CN-119255265-B - Robust network optimization method, related device and medium

CN119255265BCN 119255265 BCN119255265 BCN 119255265BCN-119255265-B

Abstract

The embodiment of the disclosure provides a robust network optimization method, a related device and a medium. The method comprises the steps of obtaining network sample data of a target network and antenna parameters of cells in the target network, carrying out gradient estimation on a second optimized objective function through a zero-order estimation algorithm based on the network sample data and the antenna parameters to obtain an estimated gradient value, updating the antenna parameters through gradient descent according to the estimated gradient value, respectively calculating a first value of a first optimized objective function and a second value of a second optimized objective function according to the updated antenna parameters, jumping to the step of carrying out gradient estimation on the second optimized objective function through the zero-order estimation algorithm based on the network sample data and the antenna parameters to obtain the estimated gradient value until preset conditions are met to obtain a plurality of first values, and taking the antenna parameter corresponding to the smallest first value in the plurality of first values as the target antenna parameter. The embodiment of the disclosure can improve the efficiency and the robustness of network optimization.

Inventors

ZHANG SHUTAO
XUE YE
SHI QINGJIANG
ZHANG ZONGHUI

Assignees

深圳市大数据研究院

Dates

Publication Date: 20260508
Application Date: 20240912

Claims (8)

1. A method of robust network optimization, the method comprising: acquiring network sample data of a target network and antenna parameters of each cell in the target network, wherein the network sample data comprises spectrum efficiency performance of a first number of grids of the target network at a second number of moments; Performing gradient estimation on a second optimization objective function through a zero-order estimation algorithm based on the network sample data and the antenna parameters to obtain an estimated gradient value, wherein the second optimization objective function is constructed through a second quantile and a network efficiency optimization expectation, the second quantile is used for selecting a grid to be optimized, and the network efficiency optimization expectation is used for representing an optimized mapping relation between the spectrum efficiency performance of the target network and the antenna parameters; Updating the antenna parameters through gradient descent according to the estimated gradient value; According to the updated antenna parameters, respectively calculating a first value of a first optimization objective function and a second value of the second optimization objective function, wherein the first optimization objective function is expected to be constructed through first quantiles and network efficiency optimization, and the first quantiles are used for selecting grids to be optimized; jumping to the network sample data and the antenna parameters, and carrying out gradient estimation on a second optimized objective function through a zero-order estimation algorithm to obtain an estimated gradient value until a preset condition is met so as to obtain a plurality of first values; Taking the antenna parameter corresponding to the smallest first value in the first values as a target antenna parameter; wherein the first optimization objective function is as follows: Wherein, the For the first optimization objective function, For the first quantile estimation function, And Respectively the first Antenna downtilt and horizontal angles of the individual cells, For the set of cells of the target network, Represent the first The first grid is The spectral efficiency performance measured at each instant, L is a first number, S is a second number, For the purpose of the averaging, And Respectively preset adjusting thresholds of the downward inclination angle and the horizontal angle; the second optimization objective function is as follows: Wherein, the For the second optimization objective function, A function is estimated for the second quantile, And Respectively the first Antenna downtilt and horizontal angles of the individual cells, For the set of cells of the target network, Represent the first The first grid is The spectral efficiency performance measured at each instant, L is a first number, S is a second number, For the purpose of the averaging, And The adjustment thresholds of the preset downward inclination angle and the preset horizontal angle are respectively set.
2. The method according to claim 1, wherein the first quantile is obtained by: Acquiring a preset first loss function, wherein the first loss function is a non-smooth function; Constructing a first quantile estimation function according to the first loss function, wherein the first quantile estimation function is used for outputting a first optimization variable which enables mathematical expectations corresponding to the first loss function to be minimum; Inputting the network sample data into the first quantile estimation function to obtain the first optimization variable; and taking the first optimization variable as the first quantile.
3. The method according to claim 2, wherein the second quantile is obtained by: Acquiring a preset second loss function, wherein the second loss function is an upper bound proxy function corresponding to the first loss function; Constructing a second quantile estimation function according to the second loss function, wherein the second quantile estimation function is used for outputting a second optimization variable which enables mathematical expectations corresponding to the second loss function to be minimum; Inputting the network sample data into the first quantile estimation function to obtain the second optimization variable; and taking the second optimization variable as the second quantile.
4. The method according to claim 1, wherein the method further comprises: And determining the spectrum efficiency performance of the target network according to the average value of the spectrum efficiency performance of the first number of grids of the target network at the second number of moments.
5. A robust network optimization apparatus, comprising: A parameter obtaining unit, configured to obtain network sample data of a target network and antenna parameters of cells in the target network, where the network sample data includes spectrum efficiency performance of a first number of grids of the target network at a second number of moments; The gradient estimation unit is used for carrying out gradient estimation on a second optimization objective function through a zero-order estimation algorithm based on the network sample data and the antenna parameters to obtain an estimated gradient value, wherein the second optimization objective function is constructed through a second quantile and a network efficiency optimization expectation, the second quantile is used for selecting a grid needing to be optimized, and the network efficiency optimization expectation is used for representing an optimized mapping relation between the spectrum efficiency performance of the target network and the antenna parameters; the gradient updating unit is used for updating the antenna parameters through gradient descent according to the estimated gradient value; the optimization calculation unit is used for respectively calculating a first value of a first optimization objective function and a second value of a second optimization objective function according to the updated antenna parameters, wherein the first optimization objective function is expected to be constructed through first quantiles and network efficiency optimization, and the first quantiles are used for selecting grids to be optimized; The iterative jump unit is used for jumping to the network sample data and the antenna parameters, and carrying out gradient estimation on the second optimization objective function through a zero-order estimation algorithm to obtain an estimated gradient value until a preset condition is met so as to obtain a plurality of first values; A parameter determining unit, configured to take, as a target antenna parameter, the antenna parameter corresponding to a smallest first value among the plurality of first values; wherein the first optimization objective function is as follows: Wherein, the For the first optimization objective function, For the first quantile estimation function, And Respectively the first Antenna downtilt and horizontal angles of the individual cells, For the set of cells of the target network, Represent the first The first grid is The spectral efficiency performance measured at each instant, L is a first number, S is a second number, For the purpose of the averaging, And Respectively preset adjusting thresholds of the downward inclination angle and the horizontal angle; the second optimization objective function is as follows: Wherein, the For the second optimization objective function, A function is estimated for the second quantile, And Respectively the first Antenna downtilt and horizontal angles of the individual cells, For the set of cells of the target network, Represent the first The first grid is The spectral efficiency performance measured at each instant, L is a first number, S is a second number, For the purpose of the averaging, And The adjustment thresholds of the preset downward inclination angle and the preset horizontal angle are respectively set.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the robust network optimization method according to any of claims 1 to 4 when executing the computer program.
7. A computer readable storage medium having stored thereon computer executable instructions which when executed by a computer implement the robust network optimization method according to any of claims 1 to 4.
8. A computer program product comprising a computer program or computer instructions, characterized in that the computer program or the computer instructions are stored in a computer readable storage medium, from which the computer program or the computer instructions are read by a processor of a computer device, the processor executing the computer program or the computer instructions, causing the computer device to perform the robust network optimization method according to any of claims 1 to 4.

Description

Robust network optimization method, related device and medium Technical Field The present disclosure relates to the field of communications, and in particular, to a robust network optimization method, related apparatus, and medium. Background With the rapid development of fifth generation (5G) wireless cellular communications, network optimization plays a key role in improving 5G network performance. There are a number of adjustable network parameters in 5G networks, such as antenna parameters, beam parameters, transmit power, etc. These network parameters need to be properly adjusted to align with the actual environment to maximize network performance. In the related art, by constructing a model of a real world wireless network, then performing analog simulation and optimizing network parameters based on the constructed model, such as a digital twin network. However, the current network optimization algorithm does not fully utilize the randomness of the antenna network, and has poor robustness. How to improve the efficiency and robustness of network optimization is a problem to be discussed currently. Disclosure of Invention The embodiment of the disclosure provides a robust network optimization method, a related device and a medium, aiming at improving the efficiency and the robustness of network optimization. In a first aspect, embodiments of the present disclosure provide a robust network optimization method, the method comprising: acquiring network sample data of a target network and antenna parameters of each cell in the target network, wherein the network sample data comprises spectrum efficiency performance of a first number of grids of the target network at a second number of moments; Performing gradient estimation on a second optimization objective function through a zero-order estimation algorithm based on the network sample data and the antenna parameters to obtain an estimated gradient value, wherein the first optimization objective function is constructed through a first quantile and a network efficiency optimization expectation, the first quantile is used for selecting a grid to be optimized, and the network efficiency optimization expectation is used for representing an optimized mapping relation between the spectrum efficiency performance of the target network and the antenna parameters; Updating the antenna parameters through gradient descent according to the estimated gradient value; Respectively calculating a first value of the first optimization objective function and a second value of a second optimization objective function according to the updated antenna parameters, wherein the second optimization objective function is expected to be constructed through a second quantile and the network efficiency optimization, and the second quantile is used for selecting grids needing to be optimized; jumping to the network sample data and the antenna parameters, and carrying out gradient estimation on a second optimized objective function through a zero-order estimation algorithm to obtain an estimated gradient value until a preset condition is met so as to obtain a plurality of first values; and taking the antenna parameter corresponding to the smallest first value in the first values as a target antenna parameter. In a second aspect, embodiments of the present disclosure provide a robust network optimization apparatus, including: A parameter obtaining unit, configured to obtain network sample data of a target network and antenna parameters of cells in the target network, where the network sample data includes spectrum efficiency performance of a first number of grids of the target network at a second number of moments; the gradient estimation unit is used for carrying out gradient estimation on a second optimization objective function through a zero-order estimation algorithm based on the network sample data and the antenna parameters to obtain an estimated gradient value, wherein the first optimization objective function is constructed through a first quantile and a network efficiency optimization expectation, the first quantile is used for selecting a grid to be optimized, and the network efficiency optimization expectation is used for representing an optimized mapping relation between the spectrum efficiency performance of the target network and the antenna parameters; the gradient updating unit is used for updating the antenna parameters through gradient descent according to the estimated gradient value; The optimization calculation unit is used for respectively calculating a first value of the first optimization objective function and a second value of a second optimization objective function according to the updated antenna parameters, wherein the second optimization objective function is expected to be constructed through a second quantile and the network efficiency optimization, and the second quantile is used for selecting grids needing to be optimized; The iterative jump unit is used