With the development of the Internet, network communication has been applied to various fields, and people seek higher-speed, lower-latency, more reliable, and more stable signals. Communication between base stations and users is transmitted through radio waves, but wireless signals are affected by various factors, inevitably suffer from loss during propagation. In complex environments, traditional base station deployments often fail to meet users’ various signal requirements. To provide stable and efficient network coverage, deploying base station locations in environments with varying signal demands becomes a challenge. Therefore, this paper designs a complex network environment, including factors such as hot points locations, signal demands, and coverage limitations, to identify optimal base station deployment positions. Precisely because the Particle Swarm Optimization (PSO) algorithm has some unavoidable shortcomings, for example, during the movement of the particles, due to insufficient learning experience, they may become trapped in a local optimum, making it difficult to find new feasible solutions, this paper designs a Multi-Sample Learning and Density Compensation Particle Swarm Optimization (MDPSO) algorithm. By incorporating multi-sample learning and density compensation strategies, MDPSO significantly improves base station coverage. Furthermore, in comparative experiments against four other algorithms, MDPSO demonstrated overall superior performance. Experiments were conducted in two scenarios: fixed hot points and illegal areas locations, and random locations. In both scenarios, the MDPSO algorithm enables model’s regional average coverage to exceed 90%, with the highest average coverage rate among all tested algorithms, and the maximum coverage rate surpassing 95%, validating its effectiveness. This study effectively achieves high network coverage and can provide insights and techniques for research related to base station deployment.

Metaheuristic algorithms have garnered much attention among researchers owing to their robustness, adaptability, independence from a predetermined initial solution, and lack of reliance on gradient computations. The flower pollination algorithm (FPA) and the slime mould algorithm (SMA) are efficient methodologies for addressing global optimization challenges. Nonetheless, tackling large-scale global problems using a single algorithm often proves challenging due to inherent limitations in its mechanism. One effective approach to mitigating this limitation is to hybrid the two algorithms employing suitable strategies. We proposed a hybrid algorithm (GFPSMA) based on FPA and SMA. First, to address the global exploration issue of FPA, a method was proposed that utilized the golden section mechanism to enhance information exchange between random individuals and the best individual. Second, to improve the reliability of the random search phase in SMA, an adaptive step-size strategy was introduced. Furthermore, a dual-competition mechanism, inspired by gaming concepts, was introduced to enhance the integration of the two algorithms. Finally, an elite learning method with adjustment conditions was employed to refine the localization of the best individual. To assess the performance advantage of GFPSMA, 39 benchmark functions were employed, comparing GFPSMA with FPA and SMA along with their six variants, six variants of other metaheuristic algorithms, three CEC competition algorithms, totaling 17 algorithms, and strategic algorithms for testing. Experimental results demonstrated the favorable performance advantage of GFPSMA. Additionally, the feasibility and practicality of GFPSMA were demonstrated in four engineering problems.