With the development of the scale of mobile communication technology, the scale of operation and the bandwidth of communication are getting larger and larger, but the coverage of base stations is getting smaller and smaller. In order to minimize the cost of establishing base stations while covering a large amount of services, this paper uses objective planning and establishes a mathematical model to solve the optimal establishment method of base station siting. At the same time, the weak coverage points are clustered so that the weak coverage points can be managed among themselves effectively. Therefore, the improved simulated annealing algorithm is used to solve the problem. Firstly, the original data is pre-processed and the service volume of weak coverage points is sorted from largest to smallest, and the accumulated service volume of the first 35917 weak coverage points has reached 90% of the total service volume. In other words, it can be considered that the base stations are selected from this part of the points, and finally the optimal solution is obtained, when 90% of the total service volume is reached, the lowest accumulated cost of building base stations is 5705, and the coordinates of all new base stations and the type of base stations built are derived from this.

Jie Zhang, Yanzhuo Lai, Ying Yang, Mingchun Wang. Design of station site selection for communication networks based on simulated annealing algorithm. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 9: 39-44. https://doi.org/10.25236/AJCIS.2022.050907.

[1] Ruan Xiaogang, Wu Xuan. Skinnerian automata: A psychological model for forming operant conditioning theory [J]. Chinese Science: Technical Science, 2013, 43(12): 1374-1390

[2] Chen, X.Y., Xiao, W. & Quan, H.Y… (2008). A hybrid ant algorithm for applying LK algorithm to solve the travel quotient problem. Computer Engineering (04), 228-230.

[3] Liang, G. H., Zhang, S., Huang, F., and He, S. L. An improved simulated annealing algorithm for solving the 0-1 backpack problem [J]. Journal of Guangxi University for Nationalities (Natural Science Edition), 2007(03): 91-93.

[4] Lv Xueqin, Chen Shuguo, Lin Jing. Adaptive genetic annealing algorithm for solving the 0/1 backpack problem [J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2013, 25(01): 138-142.

[5] Jin Huimin, Ma Liang. Application of genetic annealing evolutionary algorithm to the backpack problem [J]. Journal of Shanghai University of Technology, 2004(06): 561-564.