Federated multi-task learning (FMTL) is a promising edge learning framework to fit the data with non-independent and non-identical distribution (non-i.i.d.) by leveraging the statistical correlations among the personalized models. For many practical applications in wireless communications, the sensory data are not only heterogeneous but also non-stationary due to the mobility of terminals and the randomness of link connections. The non-stationary heterogeneous data may lead to model divergence and staleness in the training stage and poor test accuracy in the inference stage. In this paper, we shall develop an adaptive FMTL framework, which works well with non-stationary data. We further propose to optimize the model updating and cluster splitting schemes in the training stage to accelerate model convergence. We also design a low-complexity model selection and pruning schemes in both the training and inference stages to select the best model for fitting the current data and delete redundant models, respectively. The proposed framework is validated in the edge learning model, namely, the linear regression problem for indoor localization in wireless networks and GNN for wireless power control problems. Numerical results demonstrate that the proposed framework can accelerate the model training convergence and reduce the computation complexity while ensuring model accuracy.

Integrated sensing and communication (ISAC) is believed to play a vital role for connected intelligence in 6G. Radio waves can be used to sense surrounding and obtain the environment information. Furthermore, the environmental knowledge provided by sensing improves the accuracy of channel estimation, resulting in better communication throughput. This paper provides a study of sensing assisted environment reconstruction and communication in ISAC scenario. We propose a multi transmission reception points (TRP) sensing architecture based on scatter polygon assumption to improve environment sensing accuracy. Then a polygon trace scheme is introduced to reconstruct communication channel hinging on sensing reconstructed environment. Cm-level sensing accuracy and ns-level communication channel reconstruction can be achieved by 140 GHz indoor measurement campaign validation.

Existing deep learning-enabled semantic communication systems often rely on shared background knowledge between the transmitter and receiver that includes empirical data and their associated semantic information. In practice, the semantic information is defined by the pragmatic task of the receiver and cannot be known to the transmitter. The actual observable data at the transmitter can also have non-identical distribution with the empirical data in the shared background knowledge library. To address these practical issues, this paper proposes a new neural network-based semantic communication system for image transmission, where the task is unaware at the transmitter and the data environment is dynamic. The system consists of two main parts, namely the semantic coding (SC) network and the data adaptation (DA) network. The SC network learns how to extract and transmit the semantic information using a receiver-leading training process. By using the domain adaptation technique from transfer learning, the DA network learns how to convert the data observed into a similar form of the empirical data that the SC network can process without re-training. Numerical experiments show that the proposed method can be adaptive to observable datasets while keeping high performance in terms of both data recovery and task execution.

Federated multi-task learning (FMTL) is a promising edge learning framework to fit the data with non-independent and non-identical distribution (non-i.i.d.) by exploiting the correlations of personalized models. In many practical systems, the sensory data distribution in wireless systems is not only heterogeneous but also non-stationary due to the mobility of terminals and the randomness of link connections. The non-stationary heterogeneous data may lead to model divergence and staleness in the training stage and poor accuracy in the inference stage. In this paper, we design an adaptive FMTL framework, which can work in a non-stationary environment. We propose to optimize the model update scheme and cluster splitting scheme in the training stage to accelerate model convergencse when the training data are non-stationary. We further design a low-complexity model selection scheme in both the training and the inference stages to choose the best model for fitting the current data. The proposed framework is validated in two scenarios, linear regression and graph neural network (GNN)-based power control in wireless device-to-device (D2D) networks. Both sets of numerical results demonstrate that the proposed framework can accelerate the model training convergence and reduce the computation complexity while ensuring model accuracy.

In mobile social networks (MSNs), mobile users communicate with each other via mobile devices, such as smartphones and tablets, transmitting data through intermittent connections. Mobile users have high mobility, which creates higher requirements for efficient data forwarding in MSNs. Therefore, forwarding data efficiently and quickly becomes a key problem. To tackle this problem, this article proposes a routing method based on a dynamic transient social community (DTSC) to optimize the routing and forwarding performance in MSNs. In this process, combined with the duration of intensive contact between nodes and the social relations of mobile users, the similarity of each pair of contact nodes is calculated, and community detection is carried out. Then, by analyzing the emergence mode of the DTSC, the measurement value and corresponding routing algorithm of the community’s ability to deliver messages are designed. Our algorithm fully considers the duration of the node’s direct encounter and the social connection of the indirect contact to ensure that the node can deliver successfully in a short time. The experimental results show that the DTSC has an excellent performance in data forwarding.

Inter-cell interference management is an notorious issue in cellular communication. Traditionally, static techniques were used to manage the interference: frequency reuse for GSM or universal reuse for CDMA. More recently, fractional frequency reuse for LTE has been common. Based on this idea, the next set of ideas consider coordination among base stations to dynamically manage the interference among the cells. Typically this is done in the context of OFDM systems (LTE), and in particular distributed antenna system (DAS) for LTE (coordinated beamforming). In this paper, the implications of this approach in CDMA systems (example: HSPA+) are discussed. The key idea is that it is not just important to reduce total inter-cell interference, but also the dimension (measured in chips over a spreading sequence length - 16 chips in HSPA) over which the interference is caused. This leads to novel interference management techniques that are specific to CDMA technology, which we term dynamic fractional signature sequence reuse (DFSSR).

Space-frequency block codes (SFBC) combined with frequency switched transmit diversity (FSTD) is used in the downlink of 3GPP LTE system, where all transmit antennas are collocated at eNodeBs. However, all transmit antennas serving a cell are distributed at the cell edge in edge-excited distributed antenna systems. The performance of SFBC is greatly affected by the different large scale fading from different remote antenna units. In this paper, we investigate the tradeoff between the coding gain and average receive SNR of SFBC in DAS layout and propose to set apart the two antennas of SFBC transmission as far as possible. The optimal antenna pairing schemes in the edge-excited DAS cells compatible with 3GPP LTE system are those with the maximized average distance of SFBC transmission. According to the system level simulations in multicell environment, the 5% outage spectrum efficiency and average throughput per cell of SFBC transmission are improved by as much as 21.8% and 11.6% respectively in DAS3 cells,compared with those in LTE system. The DAS6 cells achieve even high gains in outage spectrum efficiency by 123.6% and average throughput per cell by 22.5%.

Multiuser diversity is achieved by maximum C/I scheduler in both fast and slow fading scenarios. However, fairness among multiple users is not guaranteed in slow fading channel because time and frequency resource are always occupied by the user with largest signal to interference and noise ratio(SINR). Opportunistic beamforming using dumb antennas is a multiple antennas transmit technique to increase the fluctuation rate and dynamic range of effective channel coefficients in slow fading environment. In this paper, we propose a method to improve the fairness of maximum C/I scheduler with the technique of dumb antennas. The theoretical analysis of users' scheduling probability shows that the fairness of maximum C/I scheduler can be greatly improved by dumb antennas in slow fading channels without significant loss in cell spectrum efficiency. The engineering issues of its application in the downlink transmission of 3GPP LTE system are discussed. The numerical results of simulation with practical LTE configurations and assumptions also verify our proposal.