阅读说明：本技术 一种同步静止轨道卫星的信道衰落确定方法及系统 (Channel fading determination method and system for geostationary orbit satellite ) 是由 白露 杜皓华 徐小雅 于 2021-09-03 设计创作，主要内容包括：本发明公开了一种同步静止轨道卫星的信道衰落确定方法及系统,用于确定Q波段同步静止轨道卫星的信道衰落。该方法包括：获取当前时刻的天气数据；当前时刻的天气数据包括温度、降雨率、相对湿度、降雨量厚度、可见度、平均粒径速度和风速；将当前时刻的天气数据输入训练好的神经网络模型,得到目标时刻的同步静止轨道卫星的信道衰落；目标时刻为当前时刻之后的第N个时刻；训练好的神经网络模型是采用已知天气数据以及与已知天气数据的时刻对应的已知同步静止轨道卫星的信道衰落进行训练得到的神经网络模型。本发明的方法及系统,能够使用通信外部数据高效、低成本地预测到Q波段卫星通信信道数据。(The invention discloses a method and a system for determining channel fading of a synchronous stationary orbit satellite, which are used for determining the channel fading of a Q-band synchronous stationary orbit satellite. The method comprises the following steps: acquiring weather data at the current moment; weather data at the current moment comprises temperature, rainfall rate, relative humidity, rainfall thickness, visibility, average particle size speed and wind speed; inputting weather data at the current moment into the trained neural network model to obtain channel fading of the synchronous stationary orbit satellite at the target moment; the target moment is the Nth moment after the current moment; the trained neural network model is obtained by training by adopting known weather data and channel fading of a known synchronous geostationary orbit satellite corresponding to the time of the known weather data. The method and the system can predict the data of the Q-band satellite communication channel by using the communication external data with high efficiency and low cost.)

1. A channel fading determination method of a synchronous static orbit satellite is characterized by being used for determining channel fading of a Q wave band synchronous static orbit satellite; the method comprises the following steps:

acquiring weather data at the current moment; the weather data comprises temperature, rainfall rate, relative humidity, rainfall thickness, visibility, average particle size velocity and wind speed;

inputting the weather data at the current moment into a trained neural network model to obtain the channel fading of the synchronous stationary orbit satellite at the target moment; the target moment is the Nth moment after the current moment, and N is more than or equal to 0; when N is equal to 0, the target moment is the current moment;

the trained neural network model is obtained by training by adopting known weather data and channel fading of a known synchronous geostationary orbit satellite corresponding to the moment of the known weather data; and when the time of channel fading of the known geostationary orbit satellite is the Nth time after the time of the known weather data, the channel fading of the known geostationary orbit satellite corresponds to the known weather data.

2. The method of claim 1, wherein the training process of the trained neural network model comprises:

acquiring known weather data and channel fading of a known synchronous geostationary orbit satellite;

establishing a corresponding relation between the known weather data at each moment and the channel fading of the known synchronous geostationary orbit satellite at the Nth moment after the known weather data to obtain a weather-fading data group;

dividing the weather-fading data group into a training set, a validation set and a test set;

training a neural network by using the training set and the verification set to obtain a preliminary neural network model;

and testing and adjusting the preliminary neural network model by using the test set to obtain the trained neural network model.

3. The method for determining channel fading of geostationary orbit satellite according to claim 2, wherein the training of the neural network using the training set and the validation set to obtain a preliminary neural network model specifically comprises:

and training by using an artificial neural network by taking the known weather data in the training set and the verification set as input vectors and the channel fading of the known synchronous geostationary orbit satellite in the training set and the verification set as output vectors, and obtaining the preliminary neural network model by adjusting network parameters to minimize the difference between the mean square error values of the training set and the verification set.

4. The method according to claim 2, wherein the testing and adjusting the preliminary neural network model using the test set to obtain the trained neural network model specifically comprises:

inputting the known weather data in the test set into the preliminary neural network model as an input vector to obtain a test output vector;

comparing the test output vector with the channel fading of the known synchronous geostationary orbit satellite in the test set to obtain a comparison result;

if the comparison result meets a preset condition, determining the preliminary neural network model as the trained neural network model;

and if the comparison result does not accord with the preset condition, adjusting the preliminary neural network model until the comparison result accords with the preset condition, and determining the adjusted neural network model as the trained neural network model.

5. A channel fading determination system of a synchronous geostationary orbit satellite is characterized by being used for determining channel fading of a Q-band synchronous geostationary orbit satellite; the system comprises:

the acquisition module is used for acquiring weather data at the current moment; the weather data comprises temperature, rainfall rate, relative humidity, rainfall thickness, visibility, average particle size velocity and wind speed;

the fading determination module is used for inputting the weather data at the current moment into the trained neural network model to obtain the channel fading of the synchronous stationary orbit satellite at the target moment;

the target moment is the Nth moment after the current moment, and N is more than or equal to 0; when N is equal to 0, the target moment is the current moment;

the trained neural network model is obtained by training by adopting known weather data and channel fading of a known synchronous geostationary orbit satellite corresponding to the moment of the known weather data; and when the time of channel fading of the known geostationary orbit satellite is the Nth time after the time of the known weather data, the channel fading of the known geostationary orbit satellite corresponds to the known weather data.

6. The system for determining channel fading for geostationary orbit satellites of claim 5, further comprising a training module for training a neural network model;

the training module comprises:

the system comprises a sample acquisition unit, a data acquisition unit and a data acquisition unit, wherein the sample acquisition unit is used for acquiring known weather data and channel fading of a known synchronous stationary orbit satellite;

a corresponding unit, configured to establish a corresponding relationship between the known weather data at each time and the channel fading of the known geostationary orbit satellite at the nth time after the known weather data, so as to obtain a weather-fading data set;

the data dividing unit is used for dividing the weather-fading data group into a training set, a verification set and a test set;

the training unit is used for training the neural network by utilizing the training set and the verification set to obtain a preliminary neural network model;

and the test adjusting unit is used for testing and adjusting the preliminary neural network model by using the test set to obtain the trained neural network model.

7. The system for determining channel fading for geostationary orbiting satellites as claimed in claim 6, wherein said training unit comprises:

and the training and network parameter adjusting subunit is used for taking the known weather data in the training set and the verification set as input vectors, taking the channel fading of the known geostationary orbit satellite in the training set and the verification set as output vectors, training by using an artificial neural network, and obtaining the preliminary neural network model by adjusting network parameters to minimize the difference between the mean square error values of the training set and the verification set.

8. The channel fading determination system for geostationary earth-orbiting satellites as claimed in claim 6, wherein said test adjustment unit comprises:

the test input subunit is used for inputting the known weather data in the test set into the preliminary neural network model as an input vector to obtain a test output vector;

the comparison subunit is used for comparing the test output vector with the channel fading of the known synchronous stationary orbit satellite in the test set to obtain a comparison result;

a comparison execution subunit, configured to determine that the preliminary neural network model is the trained neural network model if the comparison result meets a preset condition; and if the comparison result does not accord with the preset condition, adjusting the preliminary neural network model until the comparison result accords with the preset condition, and determining the adjusted neural network model as the trained neural network model.

Technical Field

The invention relates to the field of satellite communication, in particular to a method and a system for determining channel fading of a synchronous stationary orbit satellite.

Background

The existing communication channel estimation methods are all based on internal data of a communication system, but the cost of a measurement system constructed by acquiring data of Q-band satellite communication channels based on the internal data of the communication system is too high.

Disclosure of Invention

Based on the above, embodiments of the present invention provide a method and a system for determining channel fading of a geostationary orbit satellite, which can efficiently predict communication channel data of a Q-band satellite with low cost by using external communication data.

In order to achieve the purpose, the invention provides the following scheme:

a channel fading determination method of a synchronous static orbit satellite is used for determining the channel fading of a Q wave band synchronous static orbit satellite; the method comprises the following steps:

acquiring weather data at the current moment; the weather data comprises temperature, rainfall rate, relative humidity, rainfall thickness, visibility, average particle size velocity and wind speed;

inputting the weather data at the current moment into a trained neural network model to obtain the channel fading of the synchronous stationary orbit satellite at the target moment; the target moment is the Nth moment after the current moment, and N is more than or equal to 0; when N is equal to 0, the target moment is the current moment;

the trained neural network model is obtained by training by adopting known weather data and channel fading of a known synchronous geostationary orbit satellite corresponding to the moment of the known weather data; and when the time of channel fading of the known geostationary orbit satellite is the Nth time after the time of the known weather data, the channel fading of the known geostationary orbit satellite corresponds to the known weather data.

Optionally, the training process of the trained neural network model is as follows:

acquiring known weather data and channel fading of a known synchronous geostationary orbit satellite;

establishing a corresponding relation between the known weather data at each moment and the channel fading of the known synchronous geostationary orbit satellite at the Nth moment after the known weather data to obtain a weather-fading data group;

dividing the weather-fading data group into a training set, a validation set and a test set;

training a neural network by using the training set and the verification set to obtain a preliminary neural network model;

and testing and adjusting the preliminary neural network model by using the test set to obtain the trained neural network model.

Optionally, the training of the neural network by using the training set and the verification set to obtain a preliminary neural network model specifically includes:

and training by using an artificial neural network by taking the known weather data in the training set and the verification set as input vectors and the channel fading of the known synchronous geostationary orbit satellite in the training set and the verification set as output vectors, and obtaining the preliminary neural network model by adjusting network parameters to minimize the difference between the mean square error values of the training set and the verification set.

Optionally, the testing and adjusting the preliminary neural network model by using the test set to obtain the trained neural network model specifically includes:

inputting the known weather data in the test set into the preliminary neural network model as an input vector to obtain a test output vector;

comparing the test output vector with the channel fading of the known synchronous geostationary orbit satellite in the test set to obtain a comparison result;

if the comparison result meets a preset condition, determining the preliminary neural network model as the trained neural network model;

and if the comparison result does not accord with the preset condition, adjusting the preliminary neural network model until the comparison result accords with the preset condition, and determining the adjusted neural network model as the trained neural network model.

A channel fading determination system of a synchronous static orbit satellite is used for determining the channel fading of a Q wave band synchronous static orbit satellite; the system comprises:

the acquisition module is used for acquiring weather data at the current moment; the weather data comprises temperature, rainfall rate, relative humidity, rainfall thickness, visibility, average particle size velocity and wind speed;

the fading determination module is used for inputting the weather data at the current moment into the trained neural network model to obtain the channel fading of the synchronous stationary orbit satellite at the target moment;

the target moment is the Nth moment after the current moment, and N is more than or equal to 0; when N is equal to 0, the target moment is the current moment;

the trained neural network model is obtained by training by adopting known weather data and channel fading of a known synchronous geostationary orbit satellite corresponding to the moment of the known weather data; and when the time of channel fading of the known geostationary orbit satellite is the Nth time after the time of the known weather data, the channel fading of the known geostationary orbit satellite corresponds to the known weather data.

Optionally, the system further includes a training module, where the training module is used to train the neural network model;

the training module comprises:

the system comprises a sample acquisition unit, a data acquisition unit and a data acquisition unit, wherein the sample acquisition unit is used for acquiring known weather data and channel fading of a known synchronous stationary orbit satellite;

a corresponding unit, configured to establish a corresponding relationship between the known weather data at each time and the channel fading of the known geostationary orbit satellite at the nth time after the known weather data, so as to obtain a weather-fading data set;

the data dividing unit is used for dividing the weather-fading data group into a training set, a verification set and a test set;

the training unit is used for training the neural network by utilizing the training set and the verification set to obtain a preliminary neural network model;

and the test adjusting unit is used for testing and adjusting the preliminary neural network model by using the test set to obtain the trained neural network model.

Optionally, the training unit includes:

and the training and network parameter adjusting subunit is used for taking the known weather data in the training set and the verification set as input vectors, taking the channel fading of the known geostationary orbit satellite in the training set and the verification set as output vectors, training by using an artificial neural network, and obtaining the preliminary neural network model by adjusting network parameters to minimize the difference between the mean square error values of the training set and the verification set.

Optionally, the test adjusting unit includes:

the test input subunit is used for inputting the known weather data in the test set into the preliminary neural network model as an input vector to obtain a test output vector;

the comparison subunit is used for comparing the test output vector with the channel fading of the known synchronous stationary orbit satellite in the test set to obtain a comparison result;

a comparison execution subunit, configured to determine that the preliminary neural network model is the trained neural network model if the comparison result meets a preset condition; and if the comparison result does not accord with the preset condition, adjusting the preliminary neural network model until the comparison result accords with the preset condition, and determining the adjusted neural network model as the trained neural network model.

Compared with the prior art, the invention has the beneficial effects that:

the embodiment of the invention provides a method and a system for determining channel fading of a synchronous geostationary orbit satellite, which are used for determining the channel fading of the synchronous geostationary orbit satellite by using weather data, thereby realizing the acquisition of Q-band satellite communication channel data based on external data of a communication system, overcoming the problem that the Q-band satellite communication channel data can only be acquired based on internal data of the communication system in the prior art, greatly reducing the acquisition difficulty of the Q-band satellite communication channel data, improving the measurement efficiency and reducing the measurement cost.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.

Fig. 1 is a flowchart of a method for determining channel fading of a geostationary orbiting satellite according to embodiment 1.

FIG. 2 is a network structure diagram of the long-short term memory artificial neural network used in the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.

Example 1:

embodiment 1 discloses a channel fading determination method for a geostationary orbit satellite, which is used for determining channel fading of a Q-band geostationary orbit satellite.

Fig. 1 is a flowchart of a method for determining channel fading of a geostationary orbiting satellite according to embodiment 1. Referring to fig. 1, the method includes:

step 101: acquiring weather data at the current moment; the weather data at the current moment comprises seven types of weather data at the current moment, namely temperature, rainfall rate, relative humidity, rainfall thickness, visibility, average particle size speed and wind speed. The seven types of weather data are 7 types of weather data screened out to be most effective for channel fading determination by performing feature selection from 14 types of weather data using a Least Absolute Shrinkage and Selection Operator (LASSO) algorithm.

Step 102: inputting weather data at the current moment into the trained neural network model to obtain channel fading of the synchronous stationary orbit satellite at the target moment; the target moment is the Nth moment after the current moment, and N is more than or equal to 0; when N is equal to 0, the target moment is the current moment;

the trained neural network model is obtained by training by adopting known weather data and channel fading of a known synchronous geostationary orbit satellite corresponding to the moment of the known weather data; when the time of the channel fading of the geostationary orbit satellite is known to be the nth time after the time of the known weather data, the channel fading of the geostationary orbit satellite is known to correspond to the known weather data.

In one example, the training process of the trained neural network model is:

acquiring known weather data and channel fading of a known synchronous geostationary orbit satellite; according to the invention, the known weather data acquisition mode and the current weather data acquisition mode can be measured by building a weather data measurement system. The known acquisition method of channel fading of geostationary orbit satellite is: a communication system of a Q-band synchronous static orbit satellite is built, and satellite channel fading is measured at a frequency of every second.

Establishing a corresponding relation between the known weather data at each moment and the channel fading of the known synchronous geostationary orbit satellite at the Nth moment after the known weather data to obtain a weather-fading data group; when the target time is the current time, establishing a corresponding relation between the known weather data at each time and the channel fading of the known geostationary orbit satellite at the same time of the known weather data; and when the target time is the nth time after the current time, establishing a corresponding relation between the known weather data at each time and the channel fading of the known geostationary orbit satellite at the nth time after the known weather data, wherein n is greater than 0.

Dividing a weather-fading data group into a training set, a verification set and a test set; the division mode of the training set, the verification set and the test set can be as follows: 1: 1.

Training the neural network by utilizing a training set and a verification set to obtain a preliminary neural network model; the neural network is preferably a long-term-memory (LSTM) artificial neural network. The structure of the long-short term memory artificial neural network is shown in figure 2.

And testing and adjusting the preliminary neural network model by using the test set to obtain the trained neural network model.

In one example, training a neural network by using a training set and a validation set to obtain a preliminary neural network model specifically includes:

and training by using an artificial neural network, and obtaining a preliminary neural network model by adjusting network parameters to minimize the difference between the mean square error values of the training set and the verification set. The mean square error is used as a loss function, and the network can be ensured not to be over-fitted by adjusting network parameters to achieve the state of the minimum mean square error of network prediction.

In one example, the testing and adjusting of the preliminary neural network model by using the test set to obtain the trained neural network model specifically includes:

inputting known weather data in the test set as an input vector into the preliminary neural network model to obtain a test output vector;

comparing the test output vector with the channel fading of the known synchronous stationary orbit satellite in the test set to obtain a comparison result;

if the comparison result meets the preset condition, determining the preliminary neural network model as a trained neural network model;

and if the comparison result does not accord with the preset condition, adjusting the preliminary neural network model until the comparison result accords with the preset condition, and determining the adjusted neural network model as the trained neural network model. The step of adjusting the preliminary neural network model when the comparison result does not meet the preset condition may adopt the same network parameter adjustment mode as that in the step of training the neural network by using the training set and the validation set or re-execute the step of training the neural network by using the training set and the validation set.

The channel fading determination method for the geostationary orbit satellite can use a small amount of data to train the artificial neural network, and use weather data which is easy to obtain deficient satellite channel fading data which is difficult to obtain based on the neural network, so that the problems that the channel data of a Q-band satellite is deficient and difficult to obtain are solved, the measurement efficiency is improved, and the measurement cost is reduced. Meanwhile, the method can predict satellite channel data at the future time by using the current weather data, and can be used for resource optimization of a satellite communication system.

Example 2:

embodiment 2 discloses a channel fading determination system for a geostationary orbit satellite, which is used for determining channel fading of a Q-band geostationary orbit satellite; the system comprises:

the acquisition module is used for acquiring weather data at the current moment; the weather data at the current moment comprises seven kinds of weather data at the current moment, namely temperature, rainfall rate, relative humidity, rainfall thickness, visibility, average particle size speed and wind speed;

the fading determination module is used for inputting the weather data at the current moment into the trained neural network model to obtain the channel fading of the synchronous stationary orbit satellite at the target moment;

the target moment is the Nth moment after the current moment, and N is more than or equal to 0; when N is equal to 0, the target moment is the current moment;

the trained neural network model is obtained by training by adopting known weather data and channel fading of a known synchronous geostationary orbit satellite corresponding to the moment of the known weather data; when the time of the channel fading of the geostationary orbit satellite is known to be the nth time after the time of the known weather data, the channel fading of the geostationary orbit satellite is known to correspond to the known weather data.

In one example, the system further comprises a training module for training the neural network model;

the training module comprises:

the system comprises a sample acquisition unit, a data acquisition unit and a data acquisition unit, wherein the sample acquisition unit is used for acquiring known weather data and channel fading of a known synchronous stationary orbit satellite;

a corresponding unit, configured to establish a corresponding relationship between the known weather data at each time and the channel fading of the known geostationary orbit satellite at the nth time after the known weather data, so as to obtain a weather-fading data set;

the data dividing unit is used for dividing the weather-fading data group into a training set, a verification set and a test set;

the training unit is used for training the neural network by utilizing the training set and the verification set to obtain a preliminary neural network model;

and the test adjusting unit is used for testing and adjusting the preliminary neural network model by using the test set to obtain the trained neural network model.

In one example, the training unit includes:

and the training and network parameter adjusting subunit is used for taking the known weather data in the training set and the verification set as input vectors, taking the channel fading of the known synchronous geostationary orbit satellite in the training set and the verification set as output vectors, training by using an artificial neural network, and obtaining a preliminary neural network model by adjusting network parameters to minimize the difference between the mean square error values of the training set and the verification set.

In one example, the test adjustment unit includes:

the test input subunit is used for inputting the known weather data in the test set into the preliminary neural network model as an input vector to obtain a test output vector;

the comparison subunit is used for comparing the test output vector with the channel fading of the known synchronous stationary orbit satellite in the test set to obtain a comparison result;

the comparison execution subunit is used for determining the preliminary neural network model as the trained neural network model if the comparison result meets the preset condition; and if the comparison result does not accord with the preset condition, adjusting the preliminary neural network model until the comparison result accords with the preset condition, and determining the adjusted neural network model as the trained neural network model.

Compared with the prior art, the invention has the beneficial effects that:

the embodiment of the invention provides a method and a system for determining channel fading of a synchronous geostationary orbit satellite, which predict the channel fading of the synchronous geostationary orbit satellite by using weather data, thereby realizing the prediction of Q-band satellite communication channel data based on external data of a communication system, overcoming the difficulty that the Q-band satellite communication channel data can only be obtained based on internal data of the communication system in the prior art, greatly reducing the difficulty of obtaining the Q-band satellite communication channel data, improving the measurement efficiency and reducing the measurement cost.

The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.

The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.