Network working parameter optimization method based on random gradient descent method

Abstract

The invention provides a network working parameter optimization method based on a random gradient descent method. The stability and the accuracy of a working parameter derivative vector calculation result can be improved. The method comprises the following steps: obtaining a working parameter to be optimized; randomly extracting t sampling points among sampling points; determining an overall coverage ratio of t sampling points in a target area to be optimized according to the obtained working parameter to be optimized, wherein the overall coverage ratio is equal to a mean of the coverage effects of the t sampling points being covered, and the coverage effect of each sampling point being covered is a continuous value between [0, 1]; determining a derivative vector of the working parameter according to the overall coverage ratio of the t sampling points by using a continuous derivation rule; and determining the optimized working parameter according to the determined derivative vector ofthe working parameter. The network working parameter optimization method provided by the invention is suitable for network working parameter optimization operations.

Description

technical field [0001] The invention relates to the field of mobile communication, in particular to a method for optimizing network operating parameters based on a stochastic gradient descent method. Background technique [0002] The existing mobile communication network is dominated by cellular networks. By deploying multiple base stations in the network, these base station equipment are equipped with multiple (directional) antennas to transmit wireless signals in different directions to jointly achieve communication signal coverage in an area. In each base station, it generally includes 3 (there are 2-4 individual cases) radio frequency units and antennas, and each antenna has its own network operating parameters (referred to as industrial parameters), such as: azimuth, downtilt, launch power etc. [0003] Network planning and network optimization are important technical links in mobile communication networks. Network planning usually refers to the rough estimation and l...

AI Technical Summary

Problems solved by technology

[0012] The technical problem to be solved by the present invention is to provide a network working parameter optimization method based on the stochastic gradient descent method to solve the problem that the gradient descent method based on numerical solution in the prior art will lead to unstable calculation results of the derivative vector of the working parameters question

Images