Dual-mode communication optimization method

Abstract

The invention discloses a dual-mode communication optimization method, and relates to the technical field of data processing, and the method comprises the following steps: S1, collecting the data of a continuous time period through a terminal, obtaining the data of a plurality of windows, and carrying out the discarding of the data of each window; s2, verifying the validity of the data of the abandoned window by using a confidence interval mutual verification method; and S3, after the validity is verified, carrying out parameter replacement and updating to obtain an optimal data replacement parameter so as to realize global parameter optimization of dual-mode communication. According to the method, data replacement link parameters of a plurality of terminals are shared to obtain optimal data replacement parameters; by calculating the gradient of the target function to the current parameter, parameter updating is carried out, so that collaborative optimization of global parameters of dual-mode communication in a multi-terminal environment is realized, data replacement efficiency is improved, and efficient response of a dual-mode communication system is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a dual-mode communication optimization method. Background Art

[0002] With the rapid development of smart grid and Internet of Things technologies, the power system is accelerating towards intelligence, greenness and efficiency. The dual-mode communication method formed by combining power line carrier (PLC) with wireless communication technologies (such as Wi-Fi, LTE and LoRa, etc.) has become an indispensable means of data collection and transmission in power scenarios such as distributed photovoltaic power generation, demand response, orderly power management and energy Internet construction. However, traditional communication optimization methods usually do not fully consider the multi-terminal collaboration, dynamic load changes and real-time data transmission requirements in the power network, resulting in communication efficiency and reliability in complex power environments that are difficult to meet actual application requirements. In scenarios such as large-scale distributed energy access, dynamic power management and smart grid scheduling, dual-mode communication optimization still faces the following key challenges: First, existing methods fail to fully account for the uncertainties inherent in signal transmission during data transmission and substitution, leading to data loss or transmission delays, impacting system stability and data accuracy. While some methods have incorporated techniques such as data redundancy and transmission retries, these methods are unable to effectively improve data accuracy in highly volatile and unstable environments, increasing the burden and complexity of communication systems.

[0003] Second, existing methods lack effective mechanisms for inter-terminal collaboration, making it impossible to dynamically adjust and optimize data substitution parameters. Especially in multi-terminal environments, data substitution and optimization parameters cannot be shared across different terminals, resulting in an inability to achieve global optimization, which in turn affects data transmission efficiency and system responsiveness. Furthermore, existing technologies fail to effectively integrate the data substitution process across multiple terminals to achieve optimal decisions based on data characteristics. Summary of the Invention

[0004] In order to solve the above problems, the present invention proposes a dual-mode communication optimization method.

[0005] The technical solution of the present invention is: a dual-mode communication optimization method comprises the following steps: S1. Use the terminal to collect data in a continuous time period to obtain data in several windows, and discard the data in each window; S2. Use the confidence interval mutual verification method to verify the validity of the data of the discarded window; S3. After verifying the validity, perform parameter replacement and update to obtain the optimal data replacement parameters and achieve global parameter optimization of dual-mode communication.

[0006] Furthermore, S1 includes the following sub-steps: S11. Using the terminal to collect data for a continuous period of time, obtaining data for several windows; S12: Construct a first determination condition and a second determination condition, and discard the data of the window that does not meet the first determination condition or the second determination condition.

[0007] In S11, the terminal collects data and replaces data, and transmits the data back through HPLC or wireless. Each terminal collects data in a continuous time period, and each time period is a window. T w , extract the data within each window.

[0008] In S12, before completing data collection and data transmission, the terminal detects data similarity based on indicators such as sequence similarity and absolute value of sequence change within a multi-period window, and discards and replaces data based on two conditions: if the current window feature conforms to the linear trend of the previous and next windows, the original data is discarded; if the absolute value of the current window feature fluctuates slightly, the original data is discarded.

[0009] Furthermore, in S11, the terminal i No. w Window data x i ( T w ) is: ; in, x i ( T 1) Indicates the terminal i The first window T 1 data, x i ( T 2) Indicates the terminal i The second window T 2 data, x i ( T W ) indicates the terminal i No. W windows T W data, i ={1,2,..., I}, w ={1,2,..., W}, I Indicates the number of terminals, W Indicates the number of windows.

[0010] Furthermore, in S12, the expression of the first determination condition is: ; Where, Indicates terminal i The data similarity, represents a trend series, x i ( T w ) indicates the terminal i No. w windows T w data, i i (·) indicates terminal i The similarity function of V trend represents the similarity threshold, Δ x i ( T w ) represents the absolute value fluctuation of features between multiple windows, In S12, the expression of the second judgment condition is: ; Where, W 0 indicates the number of fluctuation detection windows, w 'Indicates the subscript of the adjacent window data, x i ( T w' ) represents the data of the adjacent window, V wave Indicates the fluctuation threshold.

[0011] Furthermore, in S2, the edge server evaluates the rationality of data discarding through the confidence interval mutual verification method. For the discarded window data, the trend fitting of other terminal data is used to generate alternative values, and compared with the original data for statistically significant differences. If the difference is within an acceptable range, it is determined that the data point can be safely discarded. Specifically: the confidence interval mutual verification method is used to generate the corresponding value. The data of the discarded window is safely discarded; among them, , represents the test statistic, Represents the trend-fitting model parameters s i and trend fitting data generated by other terminal data, x i ( T w ) indicates the terminal i No. w The data of the window,s i ( T w ) indicates data x i ( T w ), V char represents the confidence interval test threshold, Represents the trend-fitting model parameters s i The trend fitting function of x 1( T w ) indicates the terminal 1 w windows T w data, x 2( T w ) indicates the terminal 2 w windows T w data, x i+1 ( T w ) indicates the terminal i +1 w windows T W data, x I ( T w ) indicates the terminal I No. w windows T w data.

[0012] Furthermore, S3 includes the following sub-steps: S31. Build a replacement model for the terminal data; S32. At each iteration, the terminal i Parameters and terminals j Share, generate shared parameters; S33, using alternative models for terminals j generating a first substitute value, and generating a second substitute value using the shared parameter; S34. Using the terminal j The trend fitting model parameters and shared parameters are used to calculate the test statistics of the first alternative value and the test statistics of the second alternative value; S35, determine whether the test statistic of the first alternative value and the test statistic of the second alternative value meet If yes, then update the terminal parameters, otherwise do not update, and get the optimal data replacement parameters; where, represents the test statistic for the first alternative, Represents the test statistic for the second alternative.

[0013] Furthermore, in S32, the shared parameters The expression is: ; Where, Indicates the k Terminal during iteration i Parameters, Indicates the k -1 terminal at iteration j Parameters, α represents the shared parameter update weight.

[0014] Furthermore, in S34, the first replacement value The calculation formula is: ; Where, represents a substitution function based on a local data substitution model, x j ( T W ) indicates the terminal j No. w windows T w data; In S34, the second alternative value The calculation formula is: ; Where, Represents a surrogate function based on the shared data surrogate model after iterative updates.

[0015] Furthermore, in S35, the expression for updating the terminal parameters is: ; Where, Indicates the k Terminal during iteration j Parameters, Indicates the k -1 terminal at iteration j Parameters, represents shared parameters, represents the test statistic for the first alternative, Represents the test statistic for the second alternative.

[0016] The beneficial effects of the present invention are: (1) The present invention proposes a dual-mode communication optimization method, which significantly improves the effectiveness of data replacement by testing the rationality of terminal data discarding. First, the terminal detects data similarity based on indicators such as sequence similarity and absolute value of sequence change in a multi-period window, discards the collected data with small volatility and no characteristics in the window, and replaces it with characteristic data. Second, the edge server verifies the rationality of terminal data discarding based on the received terminal data through the confidence interval mutual verification method, calculates the data characteristic value using the reverse data of the remaining terminals, and improves the effectiveness of data replacement by comparing the characteristic value test, thereby reducing the risk of data loss and alleviating the retransmission burden of the dual-mode communication system. (2) The present invention optimizes the parameters related to the data replacement link based on the results of multi-terminal collaboration and mutual verification of confidence intervals, and realizes the sharing of parameters of the data replacement link of multiple terminals; first, a framework for multi-terminal collaborative work is constructed to determine the overall optimization goal of the system; second, based on the results of mutual verification of confidence intervals, the parameters related to the data replacement link are optimized; finally, the parameters of the data replacement link of multiple terminals are shared to obtain the optimal data replacement parameters; by calculating the gradient of the objective function to the current parameters, the parameters are updated, thereby realizing the collaborative optimization of the global parameters of dual-mode communication in a multi-terminal environment, improving the efficiency of data replacement, and realizing the efficient response of the dual-mode communication system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Flowchart of a method for optimizing dual-mode communication. DETAILED DESCRIPTION

[0018] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0019] like Figure 1 As shown, the present invention provides a dual-mode communication optimization method, comprising the following steps: S1. Use the terminal to collect data in a continuous time period to obtain data in several windows, and discard the data in each window; S2. Use the confidence interval mutual verification method to verify the validity of the data of the discarded window; S3. After verifying the validity, perform parameter replacement and update to obtain the optimal data replacement parameters and achieve global parameter optimization of dual-mode communication.

[0020] In this embodiment of the present invention, S1 includes the following sub-steps: S11. Using the terminal to collect data for a continuous period of time, obtaining data for several windows; S12: Construct a first determination condition and a second determination condition, and discard the data of the window that does not meet the first determination condition or the second determination condition.

[0021] In S11, the terminal collects data and replaces data, and transmits the data back through HPLC or wireless. Each terminal collects data in a continuous time period, and each time period is a window. T w , extract the data within each window.

[0022] In S12, before completing data collection and data transmission, the terminal detects data similarity based on indicators such as sequence similarity and absolute value of sequence change within a multi-period window, and discards and replaces data based on two conditions: if the current window feature conforms to the linear trend of the previous and next windows, the original data is discarded; if the absolute value of the current window feature fluctuates slightly, the original data is discarded.

[0023] In the embodiment of the present invention, in S11, the terminal i No. w Window data x i ( T w ) is: ; in, x i ( T 1) Indicates the terminal i The first window T 1 data, x i ( T 2) Indicates the terminal i The second window T 2 data, x i ( T W ) indicates the terminal i No. W windows T W data, i ={1,2,..., I}, w ={1,2,..., W}, I Indicates the number of terminals, W Indicates the number of windows.

[0024] In the embodiment of the present invention, in S12, the expression of the first determination condition is: ; Where, Indicates terminal i The data similarity, represents a trend series, xi ( T w ) indicates the terminal i No. w windows T w data, i i (·) indicates terminal i The similarity function of V trend represents the similarity threshold, Δ x i ( T w ) represents the absolute value fluctuation of features between multiple windows, In S12, the expression of the second judgment condition is: ; Where, W 0 indicates the number of fluctuation detection windows, w 'Indicates the subscript of the adjacent window data, x i ( T w' ) represents the data of the adjacent window, V wave Indicates the fluctuation threshold.

[0025] In the embodiment of the present invention, in S2, the edge server evaluates the rationality of data discarding by the confidence interval mutual verification method. For the discarded window data, the trend fitting of other terminal data is used to generate a replacement value, and compared with the original data for statistically significant differences. If the difference is within an acceptable range, it is determined that the data point can be safely discarded. Specifically: the confidence interval mutual verification method is used to generate a replacement value that meets the requirements of the original data. The data of the discarded window is safely discarded; among them, , represents the test statistic, Represents the trend-fitting model parameters s i and trend fitting data generated by other terminal data, x i ( T w ) indicates the terminal i No. w The data of the window, s i ( T w ) indicates data x i ( T w ), Vchar represents the confidence interval test threshold, Represents the trend-fitting model parameters s i The trend fitting function of x 1( T w ) indicates the terminal 1 w windows T w data, x 2( T w ) indicates the terminal 2 w windows T w data, x i+1 ( T w ) indicates the terminal i +1 w windows T W data, x I ( T w ) indicates the terminal I No. w windows T w data.

[0026] In this embodiment of the present invention, S3 includes the following sub-steps: S31. Build a replacement model for the terminal data; S32. At each iteration, the terminal i Parameters and terminals j Share, generate shared parameters; S33, using alternative models for terminals j generating a first substitute value, and generating a second substitute value using the shared parameter; S34. Using the terminal j The trend fitting model parameters and shared parameters are used to calculate the test statistics of the first alternative value and the test statistics of the second alternative value; S35, determine whether the test statistic of the first alternative value and the test statistic of the second alternative value meet If yes, then update the terminal parameters, otherwise do not update, and get the optimal data replacement parameters; where, represents the test statistic for the first alternative, Represents the test statistic for the second alternative.

[0027] In the embodiment of the present invention, in S32, the shared parameters The expression is: ; Where, Indicates the k Terminal during iteration i Parameters, Indicates the k -1 terminal at iteration j Parameters, α represents the shared parameter update weight.

[0028] In the embodiment of the present invention, in S34, the first replacement value The calculation formula is: ; Where, represents a substitution function based on a local data substitution model, x j ( T W ) indicates the terminal j No. w windows T w data; In S34, the second alternative value The calculation formula is: ; Where, Represents a surrogate function based on the shared data surrogate model after iterative updates.

[0029] In the embodiment of the present invention, in S35, the expression for updating the terminal parameters is: ; Where, Indicates the k Terminal during iteration j Parameters, Indicates the k -1 terminal at iteration j Parameters, represents shared parameters, represents the test statistic for the first alternative, Represents the test statistic for the second alternative.

[0030] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and it should be understood that the scope of protection of the present invention is not limited to such specific descriptions and embodiments. Those skilled in the art can make various other specific variations and combinations based on the technical teachings disclosed in the present invention without departing from the essence of the present invention, and such variations and combinations are still within the scope of protection of the present invention.

Claims

1. A dual-mode communication optimization method, characterized in that: The following steps are involved: S1. Use the terminal to collect power data for a continuous period of time, obtain data for several windows, and discard the data in each window; S2. Use the confidence interval mutual verification method to verify the validity of the data of the discarded window; S3. After verifying the validity, perform parameter replacement and update to obtain the optimal data replacement parameters and achieve global parameter optimization of dual-mode communication.

2. The dual-mode communication optimization method according to claim 1, characterized in that: The S1 includes the following sub-steps: S11. Using the terminal to collect data for a continuous period of time, obtaining data for several windows; S12: Construct a first determination condition and a second determination condition, and discard the data of the window that does not meet the first determination condition or the second determination condition.

3. The dual-mode communication optimization method according to claim 2, characterized in that: In the S11, the terminal i No. w Window data x i ( T w ) is: ； in, x i ( T 1) Indicates the terminal i The first window T 1 data, x i ( T 2) Indicates the terminal i The second window T 2 data, x i ( T W ) indicates the terminal i No. W windows T W data, i ={1,2,..., I }, w ={1,2,..., W }, I Indicates the number of terminals, W Indicates the number of windows.

4. The dual-mode communication optimization method according to claim 2, characterized in that: In S12, the expression of the first determination condition is: ； Where, Indicates terminal i The data similarity, represents a trend series, x i ( T w ) indicates the terminal i No. w windows T w data, θ i (·) indicates terminal i The similarity function of V trend represents the similarity threshold, Δ x i ( T w ) represents the absolute value fluctuation of features between multiple windows, In S12, the expression of the second determination condition is: ； Where, W 0 indicates the number of fluctuation detection windows, w 'Indicates the subscript of the adjacent window data, x i ( T w' ) represents the data of the adjacent window, V wave Indicates the fluctuation threshold.

5. The dual-mode communication optimization method according to claim 1, characterized in that: In S2, the confidence interval mutual verification method is used to verify the The data of the discarded window is safely discarded; among them, , represents the test statistic, Represents the trend-fitting model parameters σ i and trend fitting data generated by other terminal data, x i ( T w ) indicates the terminal i No. w The data of the window, s i ( T w ) indicates data x i ( T w ), V char represents the confidence interval test threshold, Represents the trend-fitting model parameters σ i The trend fitting function of x 1( T w ) indicates the terminal 1 w windows T w data, x 2( T w ) indicates the terminal 2 w windows T w data, x i+1 ( T w ) indicates the terminal i +1 w windows T W data, x I ( T w ) indicates the terminal I No. w windows T w data.

6. The dual-mode communication optimization method according to claim 1, characterized in that: The S3 includes the following sub-steps: S31. Build a replacement model for the terminal data; S32. At each iteration, the terminal i Parameters and terminals j Share, generate shared parameters; S33, using alternative models for terminals j generating a first substitute value, and generating a second substitute value using the shared parameter; S34. Using the terminal j The trend fitting model parameters and shared parameters are used to calculate the test statistics of the first alternative value and the test statistics of the second alternative value; S35, determine whether the test statistic of the first alternative value and the test statistic of the second alternative value meet If yes, then update the terminal parameters, otherwise do not update, and get the optimal data replacement parameters; where, represents the test statistic for the first alternative, Represents the test statistic for the second alternative.

7. The dual-mode communication optimization method according to claim 6, characterized in that: In S32, the shared parameters The expression is: ； Where, Indicates the k Terminal during iteration i Parameters, Indicates the k -1 terminal at iteration j Parameters, α represents the shared parameter update weight.

8. The dual-mode communication optimization method according to claim 6, characterized in that: In the S34, the first replacement value The calculation formula is: ； Where, represents a substitution function based on a local data substitution model, x j ( T W ) indicates the terminal j No. w windows T w data; In S34, the second replacement value The calculation formula is: ， Where, Represents a surrogate function based on the shared data surrogate model after iterative updates.

9. The dual-mode communication optimization method according to claim 6, characterized in that: In the above S35, the expression for updating the terminal parameters is: ； Where, Indicates the k Terminal during iteration j Parameters, Indicates the k -1 terminal at iteration j Parameters, represents shared parameters, represents the test statistic for the first alternative, Represents the test statistic for the second alternative.

Images