Unmanned aerial vehicles (UAVs) can serve as air relays to improve communication coverage by optimizing positions. UAV position optimisation is a typical nonlinear, nonconvex problem, and obtaining an analytical solution is difficult. Although swarm intelligence algorithms can effectively deal with such complex problems, they often face the challenges of complex parameter adjustment and a difficult balance between exploration and exploitation. Therefore, this paper proposes a biogeography-based optimization algorithm based on hybrid migration and mutation (BBOHMM). The algorithm dynamically combines migration rates with fitness and iteration times to enhance exploration of high-quality solutions. Meanwhile, the function of Gaussian and uniform mutation is coordinated to accelerate the solution space search in the early stage, while in the later stage, the fine exploitation is carried out around the potential optimal solutions, thereby balancing convergence speed with solution accuracy. Compared with the existing algorithms, the experimental results show that the BBOHMM can deploy UAVs more effectively and achieve a wider coverage. The test in a complex environment further verifies that the algorithm has good stability and real-time performance.

Abstract Accurate signal‐to‐noise ratio (SNR) estimation is critical in wireless communication systems as it directly impacts system performance and the assessment of signal quality. Recent advances in deep learning‐based SNR estimation have significantly improved estimation accuracy in low SNR conditions. This paper presents a novel deep learning approach that uses a power spectrum generated through overlapping segmentation as input to a neural network for SNR estimation. The performance of SNR estimation has been enhanced by integrating an augmented squeeze‐and‐excitation (SE) attention mechanism with a residual block fusion module, employing multiple residual structures, and deepening the network architecture. To validate the efficacy of this method, extensive simulation experiments were conducted under various scenarios, including additive white Gaussian noise (AWGN), Rayleigh, and Rician channel conditions. The results demonstrate that this method outperforms state‐of‐the‐art techniques in high SNR environments and across diverse channel conditions. Furthermore, there is only minimal performance degradation under low signal‐to‐noise ratio conditions.