Research on Community PCI Planning Based on Multi Model Simulated Annealing Algorithm

PCI planning is crucial for ensuring the normal operation and user experience of mobile communication networks. By avoiding PCI conflicts, confusion, and PCI mode 3 interference, as well as properly configuring PCI resources, signal interference can be effectively reduced, network performance can be improved, and user experience can be improved. This paper is based on the background of this problem, using Python programming to construct random forests, LightGBM, and multiple regression models to explore the relationship between PCI and MR numbers. Then, simulated annealing algorithm is used to optimize this relationship and obtain the optimal PCI configuration for the cell that meets the problem. We conducted sensitivity analysis on the model and controlled variable analysis on the population size and cooling rate of the simulated annealing algorithm. The final conclusion is that the model results are reliable and highly credible.