Specific emitter identification (SEI) based on radio frequency fingerprinting (RFF) is a physical layer authentication method in the field of wireless network security. RFFs are unique features embedded in the electromagnetic waves, which come from the hard imperfections in the wireless devices. Deep learning has been applied to many SEI tasks due to its powerful feature extraction capabilities. However, the success of most methods hinges on massive and labeled samples, and few methods focus on a realistic scenario, where few samples are available and labeled. In this paper, to overcome data limitations, we propose a few-shot SEI (FS-SEI) method based on self-supervised learning and adversarial augmentation (SA2SEI). Specifically, to overcome the limitation of label dependence for auxiliary dataset, a novelty adversarial augmentation (Adv-Aug)-powered self-supervised learning is designed to pre-train a RFF extractor using unlabeled auxiliary dataset. Subsequently, to overcome the limitation of sample dependence, knowledge transfer is introduced to fine-tune the extractor and a classifier with target dataset including few samples (5-30 samples per emitter in this paper) and corresponding labels. In addition, auxiliary dataset and target dataset are come from different emitters. An open-source large-scale real-world automatic-dependent surveillance-broadcast (ADS-B) dataset and a Wi-Fi dataset are used to evaluate the proposed SA2SEI method. The simulation results show that the proposed method can extract more discriminative RFF features and obtain higher identification performance in the FS-SEI. Specifically, when there are only 5 samples per Wi-Fi device, it can achieve $83.40\%$ identification accuracy, in which $38.63\%$ identification accuracy improvement comes from the Adv-Aug of pre-training process. The codes are available at https://github.com/LIUC-000/SA2SEI .

Automatic modulation recognition (AMR) technique plays an important role in the identification of modulation types of unknown signal of integrated sensing and communication (ISAC) systems. Deep neural network (DNN) based AMR is considered as a promising method. Considering the complexity of a typical ISAC system, devising the DNN manually with limited knowledge of its various classifications will be very tasking. This paper proposes a neural architecture search (NAS) based AMR method to automatically adjust the structure and parameters of DNN and find the optimal structure under the combination of training and constraints. The proposed NAS-AMR method will improve the flexibility of model search and overcome the difficulty of gradient propagation caused by the non-differentiable quantization function in the process of back propagation. Simulation results are provided to confirm that the proposed NAS-AMR method can identify the modulation types in various ISAC electromagnetic environments. Furthermore, compared with other fixed structure networks, our proposed method delivers the highest recognition accuracy, under the condition of low parameters and floating-point operations (FLOPs).

The communication between vehicle-to-vehicle (V2V) with high frequency, group sending, group receiving and periodic lead to serious collision of wireless resources and limited system capacity, and the rapid channel changes in high mobility vehicular environments preclude the possibility of collecting accurate instantaneous channel state information at the base station for centralized resource management. In addition, road and traffic safety have very strict requirements for low-latency, high-reliability communication, and information transmission is only valuable within a certain range, and requires timeliness. For the Internet of Vehicles (IoV), it is a fundamental challenge to achieve low latency and high reliability communication for real-time data interaction over short distances in a complex wireless propagation environment, as well as to attenuate and avoid inter-vehicle interference through a reasonable spectrum allocation. To solve the above problems, this paper proposes a resource allocation (RA) method using dueling double deep-Q network reinforcement learning (RL) with low-latitude fingerprints and soft-update architecture (D3QN-LS) while constructing a multi-agent model based on a Manhattan grid layout urban virtual environment, with communication links between V2V links acting as agents to reuse vehicle-to-infrastructure (V2I) spectrum resources. These agents work in concert, interact with the environment, receive appropriate observations, rewards, and ultimately learn to improve power and spectrum allocation to provide a better entertainment experience and safer driving environment for users. We also address the shortcomings in existing literature studies. Firstly, the low upper limit of transmitted data volume; Secondly, the artificial assumption that the spectrum is consistent with the number of V2V links, which is insufficient for future applications in spectrum shortage sections. We accordingly extend the amount of transmitted data while adding a scenario where the spectrum resources are relatively short, i.e., the number of V2V links is significantly larger than the amount of spectrum. Experimental results show that with proper training mechanism and reward function construction, multiple intelligence can cooperate effectively. Therefore, the total link capacity of the V2I link and the success rate of periodic security information transmission are further improved.

Federated learning (FL) is promising in enabling large-scale model training by massive devices without exposing their local datasets. However, due to limited wireless resources, traditional cloud-based FL system suffers from the bottleneck of communication overhead in core network. Fueled by this issue, we consider a hierarchical FL system and formulate a joint problem of edge aggregation interval control and resource allocation to minimize the weighted sum of training loss and training latency. To quantify the learning performance, an upper bound of the average global gradient deviation, in terms of the edge aggregation interval, the training latency, and the number of successfully participating devices, is derived. Then an alternative problem is formulated, which can be decoupled into an edge aggregation interval control problem and a resource allocation problem, and solved by an iterative optimization algorithm. Specifically, given the resource allocation strategy, a relaxation and rounding method is proposed to optimize the edge aggregation interval. The problem of resource allocation including training time allocation and bandwidth allocation is solved separately based on the convex optimization theory. Simulation results show that the proposed algorithm, compared to the benchmarks, can achieve higher learning performance with lower training latency, and is capable of adaptively adjusting the edge aggregation interval and the resource allocation strategy according to the training process.

Integrating reconfigurable intelligent surface (RIS) into cell-free massive multiple-input multiple-output (MIMO) is a promising approach to enhance the coverage quality, spectral efficiency (SE), and energy efficiency. In this paper, an RIS-assisted cell-free massive MIMO downlink system suffering from the transceiver hardware impairments (T-HWIs) is investigated. To improve the accuracy of the direct estimation (DE) scheme, a modified ON/OFF estimation (MOE) with moderate pilot overhead is proposed. Relying on the knowledge of imperfect channel state information, we derive closed-form expressions of the lower-bound achievable SE with T-HWIs under both DE and MOE schemes. The closed-form results facilitate the investigation of how RIS improves the downlink SE under various system settings and allow us to explore the trade-off strategies between using more hardware-impaired APs and low-cost RISs in terms of the downlink SE and power consumption. Numerical results validate the theoretical analysis and show that the proposed MOE scheme outperforms the DE scheme in terms of the downlink SE. Moreover, the benefits of introducing RIS into hardware-impaired cell-free massive MIMO systems are also illustrated.

While 5G is being deployed all around the world, the industry and academia start the investigation of 6G. Network function virtualization (NFV) is seen as the key enabler towards the flexible resource management and sharing of 6G networks. The main idea of NFV is to decouple the physical devices from the specific functions that run on them. In NFV, virtual network service (NS) is modeled as a service function chain (SFC). The challenges in SFC description, composition, embedding, and scheduling are key issues in NFV. In this paper, we focus on the joint SFC embedding and scheduling for NFV in 6G networks. With the assistance of sensing the physical node resource abilities, we propose a novel SFC embedding and scheduling algorithm, which is named as RA-SFC-6G. A new service is first composed as an SFC which is an ordered sequence of virtual network functions (VNFs). Afterwards, our RA-SFC-6G algorithm will select the physical nodes with stronger resource abilities and abundant resources to accommodate the SFC. In addition, the NS is guaranteed to be implemented without violating the NS maximum allowed scheduling time. If violated, our RA-SFC-6G can re-embed and re-schedule the violated VNFs to suitable positions. In order to validate our RA-SFC-6G performance, we do the experiment work. Experiment results show that our RA-SFC-6G achieves at least 10% higher SFC acceptance ratio than the previous counterparts and the typical heuristics.