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.