, we handle the association and resource allocation problems for wireless backhaul and access links considering multi-hop backhauling. Since the optimization problem for IAB network is formulated as a mixed integer non-linear programming (MINLP), we divide it into three subproblems for association, subchannel allocation, and power allocation, respectively, and these subproblems are solved alternatively to obtain a local optimal solution. For the association problem, we adopt the Lagrangian duality approach to configure the backhaul and access links and successive convex approximation (SCA) approach is used to solve the subchannel and power allocation problems efficiently. Simulation results demonstrate that the proposed algorithm achieves better performance than single-hop backhauling based network and enhances the capacity and coverage by configuring the multi-hop backhauling.

Integrating LEO Satellites and Multi-UAV Reinforcement Learning for Hybrid FSO/RF Non-Terrestrial Networks

A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) and burgeoning unmanned aerial vehicles (UAVs) are promising enablers for high-speed and long-distance communications in beyond fifth-generation (5G) systems. Integrating SATs and UAVs within a non-terrestrial network (NTN), in this article we investigate the problem of forwarding packets between two faraway ground terminals through SAT and UAV relays using either millimeter-wave (mmWave) radio-frequency (RF) or free-space optical (FSO) link. Towards maximizing the communication efficiency, the real-time associations with orbiting SATs and the moving trajectories of UAVs should be optimized with suitable FSO/RF links, which is challenging due to the time-varying network topology and a huge number of possible control actions. To overcome the difficulty, we lift this problem to multi-agent deep reinforcement learning (MARL) with a novel action dimensionality reduction technique. Simulation results corroborate that our proposed SAT-UAV integrated scheme achieves 1.99x higher end-to-end sum throughput compared to a benchmark scheme with fixed ground relays. While improving the throughput, our proposed scheme also aims to reduce the UAV control energy, yielding 2.25x higher energy efficiency than a baseline method only maximizing the throughput. Lastly, thanks to utilizing hybrid FSO/RF links, the proposed scheme achieves up to 62.56x higher peak throughput and 21.09x higher worst-case throughput than the cases utilizing either RF or FSO links, highlighting the importance of co-designing SAT-UAV associations, UAV trajectories, and hybrid FSO/RF links in beyond-5G NTNs.