Abstract：Network slicing is crucial for enabling networks to meet the diverse service demands of various verticals. To address the issue of dynamic changes in slice types, a Federated Multi-Agent Reinforcement Learning (F-MALML) algorithm with dualtime scale resource allocation is proposed. At the large time scale, a finite memory learning algorithm allocates resources to each base station. At the small time scale, each base station uses F-MALML to dynamically allocate resources to users. A probabilistic learning mechanism is introduced to adjust the allocation strategy based on previous results and the current network state. Simulation results show that the proposed algorithm achieves significant improvements in slice satisfaction for newly added slices and system spectral efficiency compared to the two benchmark algorithms, while demonstrating better stability.

Abstract：With the widespread application of encrypted communications, traditional malicious traffic detection methods based on content analysis have gradually become ineffective. How to efficiently detect malicious behavior in encrypted traffic has become a research focus in the field of network security. This paper proposes a neural network-based encrypted malicious traffic detection method, which realizes the classification of malicious encrypted traffic through a deep learning model. First, the network traffic is preprocessed and key features are extracted, including packet size distribution, time interval, and protocol type. The features are then mapped into a two-dimensional feature map as the input of the deep learning model. A scalable window self-attention mechanism is designed, and the Transfomer neural network model is used to classify feature maps, achieving efficient detection of malicious traffic.Experimental results show that this method performs well in detection accuracy, recall rate, and model robustness, and provides a feasible solution to the problem of malicious behavior detection in encrypted traffic.

Abstract：The emergence of non-terrestrial networks (NTN) marks a major breakthrough in communication technology. It expands the coverage of terrestrial networks by using satellites and high-altitude platforms, thus providing new solutions for global communications. This paper provides a multi-faceted research of NTN, including the following aspects: Firstly, the basic concepts and importance of NTN are introduced, and the deployment mode, application scenario and working frequency bands of NTN are comprehensively outlined, while different system architectures are described in detail; secondly, the main technical challenges faced by NTN are discussed, and related research results are summarized; finally, the future development of NTN is prospected, and potential technological innovations and development paths are pointed out.

Abstract：To meet the future industry application requirements, the 6G network needs to build a high-performance, highly flexible, and highly reliable network. Starting from the scenarios and requirements of the 6G distributed network, this study designs a 6G distributed network architecture composed of central network nodes and distributed network nodes, and proposes key technologies such as information interaction at the network node granularity, service continuity assurance, network autonomy, and networking coordination. The research results show that this architecture and key technologies can effectively support the diversified services and flexible deployment of the 6G network, providing theoretical support and practical guidance for the development of 6G networks.

Abstract：Autoencoder (AE) based on deep learning is a new method to replace traditional communication transmitter and receiver. This paper proposes an autoencoder based on Convolutional Neural Network (CNN) and Gate Recurrent Unit (GRU), which integrates constellation mapping and channel coding. Specifically, this paper designs a parallel CNN structure and segment the input bitstream for one-hot encoding, which has two advantages:(1) Compared with the original one-hot encoding, the dimension of the input data is reduced; (2) The features of the data are not too sparse, which allows the network to converge faster and better. In addition, the GRU is introduced for channel coding. The proposed model can be applied to high-order modulation such as 4096QAM signal, and has better performance than traditional methods under both added white Gaussian noise (AWGN) channels and Rayleigh channels.

Abstract： NTN (non-terrestrial network) is an important application scenario for satellite communications and low-altitude communications, marking the transition of 5G technology applications from land communications to space communications. It is foreseeable that satellite networks will be an important component of future 6G communications networks. In order to meet the quality requirements of satellite communication and maximize the system capacity, it is necessary to apply adaptive coding and modulation technology to dynamically adjust the modulation order and coding rate according to the channel state information in the changing communication environment. AI has clear potential to solve problems arising from rapidly changing channel conditions in satellite high-dynamic scenarios. This paper adopts the low-orbit satellite adaptive coding and modulation strategy based on reinforcement learning to solve the problem of the mismatch between the threshold table and the actual channel caused by the change of the satellite communication environment, which is improved by above 20% compared with the traditional ARIMA (autoregressive integrated moving average) algorithm.

Abstract： As an important feature and key enabling technology of 6G, integrated sensing and communication (ISAC) achieves information sharing and collaborative gain for communication and awareness. This paper firstly introduces the current research status of ISAC technology, and then combs it from two aspects: academic research and standardization progress. Then, this paper deeply discusses and summarizes the integration design issues of communication technology and sensing technology in three aspects: network architecture, networking and waveform design. Finally, the development trend of ISAC technology in 6G is forecasted and the possible challenges are analyzed.

Abstract：Facing wide-area and non-uniformly distributed service requirements, this paper proposes a beam resource management scheme based on improved particle swarm optimization, which considers the joint optimization of beam hopping pattern design, beam frequency allocation and power allocation, in the scenario of multiple LEO satellites with moving beam cells. By system-level simulation, its performance is verified. Specifically, compared with beam resource management schemes based on spatial isolation angle and priority, results show that this proposal can significantly improve user SINR and system capacity under full-buffer service model, and lower frequency reuse factor results in higher system capacity.