Spectrum is the indispensable resource for 5G wireless systems and beyond. The dynamic spectrum management (DSM) framework with spectrum sharing among different kinds of users is essential to satisfy the sustainable rapid increase of the bandwidth requirement. Based on the analysis of the DSM as well as the latent applications of the machine learning and artificial intelligence (AI) in the spectrum access, this paper will address the problem of incorporating intelligence into the spectrum management. Firstly, the spectrum opportunity (SOP) related information is layered into the spectrum data, the spectrum information and the spectrum knowledge based on the processing and abstractive level. The spectrum knowledge is formally defined as the extendible and scalable information to reason and predict the SOP usability as well as the outcome of the SOP occupancy. Then the smart spectrum model (SSM) is proposed with the spectrum knowledge as the key enabler and the coupled SOP exploration and exploitation as the core feature. Under the SSM framework, the spectrum knowledge and real-time observing (SKRO) enabled SOP exploration scheme is designed, which can make use of both the historical information and the real-time sensing information for smart SOP exploration. Extensive simulations are provided which demonstrate that the SKRO enabled SSM can achieve much better SOP utilization while satisfying the required legacy assurance. Specifically, in the low signal to noise environment, at least 16.55% gains on the SOP utilization ratio can be obtained compared with the DSM.

With the rapid advancement of unmanned aerial vehicle (UAV) technology, its high mobility and ease of deployment have demonstrated tremendous potential in integrated sensing and communication (ISAC) systems. However, as user demands diversify, network architectures become increasingly distributed, and as the number of UAVs grows rapidly, ISAC systems face significant challenges in optimizing communication and sensing resources. In particular, UAV communication in collaborative UAV missions is highly susceptible to hostile signal disruptions, leading to degraded communication quality, weakened sensing performance, resource wastage, and increased energy consumption. To address these challenges, this paper proposes a game-theoretic optimization method for multi-UAV ISAC networks. First, a multi-UAV communication-sensing network model is constructed to characterize the impact of interference sources on communication and sensing performance. Based on this model, under energy constraints, a joint optimization of transmission power and UAV trajectory is performed. The problem is formulated as a utility maximization framework for the ISAC network and modeled as a game-theoretic approach. The proposed model is rigorously proven to be an exact potential game, ensuring the existence of at least one pure-strategy Nash equilibrium. To solve for the equilibrium, a distributed optimization algorithm—the Electric Eel Foraging Optimization (EEFO) algorithm is developed. Simulation results validate the effectiveness of the proposed method, showing that it significantly enhances the communication and sensing performance of multi-UAV networks while effectively reducing energy consumption. This work provides a novel solution to the resource optimization challenges in multi-UAV ISAC networks, offering both theoretical and practical contributions to advance ISAC technology.

Accurate radio environment maps (REMs) can enhance the performance of wireless networks and optimize spectrum utilization efficiency. However, in rugged terrain environments, radio propagation is significantly affected by terrain variations, resulting in spatial heterogeneity in received signal strength (RSS) and impairing the accuracy of REM construction. To address these challenges, a Gaussian Process Regression method incorporating terrain (GPRT) is proposed to exploit both spatial and terrain correlation properties. In GPRT, a specialized kernel function is designed to integrate digital elevation data into the Gaussian process framework, capturing anisotropic spatial correlation and terrain effects. In addition, an Adaptive Moment Estimation (Adam) optimization algorithm is utilized for efficient hyperparameter tuning, enhancing convergence speed and parameter accuracy. Simulations with varying numbers of emitters and field experiments in real-world terrain demonstrate the superiority and effectiveness of the proposed GPRT over competing methods in terms of robustness and accuracy. Specifically, GPRT outperformed the best comparative approaches by 20% to 33% in simulations and by up to 20% in the field experiment.

Spectrum sensing is an important step of Dynamic Spectrum Access (DSA). However, the existing sensing technology are limited by the scarcity of sensing nodes, the narrow sensing range, and the security issues. In this paper, Crowd Sensing (CS) is used to collect sensed data with a large number of mobile devices equipped with sensors to ensure reliability and sensing range. In order to solve single point of failure caused by the vulnerability of the cluster in CS, we used the characteristics of blockchain (i.e. de-centralization and de-trust) to ensure the security and correctness of the spectrum trading process. Specifically, a Blockchain Based Spectrum Sensing (BBSS) system is proposed, in which requester recruit sensing workers to involve in spectrum sensing, sensing workers obtain benefits by participating in spectrum sensing and miner verifies and packages transactions into the blockchain. In particular, the recruitment and sensing worker’s response is modeled as a Reward-Sensing-time game, and the strategy of requester is the total reward R, and the strategy of sensing worker is the sensing time t. We proved that both of them can adopt strategies to maximize their own benefits. Simulation results show that requester benefit increases with the growing number of sensing workers, but the amplification is smaller and smaller. A certain sensing worker who adopted strategy can achieve larger benefit compared with random allocation of sensing time when the number of sensing workers is smaller (less than 500) in the system.

To address the problems of the limited prediction accuracy and poor explainability of the deep learning (DL) ena-bled spectrum prediction models, a spectrum prediction method based on wavelet decomposition explainable long short-term memory (WDE-LSTM) is proposed in this study. Firstly, the historical spectrum data is wavelet decomposed, and the obtained subsequences are predicted by the LSTM model, for which the prediction accuracy can be improved effectively. Secondly, the Shapley additive explanations (SHAP) method is used to identify the influence of each spectrum subsequence on the prediction performance and the weight coefficients are added to the model accordingly to achieve explainable and high-precision prediction. Extensive simulation shows that the proposed method makes DL-enabled spectrum prediction explainable and improves the met-rics of mean absolute percentage error (MAPE) and root mean square error (RMSE) by an average of about 13% and 15%, respectively, compared with the existing methods.