Method for adjusting the emission power of an optical module

Abstract

The application discloses a transmitting optical power adjusting method of an optical module and relates to the technical field of optical communication. The method comprises the following steps: based on historical communication data of a communication base station, evaluating a multi-dimensional attention demand vector preference of a historical network state of the communication base station; obtaining operation parameters of a real-time communication base station, and analyzing a multi-dimensional attention vector of a real-time network state of the communication base station; judging whether the multi-dimensional attention vector of the real-time network state of the communication base station meets the multi-dimensional attention demand vector preference of the historical network state of the communication base station, if not, determining that the transmitting optical power needs to be adjusted, establishing a dynamic transmitting optical power adjusting model according to the deviation between the multi-dimensional attention demand vector preference of the historical network state of the communication base station and the multi-dimensional attention vector of the real-time network state of the communication base station, and generating a dynamic transmitting optical power adjusting value of the communication base station. The application has the advantages of improving communication quality, reducing delay and ensuring the stability of the network.

Description

Technical Field

[0001] This invention relates to the field of optical communication technology, specifically to a method for adjusting the transmitted optical power of an optical module. Background Technology

[0002] Current 5G optical power adjustment methods primarily rely on fixed algorithms and static thresholds, failing to fully consider the dynamic changes in real-time network conditions and the varying needs of different regions. This results in the inability to accurately adjust transmit optical power under conditions such as network load fluctuations, changes in user density, or signal interference, potentially leading to excessively strong or weak signals, thus impacting network quality and energy efficiency optimization. Therefore, how to flexibly adjust optical power based on real-time network conditions and demand changes remains an unresolved issue. Summary of the Invention

[0003] To address the aforementioned technical issues, this solution provides a method for adjusting the transmit optical power of optical modules. This method overcomes the limitations of existing 5G optical power adjustment methods, which primarily rely on fixed algorithms and static thresholds, failing to adequately consider the dynamic changes in real-time network conditions and the varying needs of different regions. This results in the inability to accurately adjust the transmit optical power under conditions such as network load fluctuations, changes in user density, or signal interference, potentially leading to excessively strong or weak signals, thus impacting network quality and energy efficiency. Therefore, how to flexibly adjust optical power based on real-time network conditions and changing demands remains an unresolved issue.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] The method for adjusting the emitted optical power of an optical module includes:

[0006] Based on historical communication data from communication base stations, the transmission request timing parameters of historical communication data are analyzed to evaluate the multi-dimensional attention demand vector preference of the historical network status of communication base stations; the multi-dimensional attention demand vector preference includes: communication data quality dimension, communication data latency dimension, and communication network stability dimension.

[0007] Based on the built-in sensors in the optical modules of communication base stations, the real-time operating parameters of the communication base stations are obtained, and the multi-dimensional attention vector of the real-time network status of the communication base stations is analyzed.

[0008] If the multi-dimensional attention vector of the real-time network status of the communication base station meets the preference of the multi-dimensional attention demand vector of the historical network status of the communication base station, then it is determined that there is no need to adjust the transmit optical power; otherwise, it is determined that the transmit optical power needs to be adjusted.

[0009] If it is determined that the transmitted optical power needs to be adjusted, a dynamic transmitted optical power adjustment model is established based on the deviation between the multi-dimensional attention demand vector preference of the historical network status of the communication base station and the multi-dimensional attention vector of the real-time network status of the communication base station, and the dynamic transmitted optical power adjustment value of the communication base station is generated.

[0010] Preferably, based on historical communication data from communication base stations, the analysis of transmission request timing parameters of historical communication data, and the evaluation of multi-dimensional attention demand vector preferences for the historical network status of communication base stations specifically include:

[0011] Based on the standardized processing of historical communication data of communication base stations, a sliding window is established according to unit time, and the transmission request time sequence parameters of historical communication data are used as variable attributes to obtain multi-dimensional demand feature values ​​of the historical network status of communication base stations.

[0012] Using the K-means clustering algorithm, the multi-dimensional demand feature values ​​of the historical network status of communication base stations are divided into clusters according to the demand of each dimension per unit time, resulting in a multi-dimensional demand feature parameter dataset of the historical network status of communication base stations. ;in, The i-th dimension of the demand feature parameter represents the historical network status of the communication base station at the t-th unit of time.

[0013] Based on AR time series analysis-autoregression, a multi-dimensional preference analysis model of historical network states is constructed.

[0014] The multi-dimensional demand characteristic parameter dataset of the historical network status of communication base stations is stabilized and substituted into the multi-dimensional preference analysis model of the historical network status. The multi-dimensional demand characteristic parameters are used as input and the multi-dimensional attention demand vector preference of the historical network status of communication base stations is used as output.

[0015] Specifically, the multi-dimensional preference analysis model for historical network states is as follows:

[0016] ,

[0017] In the formula, For the historical network status of the communication base station, the i-th dimension of the focus demand vector preference value is defined in the t-th unit of time. for For the historical network status of communication base stations The i-th dimension of the demand feature parameter under the autoregressive order of unit time. Let n be the error term of the i-th dimension of the historical network status of the communication base station at the t-th unit time, where n is the total number of multi-dimensional demand characteristic parameters. The autoregressive coefficients of the demand vector are for the i-th dimension;

[0018] Preferably, the multi-dimensional attention vector for analyzing the real-time network status of the communication base station, based on the sensors built into the optical module in the communication base station to obtain real-time operating parameters of the communication base station, specifically includes:

[0019] Based on the normalization of the operating parameters of the real-time communication base station, and according to the sliding window, the multi-dimensional demand characteristic data of the real-time network status of the communication base station are marked.

[0020] A multi-factor linear regression model for real-time network status is established based on multi-factor linear regression.

[0021] Based on the multi-factor linear regression model of real-time network status, the multi-dimensional demand feature data of real-time network status of communication base stations is used as the original training set, the multi-dimensional demand feature data is used as the input of independent variables, and the multi-dimensional attention vector of real-time network status of communication base stations is used as the output of dependent variables.

[0022] The multi-factor linear regression model for real-time network status is as follows:

[0023] ,

[0024] In the formula, This is the attention vector of the i-th dimension in the t-th unit of time for the historical network status of the communication base station. This refers to the demand feature data of the i-th dimension in the t-th unit of time of the historical network status of the communication base station. , , , All are linear regression coefficients.

[0025] Preferably, if it is determined that the transmitted optical power needs to be adjusted, a dynamic transmitted optical power adjustment model is established based on the deviation between the multi-dimensional attention demand vector preference of the historical network status of the communication base station and the multi-dimensional attention vector of the real-time network status of the communication base station. The dynamic transmitted optical power adjustment value of the communication base station specifically includes:

[0026] The multi-dimensional attention demand vector preference based on the historical network status of the communication base station and the multi-dimensional attention vector based on the real-time network status of the communication base station are normalized.

[0027] Align the multi-dimensional attention demand vector preference for the historical network status of communication base stations based on time attributes with the multi-dimensional attention vector for the real-time network status of communication base stations.

[0028] Using the Euclidean distance formula, the spatial distance between the historical network state multidimensional attention demand vector preference of the communication base station and the real-time network state multidimensional attention vector of the communication base station is calculated per unit time, and the multidimensional attention demand deviation vector of the real-time network state of the communication base station is determined.

[0029] Based on the multi-dimensional attention demand deviation vector of the real-time network status of communication base stations, a dynamic transmit optical power adjustment model is established according to weighted linear regression to generate the dynamic transmit optical power adjustment value of communication base stations.

[0030] The Euclidean distance formula is as follows:

[0031] ,

[0032] In the formula, The focus is on the demand deviation vector in the i-th dimension of the real-time network status of the communication base station at the t-th unit time.

[0033] Specifically, the dynamic transmit optical power adjustment value of the generated communication base station is as follows:

[0034] ,

[0035] In the formula, This refers to the dynamic transmit optical power adjustment value of the communication base station. is the weight of the i-th dimension of the real-time network status of the communication base station, and b is the bias term.

[0036] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0037] This invention proposes a scheme for adjusting the transmit optical power of optical modules. By analyzing historical communication data to assess the network demand preferences of the base station, and combining this with real-time operating parameters acquired by the base station's built-in sensors, it determines whether the current network state meets historical demand preferences. If not, a dynamic transmit optical power adjustment model is established to adjust the transmit optical power based on the deviation between the two. The beneficial effects of this scheme are: optimizing transmit optical power adjustment according to the real-time needs of the base station, improving communication quality, reducing latency, and ensuring network stability. Attached Figure Description

[0038] Figure 1 The flowchart shows the method for adjusting the emitted optical power of an optical module.

[0039] Figure 2 Flowchart of a multi-dimensional focus demand vector preference method for evaluating the historical network status of communication base stations;

[0040] Figure 3 Flowchart of the multi-dimensional attention vector method for analyzing the real-time network status of communication base stations;

[0041] Figure 4 Flowchart of a method for generating dynamic transmit optical power adjustment values ​​for communication base stations. Detailed Implementation

[0042] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0043] Reference Figure 1 As shown, the method for adjusting the emitted optical power of an optical module includes:

[0044] Based on historical communication data from communication base stations, the transmission request timing parameters of historical communication data are analyzed to evaluate the multi-dimensional attention demand vector preference of the historical network status of communication base stations; the multi-dimensional attention demand vector preference includes: communication data quality dimension, communication data latency dimension, and communication network stability dimension.

[0045] Based on the built-in sensors in the optical modules of communication base stations, the real-time operating parameters of the communication base stations are obtained, and the multi-dimensional attention vector of the real-time network status of the communication base stations is analyzed.

[0046] If the multi-dimensional attention vector of the real-time network status of the communication base station meets the preference of the multi-dimensional attention demand vector of the historical network status of the communication base station, then it is determined that there is no need to adjust the transmit optical power; otherwise, it is determined that the transmit optical power needs to be adjusted.

[0047] If it is determined that the transmitted optical power needs to be adjusted, a dynamic transmitted optical power adjustment model is established based on the deviation between the multi-dimensional attention demand vector preference of the historical network status of the communication base station and the multi-dimensional attention vector of the real-time network status of the communication base station, and the dynamic transmitted optical power adjustment value of the communication base station is generated.

[0048] This solution analyzes historical communication data to assess the network demand preferences of base stations and combines this with real-time operational parameters acquired by the base station's built-in sensors to determine whether the current network status meets historical demand preferences. If not, a dynamic transmit optical power adjustment model is established to adjust the transmit optical power based on the deviation between the two. The benefits of this solution are: optimizing transmit optical power adjustment according to the real-time needs of the base station, improving communication quality, reducing latency, and ensuring network stability.

[0049] Reference Figure 2 As shown, based on historical communication data from communication base stations, the transmission request timing parameters of historical communication data are analyzed to evaluate the multi-dimensional attention demand vector preferences of the historical network status of communication base stations. Specifically, this includes:

[0050] Based on the standardized processing of historical communication data of communication base stations, a sliding window is established according to unit time, and the transmission request time sequence parameters of historical communication data are used as variable attributes to obtain multi-dimensional demand feature values ​​of the historical network status of communication base stations.

[0051] Using the K-means clustering algorithm, the multi-dimensional demand feature values ​​of the historical network status of communication base stations are divided into clusters according to the demand of each dimension per unit time, resulting in a multi-dimensional demand feature parameter dataset of the historical network status of communication base stations. ;in, The i-th dimension of the demand feature parameter represents the historical network status of the communication base station at the t-th unit of time.

[0052] Based on AR time series analysis-autoregression, a multi-dimensional preference analysis model of historical network states is constructed.

[0053] The multi-dimensional demand characteristic parameter dataset of the historical network status of communication base stations is stabilized and substituted into the multi-dimensional preference analysis model of the historical network status. The multi-dimensional demand characteristic parameters are used as input and the multi-dimensional attention demand vector preference of the historical network status of communication base stations is used as output.

[0054] Specifically, the multi-dimensional preference analysis model for historical network states is as follows:

[0055] ,

[0056] In the formula, For the historical network status of the communication base station, the i-th dimension of the focus demand vector preference value is defined in the t-th unit of time. for For the historical network status of communication base stations The i-th dimension of the demand feature parameter under the autoregressive order of unit time. Let n be the error term of the i-th dimension of the historical network status of the communication base station at the t-th unit time, where n is the total number of multi-dimensional demand characteristic parameters. The autoregressive coefficients of the demand vector are for the i-th dimension;

[0057] This solution extracts multi-dimensional network demand characteristics through in-depth analysis of historical communication data from communication base stations. Combining K-means clustering and AR time series analysis methods, it accurately assesses the network status of base stations. Through standardization processing and sliding window technology, it can accurately capture demand changes over different time periods, providing data support for adjusting the transmit optical power of optical modules. This enables dynamic optimization of optical power based on network load, improving communication quality, reducing energy consumption, and ensuring network stability and efficiency.

[0058] Reference Figure 3 The aforementioned method, which uses sensors built into the optical modules of communication base stations to acquire real-time operating parameters and analyze the multi-dimensional attention vector of the real-time network status of the communication base stations, specifically includes:

[0059] Based on the normalization of the operating parameters of the real-time communication base station, and according to the sliding window, the multi-dimensional demand characteristic data of the real-time network status of the communication base station are marked.

[0060] A multi-factor linear regression model for real-time network status is established based on multi-factor linear regression.

[0061] Based on the multi-factor linear regression model of real-time network status, the multi-dimensional demand feature data of real-time network status of communication base stations is used as the original training set, the multi-dimensional demand feature data is used as the input of independent variables, and the multi-dimensional attention vector of real-time network status of communication base stations is used as the output of dependent variables.

[0062] The multi-factor linear regression model for real-time network status is as follows:

[0063] ,

[0064] In the formula, The historical network status of the communication base station, at the t-th unit of time, includes the i-th dimension of the attention vector, a multi-dimensional attention demand vector, and preferences. This refers to the demand feature data of the i-th dimension in the t-th unit of time of the historical network status of the communication base station. , , , All are linear regression coefficients.

[0065] It is understandable that the optimal linear regression coefficients in the model can be obtained using the least squares method, which is well known to those skilled in the art and will not be discussed further here.

[0066] This solution utilizes the built-in sensors of the optical module in the communication base station to acquire real-time operating parameters. Combined with sliding window technology, it normalizes multi-dimensional demand characteristic data, enabling real-time analysis of the base station network status. Furthermore, it establishes an accurate network status prediction mechanism through a multi-factor linear regression model. This model can use real-time network status data as a training set and predict the multi-dimensional attention vector of the real-time network status of the communication base station by inputting multi-dimensional feature data, providing crucial data for subsequent adjustment of the optical module's transmit optical power in the communication base station.

[0067] Reference Figure 4As shown, if it is determined that the transmitted optical power needs to be adjusted, a dynamic transmitted optical power adjustment model is established based on the deviation between the multi-dimensional attention demand vector preference of the historical network status of the communication base station and the multi-dimensional attention vector of the real-time network status of the communication base station. The specific dynamic transmitted optical power adjustment values ​​of the communication base station include:

[0068] The multi-dimensional attention demand vector preference based on the historical network status of the communication base station and the multi-dimensional attention vector based on the real-time network status of the communication base station are normalized.

[0069] Align the multi-dimensional attention demand vector preference for the historical network status of communication base stations based on time attributes with the multi-dimensional attention vector for the real-time network status of communication base stations.

[0070] Using the Euclidean distance formula, the spatial distance between the historical network state multidimensional attention demand vector preference of the communication base station and the real-time network state multidimensional attention vector of the communication base station is calculated per unit time, and the multidimensional attention demand deviation vector of the real-time network state of the communication base station is determined.

[0071] Based on the multi-dimensional attention demand deviation vector of the real-time network status of communication base stations, a dynamic transmit optical power adjustment model is established according to weighted linear regression to generate the dynamic transmit optical power adjustment value of communication base stations.

[0072] The Euclidean distance formula is as follows:

[0073] ,

[0074] In the formula, The focus is on the demand deviation vector in the ith dimension of the real-time network status of the communication base station at the t-th unit of time.

[0075] Specifically, the dynamic transmit optical power adjustment value of the generated communication base station is as follows:

[0076] ,

[0077] In the formula, This refers to the dynamic transmit optical power adjustment value of the communication base station. is the weight of the i-th dimension of the real-time network status of the communication base station, and b is the bias term.

[0078] It is understandable that the allocation of dimensional weights is based on gradient descent or other optimization algorithms, which is well known and undisputed by those skilled in the art, and will not be elaborated upon here.

[0079] The solution is based on normalized processing and alignment of multi-dimensional attention vectors between historical and real-time network states. It calculates the deviation vector using the Euclidean distance formula and constructs a dynamic transmit optical power adjustment model based on this deviation vector, dynamically generating the transmit optical power adjustment value for the communication base station. By quantifying the difference between historical preferences and real-time states, it accurately reflects changes in network demand, thereby optimizing the transmit optical power adjustment of the communication base station's optical modules. The beneficial effects include improved real-time performance and accuracy of optical power adjustment, enhanced network adaptability of the communication base station, reduced signal quality degradation caused by improper power, and improved overall communication system performance and efficiency.

[0080] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A method for adjusting the emitted optical power of an optical module, characterized in that, include: Based on historical communication data from communication base stations, analyze the transmission request timing parameters of historical communication data, and evaluate the multi-dimensional attention demand vector preference of historical network status of communication base stations. The multi-dimensional focus on demand vector preferences includes: communication data quality dimension, communication data latency dimension, and communication network stability dimension; Based on the built-in sensors in the optical modules of communication base stations, the real-time operating parameters of the communication base stations are obtained, and the multi-dimensional attention vector of the real-time network status of the communication base stations is analyzed. If the multi-dimensional attention vector of the real-time network status of the communication base station meets the preference of the multi-dimensional attention demand vector of the historical network status of the communication base station, then it is determined that there is no need to adjust the transmit optical power; otherwise, it is determined that the transmit optical power needs to be adjusted. If it is determined that the transmit optical power needs to be adjusted, a dynamic transmit optical power adjustment model is established based on the deviation between the multi-dimensional attention demand vector preference of the historical network status of the communication base station and the multi-dimensional attention vector of the real-time network status of the communication base station, and the dynamic transmit optical power adjustment value of the communication base station is generated. Specifically, based on historical communication data from communication base stations, the analysis of transmission request timing parameters of historical communication data, and the evaluation of the multi-dimensional attention demand vector preferences of the historical network status of communication base stations include: Based on the standardized processing of historical communication data of communication base stations, a sliding window is established according to unit time, and the transmission request time sequence parameters of historical communication data are used as variable attributes to obtain multi-dimensional demand feature values ​​of the historical network status of communication base stations. Using the K-means clustering algorithm, the multi-dimensional demand feature values ​​of the historical network status of communication base stations are divided into clusters according to the demand of each dimension per unit time, resulting in a multi-dimensional demand feature parameter dataset of the historical network status of communication base stations. ;in, The i-th dimension of the demand feature parameter represents the historical network status of the communication base station at the t-th unit of time. Based on AR time series analysis-autoregression, a multi-dimensional preference analysis model of historical network states is constructed. The multi-dimensional demand characteristic parameter dataset of the historical network status of communication base stations is stabilized and substituted into the multi-dimensional preference analysis model of the historical network status. The multi-dimensional demand characteristic parameters are used as input and the multi-dimensional attention demand vector preference of the historical network status of communication base stations is used as output. Specifically, the multi-dimensional preference analysis model for historical network states is as follows: ， In the formula, For the historical network status of the communication base station, the i-th dimension of the focus demand vector preference value is defined in the t-th unit of time. for For the historical network status of communication base stations The i-th dimension of the demand feature parameter under the autoregressive order of unit time. Let n be the error term of the i-th dimension of the historical network status of the communication base station at the t-th unit time, where n is the total number of multi-dimensional demand characteristic parameters. The autoregressive coefficients of the demand vector are for the i-th dimension; Specifically, the multi-dimensional attention vector for analyzing the real-time network status of communication base stations, based on the sensors built into the optical modules of the communication base stations to obtain real-time operating parameters, includes: Based on the normalization of the operating parameters of the real-time communication base station, and according to the sliding window, the multi-dimensional demand characteristic data of the real-time network status of the communication base station are marked. A multi-factor linear regression model for real-time network status is established based on multi-factor linear regression. Based on the multi-factor linear regression model of real-time network status, the multi-dimensional demand feature data of real-time network status of communication base stations is used as the original training set, the multi-dimensional demand feature data is used as the input of independent variables, and the multi-dimensional attention vector of real-time network status of communication base stations is used as the output of dependent variables. The multi-factor linear regression model for real-time network status is as follows: ， In the formula, This is the attention vector of the i-th dimension in the t-th unit of time for the historical network status of the communication base station. This refers to the demand feature data of the i-th dimension in the t-th unit of time of the historical network status of the communication base station. , , , All are linear regression coefficients; Specifically, if it is determined that the transmitted optical power needs to be adjusted, a dynamic transmitted optical power adjustment model is established based on the deviation between the multi-dimensional attention demand vector preference of the historical network status of the communication base station and the multi-dimensional attention vector of the real-time network status of the communication base station. The dynamic transmitted optical power adjustment value of the communication base station specifically includes: The multi-dimensional attention demand vector preference based on the historical network status of the communication base station and the multi-dimensional attention vector based on the real-time network status of the communication base station are normalized. Align the multi-dimensional attention demand vector preference for the historical network status of communication base stations based on time attributes with the multi-dimensional attention vector for the real-time network status of communication base stations. Using the Euclidean distance formula, the spatial distance between the historical network state multidimensional attention demand vector preference of the communication base station and the real-time network state multidimensional attention vector of the communication base station is calculated per unit time, and the multidimensional attention demand deviation vector of the real-time network state of the communication base station is determined. Based on the multi-dimensional attention demand deviation vector of the real-time network status of communication base stations, a dynamic transmit optical power adjustment model is established according to weighted linear regression to generate the dynamic transmit optical power adjustment value of communication base stations.

2. The method for adjusting the emitted optical power of an optical module according to claim 1, characterized in that, The Euclidean distance formula is as follows: ， In the formula, The focus is on the demand deviation vector in the i-th dimension of the real-time network status of the communication base station at the t-th unit time.

3. The method for adjusting the emitted optical power of an optical module according to claim 2, characterized in that, The specific dynamic transmit optical power adjustment value of the generated communication base station is as follows: ， In the formula, This refers to the dynamic transmit optical power adjustment value of the communication base station. is the weight of the i-th dimension of the real-time network status of the communication base station, and b is the bias term.

Images