Base station layout method and device

Abstract

The invention provides a base station layout method and device, and the method comprises the steps: taking the elements of each row of a matrix as the coordinates of a to-be-solved base station in a target positioning space, and carrying out the initialization of a particle swarm, thereby obtaining an original population; obtaining a reverse learning population according to the original population; respectively substituting the original population and the reverse learning population into a fitness function to carry out iterative calculation on the fitness of the base station to obtain the optimal positions of individuals in the original population and the reverse learning population; and taking the determined optimal position as the base station layout of the target positioning space. According to the method, the problem that the algorithm is prone to falling into a local optimal solution can be solved, the precision of the swarm intelligence optimization algorithm for the layout optimization problem can be improved, the layout optimization is carried out on the positioning base station in the mode, better base station layout coordinates can be obtained, and higher positioning precision can be obtained.

Description

technical field [0001] The present invention relates to the technical field of communication base stations, and in particular, to a base station layout method and device. Background technique [0002] For the problem of outdoor positioning base station layout, it can be regarded as an optimal value solution problem. Within a certain layout range, an intelligent optimization algorithm is used to perform global optimization in this area, and a global optimal solution is obtained through constant iteration of the algorithm. [0003] At present, the more commonly used swarm intelligence algorithms such as genetic algorithm, particle swarm algorithm, ant colony algorithm, simulated annealing algorithm, etc. are relatively classic algorithms, and relatively new ones such as salps algorithm, gray wolf algorithm and so on. [0004] The existing swarm intelligence optimization algorithms have their own characteristics. The classic ones, such as the genetic algorithm, have strong opt...

AI Technical Summary

Problems solved by technology

[0004] Existing swarm intelligence optimization algorithms have their own characteristics. The classic genetic algorithm has strong optimization ability and good algorithm robustness, but the algorithm consumes a lot of resources when performing operations such as genetic mutation.

The traditional particle swarm optimization algorithm has strong optimization ability for nonlinear problems, but it is difficult to solve the problem that the algorithm is easy to fall into the local optimal solution, which will affect the final solution accuracy of the algorithm

There are some other swarm intelligence optimization algorithms such as simulated annealing algorithm and genetic algorithm fusion swarm intelligence optimization algorithm, but these algorithms cannot jump out of the local optimal solution

Images