The rapid advancement in large foundation models is propelling the paradigm shifts across various industries. One significant change is that agents, instead of traditional machines or humans, will be the primary participants in the future production process, which consequently requires a novel AI-native communication system tailored for agent communications. Integrating the ability of large language models (LLMs) with task-oriented semantic communication is a potential approach. However, the output of existing LLM is human language, which is highly constrained and sub-optimal for agent-type communication. In this paper, we innovatively propose a task-oriented agent communication system. Specifically, we leverage the original LLM to learn a specialized machine language represented by token embeddings. Simultaneously, a multi-modal LLM is trained to comprehend the application task and to extract essential implicit information from multi-modal inputs, subsequently expressing it using machine language tokens. This representation is significantly more efficient for transmission over the air interface. Furthermore, to reduce transmission overhead, we introduce a joint token and channel coding (JTCC) scheme that compresses the token sequence by exploiting its sparsity while enhancing robustness against channel noise. Extensive experiments demonstrate that our approach reduces transmission overhead for downstream tasks while enhancing accuracy relative to the SOTA methods.

CSI compression, which serves as the first-tire use case for AI/ML applications in 3GPP, has gained widespread attention. The 3GPP-defined Type-3 training with CSI encoder and decoder sequentially trained in different sessions has been accorded a prioritized option due to its exceptional capacity for preserving intellectual property. However, current framework incorporating strong constraints on the latent feature, compromises the principle of separate training. In addition, in the context of a single UE served by multiple NW vendors, the adoption of a unified UE encoder accommodating multiple NW vendors is compelling from complexity perspective, yet remains unexplored. This paper proposes a novel separate training framework followed by a UE-side model training scheme, which leverages the vector quantizer (VQ) with a vendor-proprietary codebook to conceal the interpretation between disclosed codewords and latent representations. We further extend this scheme to encompass multi-NW-vendor scenarios, which enables a unified encoder compatible with multiple NW decoders. Simulation results on the system level simulation dataset and real-world over-the-air dataset demonstrate that sequentially trained encoder-decoder can cooperate seamlessly with negligible performance degradation compared to the Type-1 encoder-decoder joint training. Furthermore, the proposed scheme remains insensitive to changes in the number of NW vendors and codebook variations.

The deep learning (DL)-based channel state information (CSI) feedback methods have been intensively explored in recent years. Most existing works are trained offline based on the prestored datasets. However, in real-world deployment, the pretrained model may not fit the field environment due to the wireless environment changes. In a previous study, a supervised learning approach has been introduced to deal with this CSI feedback transferability problem by finetuning the model. Nevertheless, the transmission for the original uncompressed CSI data will cause intense traffic in air interface. In this paper, a novel unsupervised transfer learning framework named Discrepancy-based Domain Adaptation Network (DDA-Net) is proposed to solve this problem. By minimizing the discrepancy between the CSI codeword datasets from the pretrained environment and field environment, the encoder and decoder are finetuned to extract the common features in both environments, so that the DL-based CSI feedback model can also work properly in a drifted environment without transmitting any original uncompressed CSI data. Simulation results show that the DDA approach can augment CSI feedback reconstruction accuracy and combat overfitting problems in the deployment environment. Compared to the existing supervised learning approach, the DDA approach can achieve similar CSI recovery performance without transmitting the original uncompressed CSI data, reducing considerable transmission traffic.

Vehicle-to-infrastructure (V2I) communication enables vehicles to acquire surrounding traffic information in real time, which significantly improves the driving safety and comfort. The cable-connected roadside unit (c-RSU) with high communication capability and large communication range plays an indispensable role in V2I communication. Meanwhile, unmanned aerial vehicle (UAV) technology has developed rapidly. In terms of its unique mobility and flexibility, the UAV-assisted RSU (u-RSU) can dynamically adjust its position according to the traffic density and emergencies. So the u-RSU can be a reliable supplement to the ground RSU in V2I communication. In this paper, a combined c-RSU and u-RSU deployment strategy is proposed to achieve the maximal effective traffic coverage ratio (ETCR) under a given tough budget bound. To solve this problem, we introduce a two layer improved greedy algorithm (TLIGA). Within TLIGA, the first layer greedy algorithm embedded with the improved Kruskal algorithm is used to deploy c-RSUs and cable, while the second layer improved greedy algorithm is used to determine the optimal number of u-RSUs and their flight strategy. Simulation results show that compared with the existing methods the proposed algorithm TLIGA can significantly increase ETCR.

Recently, many researches based on millimeter wave (mmWave) together with analog beamforming technology have been done to provide higher transmission throughput in vehicle-to-everything (V2X) communication. While hybrid beamforming technology, which can generate multi radio frequency (RF) chains with reduced hardware complexity, continues attracting attention. Hence, this paper focuses on a hybrid-beamforming-based roadside unit (RSU) beam resource scheduling problem in vehicle-to-infrastructure (V2I) communication and intends to improve transmission fairness. Then, this paper proposes an indicator Q to evaluate transmission fairness. Furthermore, a Power-allocated-based Beam resource Scheduling strategy (PBS) and a Time-allocated-based Beam resource Scheduling strategy (TBS) are designed for the multi-RF-chain based V2I communication to enhance transmission fairness. Simulation results prove that, the two proposed beam resource scheduling strategies can effectively improve the transmission fairness in V2I communication.

Vehicle-to-infrastructure (V2I) communication enables vehicles to acquire surrounding traffic information in real time, which significantly improves the driving safety and comfort. The roadside unit (RSU) which transfers information among vehicles plays an indispensable role in V2I communication. For a long time, researchers have been focusing on choosing proper RSU deployment locations to deploy fixed RSUs. Meanwhile, unmanned aerial vehicle (UAV) technology has developed rapidly. In terms of its unique mobility and flexibility, the UAV-assisted RSU (u-RSU) is able to cover a larger area. If the flight trajectory is designed properly, fewer u-RSUs can solve the RSU deployment problem and ensure the network performance. Therefore, the large-scale u-RSU collaborative trajectories design problem is investigated in this paper. We propose a u-RSU flight trajectory strategy and solve the problem in three steps. An improved greedy algorithm and an ant colony optimization (ACO) algorithm are used in the solution. Under different conditions, the proposed u-RSU flight strategy is analyzed and compared with other deployment strategies. Simulation results show that our strategy always has better network performance and deploys fewer u-RSUs. Thus, the proposed strategy is more economical and effective compared with the traditional deployment strategy.

In this paper, a layered-division multiplexing (LDM) based non-orthogonal transmission framework is proposed to enhance the spectral efficiency of Multicast- Broadcast Single Frequency Network (MBSFN). In this framework, different ranges of MBSFN areas are incorporated into a two-layer LDM system, one layer is for small scale local services, the other layer is for large scale global service. To optimize the proposed transmission framework, we design a cooperative beamforming scheme and abstract it as a max-min fair (MMF) problem. We transform the problem into the difference of convex (DC) structure and design a concave-convex procedure (CCCP) based algorithm to find a local optimal of the problem. In addition, performance upper bounds and baselines are formed through semidefinite relaxation (SDR). The results show that the proposed CCCP-based algorithm performs close to upper bounds and better than the SDR-based approach. And this LDM-based non-orthogonal transmission framework also acquires better spectral efficiency than the orthogonal transmission frameworks.

Recently, sharing perception sensor information among vehicles sets a higher transmission demand for vehicular communication. Facing the challenges, millimeter wave (mmWave) has the potential to realize multi-Gbps throughput transmissions. However, in conventional methods, beam sweeping is utilized in beam alignment, which is inefficient in high mobility scenarios. To overcome the drawback, this paper introduces vehicular position information into beam alignment in vehicle-to-vehicle (V2V) communication. Considering localization errors, in order to avoid beam misalignment, two beamwidth optimization methods are proposed to maximize the average throughput among the nearby region of receiver's estimated position. Simulation results suggest that the proposed schemes provide appreciable performance improvements as compared to the traditional beam sweeping scheme.

In order to achieve high-quality entertainment services and large-capacity sensor sharing, it is imperative to improve the throughput of V2I communication systems. Millimeter wave communication is a promising technology, which is generally combined with beamforming techniques. When it comes to beam design, we need to focus on the tradeoff between system throughput and alignment overhead. However, conventional optimization schemes are limited by uniform beamwidth design. Considering the characteristics of V2I communication on the highway, this paper proposes a non-uniform beamwidth design idea. Firstly, an average throughput model based on beam training is established. Then, a recursive algorithm is used to achieve non-uniform beamwidth optimization. Finally, the simulation results prove that the non-uniform beamwidth scheme can significantly improve the throughput of the V2I system.

In vehicular network, high reliability and low latency of communication ensure the driving safety. In order to avoid traffic accidents, it is important to warn surrounding vehicles before a potential traffic accident occurs as soon as possible. In the case of short spectrum resource, a reasonable resource allocation for alarm information is critical in V2V (Vehicle to Vehicle) communication. In this paper, a modified scheme is introduced by taking account of vehicle's priority level and spectrum availability to allocate the frequency resources to upcoming cars. The connection among priority level vehicles will be ensured and channel congestion caused by the surrounding vehicles will be drastically reduced while spectrum resources are insufficient. Simulation results show that the combinative use of sharing vehicle level and available spectrum resource improves the efficiency of spectrum resources, shortens the access-time of alarm information on the premise of successful communication, and improves the safety of vehicle driving.