A flow prediction method, system and storage medium for electric power optical communication network

Abstract

The present invention discloses a flow prediction method, system, and storage medium for an electric power optical communication network. The method comprises: obtaining target flow-related data of a target electric power optical communication network to obtain various flow-related modal components; wherein the flow-related modal components reflect various factors that affect the target flow-related data, obtaining the relevant weights of each flow-related modal component, and then determining the flow key modal components; the first flow key modal component and the second flow key modal component obtained by division are sequentially input into a target communication flow prediction model constructed by long short-term memory network technology, obtaining component prediction results for each second flow key modal component, and obtaining target flow prediction results based on the relevant weights and corresponding component prediction results. The flow prediction method, system, and storage medium for an electric power optical communication network provided by the embodiments of the present invention improve the accuracy of flow prediction for an electric power optical communication network.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a flow prediction method, system and storage medium for a power optical communication network. Background Art

[0002] The power optical communication network is a dedicated fiber-optic communications infrastructure for power systems. Using optical fiber as the transmission medium, it carries the communication needs of power grid production, control, and management operations. By predicting and analyzing traffic trends within the power optical communication network, routing strategies can be dynamically adjusted or backup channels activated to prevent sudden traffic surges from causing network outages.

[0003] However, since the power optical communication network is easily affected by various factors, the existing technology directly predicts the traffic of the power optical communication network without considering the influence of external factors, resulting in low accuracy of traffic prediction for the power optical communication network.

[0004] It can be seen that how to improve the accuracy of traffic prediction for power optical communication networks has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] The present invention provides a traffic prediction method, system and storage medium for an electric power optical communication network to solve the technical problem that the electric power optical communication network is easily affected by various factors, and the existing technology directly predicts the traffic of the electric power optical communication network without considering the influence of external factors, resulting in low accuracy of traffic prediction for the electric power optical communication network.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a traffic prediction method for a power optical communication network.

[0007] Obtaining target flow-related data of a target electric power optical communication network; wherein the target flow-related data includes flow data and external influence data; performing modal decomposition on each target flow-related sequence data constructed from the target flow-related data to obtain each flow-related modal component of each target flow-related data; wherein the flow-related modal component reflects each factor that affects the target flow-related data;

[0008] Determining a corresponding relevant weight based on an importance analysis result of each of the flow-related modal components; determining a flow key modal component of each of the target flow-related data based on the relevant weights of each of the flow-related modal components of each of the target flow-related data;

[0009] Dividing all the traffic key modal components into a data set to obtain a first traffic key modal component and a second traffic key modal component; sequentially inputting the first traffic key modal component and the second traffic key modal component into a target communication traffic prediction model constructed using long short-term memory network technology to obtain a component prediction result for each of the second traffic key modal components;

[0010] Based on the relevant weight of each of the second traffic key modal components and the corresponding component prediction result, a target traffic prediction result of the target electric power optical communication network is obtained.

[0011] As one preferred solution, determining the flow key modal component of each target flow related data based on the relevant weights of the respective flow related modal components of each target flow related data includes:

[0012] sorting the relevant weights of all the flow-related modal components of each target flow-related data in descending order to obtain a component weight sequence of each target flow-related data;

[0013] Inputting the relevant weight of each of the flow-related modal components in the component weight sequence into a cumulative contribution calculation expression to calculate a cumulative contribution sequence corresponding to the component weight sequence; wherein the cumulative contribution calculation expression is designed to sequentially accumulate the results of descending arrangement of the relevant weights of all the flow-related modal components of each of the target flow-related data;

[0014] The first element in the cumulative contribution sequence that is greater than a preset contribution rate threshold is used as a segmentation point to obtain the key modal component of the flow of each target flow-related data.

[0015] As one preferred solution, the external impact data at least includes grid load data, optical fiber status data, electromagnetic field data, and temperature and humidity data.

[0016] As one preferred solution, determining the corresponding relevant weight based on the importance analysis result of each of the flow-related modal components includes:

[0017] Inputting all the flow-related modal components of each target flow-related data into a random forest algorithm to calculate the importance score of each flow-related modal component;

[0018] The importance scores of all the flow-related modal components of each target flow-related data are normalized to obtain relevant weights of the respective flow-related modal components.

[0019] As one of the preferred solutions, the cumulative contribution calculation expression is designed as:

[0020]

[0021] in, is the i-th element in the cumulative contribution sequence, is the jth element in the component weight sequence.

[0022] As one preferred solution, the step of sequentially inputting the first traffic-critical modal component and the second traffic-critical modal component into a target communication traffic prediction model to obtain a component prediction result of each second traffic-critical modal component includes:

[0023] Inputting the first traffic key modal component obtained from the historical target traffic related data into the first target communication traffic prediction model for prediction training;

[0024] The second target communication traffic prediction model obtained by the prediction training is used to perform prediction analysis on the second traffic key modal components obtained from the real-time target traffic related data to obtain a component prediction result of each of the second traffic key modal components.

[0025] As one preferred solution, the method further comprises:

[0026] The parameters of the first target communication flow prediction model are feedback optimized by using a sparrow search algorithm during the prediction training process to obtain a target parameter combination of the second target communication flow prediction model.

[0027] As one preferred solution, the method further comprises:

[0028] Calculating various performance evaluation indicators of the second target communication traffic prediction model based on the difference characteristics between the target traffic prediction result and the corresponding target monitoring result of the real-time target traffic related data;

[0029] Feedback optimization is performed on the target parameter combination of the second target communication traffic prediction model using all the performance evaluation indicators.

[0030] As one of the preferred solutions, the performance evaluation indicators include at least root mean square error, mean absolute error, mean absolute percentage error and determination coefficient.

[0031] Another embodiment of the present invention provides a traffic prediction system for a power optical communication network, comprising:

[0032] a data modal decomposition module, configured to obtain target flow-related data of a target electric power optical communication network; wherein the target flow-related data includes flow data and external influence data; perform modal decomposition on each target flow-related sequence data constructed from the target flow-related data to obtain each flow-related modal component of each target flow-related data; wherein the flow-related modal component reflects each factor that affects the target flow-related data;

[0033] a data modality screening module, configured to determine a corresponding relevant weight based on an importance analysis result of each of the flow-related modal components; and determine a flow key modal component of each of the target flow-related data based on the relevant weights of each of the flow-related modal components of each of the target flow-related data;

[0034] A key modal prediction module is configured to divide the data set of all the traffic key modal components to obtain a first traffic key modal component and a second traffic key modal component; input the first traffic key modal component and the second traffic key modal component into a target communication traffic prediction model constructed using long short-term memory network technology in sequence to obtain a component prediction result of each second traffic key modal component;

[0035] A prediction result reconstruction module is used to obtain a target traffic prediction result of the target electric power optical communication network based on the relevant weight of each second traffic key modal component and the corresponding component prediction result.

[0036] As one preferred solution, determining the flow key modal component of each target flow related data based on the relevant weights of the respective flow related modal components of each target flow related data includes:

[0037] sorting the relevant weights of all the flow-related modal components of each target flow-related data in descending order to obtain a component weight sequence of each target flow-related data;

[0038] Inputting the relevant weight of each of the flow-related modal components in the component weight sequence into a cumulative contribution calculation expression to calculate a cumulative contribution sequence corresponding to the component weight sequence; wherein the cumulative contribution calculation expression is designed to sequentially accumulate the results of descending arrangement of the relevant weights of all the flow-related modal components of each of the target flow-related data;

[0039] The first element in the cumulative contribution sequence that is greater than a preset contribution rate threshold is used as a segmentation point to obtain the key modal component of the flow of each target flow-related data.

[0040] As one preferred solution, the external impact data at least includes grid load data, optical fiber status data, electromagnetic field data, and temperature and humidity data.

[0041] As one preferred solution, determining the corresponding relevant weight based on the importance analysis result of each of the flow-related modal components includes:

[0042] Inputting all the flow-related modal components of each target flow-related data into a random forest algorithm to calculate the importance score of each flow-related modal component;

[0043] The importance scores of all the flow-related modal components of each target flow-related data are normalized to obtain relevant weights of the respective flow-related modal components.

[0044] As one of the preferred solutions, the cumulative contribution calculation expression is designed as:

[0045]

[0046] in, is the i-th element in the cumulative contribution sequence, is the jth element in the component weight sequence.

[0047] As one preferred solution, the step of sequentially inputting the first traffic-critical modal component and the second traffic-critical modal component into a target communication traffic prediction model to obtain a component prediction result of each second traffic-critical modal component includes:

[0048] Inputting the first traffic key modal component obtained from the historical target traffic related data into the first target communication traffic prediction model for prediction training;

[0049] The second target communication traffic prediction model obtained by the prediction training is used to perform prediction analysis on the second traffic key modal components obtained from the real-time target traffic related data to obtain a component prediction result of each of the second traffic key modal components.

[0050] As one preferred solution, the system further includes:

[0051] The parameters of the first target communication flow prediction model are feedback optimized by using a sparrow search algorithm during the prediction training process to obtain a target parameter combination of the second target communication flow prediction model.

[0052] As one preferred solution, the system further includes:

[0053] Calculating various performance evaluation indicators of the second target communication traffic prediction model based on the difference characteristics between the target traffic prediction result and the corresponding target monitoring result of the real-time target traffic related data;

[0054] Feedback optimization is performed on the target parameter combination of the second target communication traffic prediction model using all the performance evaluation indicators.

[0055] As one of the preferred solutions, the performance evaluation indicators include at least root mean square error, mean absolute error, mean absolute percentage error and determination coefficient.

[0056] Yet another embodiment of the present invention provides a computer-readable storage medium storing a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the traffic prediction method for the electric power optical communication network as described above is implemented.

[0057] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0058] The target flow-related data of the target electric power optical communication network is obtained, while considering the flow data and external influence data; each target flow-related sequence data constructed by the target flow-related data is modally decomposed to obtain each flow-related modal component of each target flow-related data, and the mixed signal is separated into independent modal components through modal decomposition, which solves the problem of traditional methods ignoring external factors, and each modal component corresponds to a potential influencing factor; by screening the key modal components of the flow, the interference of the noise components is avoided, which can reduce the error of subsequent flow prediction of the target electric power optical communication network and improve the accuracy of the flow prediction of the electric power optical communication network; after dividing the data set, the long short-term memory network technology is used to predict in stages, the first key modal component of the flow obtained from the historical data is used to train and optimize the basic model, and the second key modal component of the flow obtained from the real-time data is used for real-time prediction, and different weights are set for different component prediction results according to the component importance analysis results to obtain the target flow prediction result of the target electric power optical communication network, which further improves the accuracy of the flow prediction of the electric power optical communication network. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a flow chart of a method for traffic prediction in a power optical communication network according to one embodiment of the present invention;

[0060] Figure 2 This is a structural block diagram of a traffic prediction system for an electric power optical communication network in one embodiment of the present invention. DETAILED DESCRIPTION

[0061] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0062] In the description of this application, the terms "first," "second," "third," etc. are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first," "second," "third," etc. may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0063] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be a communication between the two components. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are for illustrative purposes only, and do not indicate or imply that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0064] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meanings as those commonly understood by those skilled in the art. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. Those skilled in the art will understand the specific meanings of the above terms in this application in specific circumstances.

[0065] An embodiment of the present invention provides a method for predicting traffic flow in a power optical communication network. Figure 1 , Figure 1 The flowchart shows a method for traffic prediction of a power optical communication network in one embodiment of the present invention.

[0066] A flow chart of a method for traffic prediction in a power optical communication network in one embodiment of the present invention includes the following steps S1 to S4, which are specifically as follows:

[0067] Step S1: Obtain target flow-related data of the target power optical communication network; wherein the target flow-related data includes flow data and external influence data; perform modal decomposition on each target flow-related sequence data constructed by the target flow-related data to obtain each flow-related modal component of each target flow-related data; wherein the flow-related modal component reflects each factor that affects the target flow-related data.

[0068] Step S2: Based on the importance analysis result of each flow-related modal component, determine the corresponding relevant weight; based on the relevant weight of each flow-related modal component of each target flow-related data, determine the flow key modal component of each target flow-related data.

[0069] Step S3: Divide the data set of all traffic key modal components to obtain the first traffic key modal component and the second traffic key modal component; input the first traffic key modal component and the second traffic key modal component into the target communication traffic prediction model constructed by long short-term memory network technology in sequence to obtain the component prediction result of each second traffic key modal component.

[0070] Step S4: Based on the relevant weight of each second traffic key modal component and the corresponding component prediction result, a target traffic prediction result of the target power optical communication network is obtained.

[0071] It should be noted that modal decomposition is a method that decomposes complex signals or systems into several inherent modes or characteristic vibration modes. It is widely used in signal processing, structural dynamics, fluid mechanics and other fields. In power optical communication networks, it can be used to analyze the multi-scale characteristics of time series data such as traffic and electromagnetic interference; long short-term memory network technology is a special recurrent neural network that is good at modeling long-term dependencies of time series data and can be used for prediction. Modal decomposition and long short-term memory network technologies are both well-known technologies and will not be elaborated here in this embodiment.

[0072] The method for predicting traffic flow in a power optical communication network provided by an embodiment of the present invention has the following advantages over the prior art:

[0073] The target flow-related data of the target electric power optical communication network is obtained, while considering the flow data and external influence data; each target flow-related sequence data constructed by the target flow-related data is modally decomposed to obtain each flow-related modal component of each target flow-related data, and the mixed signal is separated into independent modal components through modal decomposition, which solves the problem of traditional methods ignoring external factors, and each modal component corresponds to a potential influencing factor; by screening the key modal components of the flow, the interference of the noise components is avoided, which can reduce the error of subsequent flow prediction of the target electric power optical communication network and improve the accuracy of the flow prediction of the electric power optical communication network; after dividing the data set, the long short-term memory network technology is used to predict in stages, the first key modal component of the flow obtained from the historical data is used to train and optimize the basic model, and the second key modal component of the flow obtained from the real-time data is used for real-time prediction, and different weights are set for different component prediction results according to the component importance analysis results to obtain the target flow prediction result of the target electric power optical communication network, which further improves the accuracy of the flow prediction of the electric power optical communication network.

[0074] In one embodiment, the external impact data in step S1 at least includes grid load data, optical fiber status data, electromagnetic field data, and temperature and humidity data.

[0075] It should be noted that when the grid load increases, the power communication network needs to transmit more monitoring, protection and control instructions, resulting in an increase in traffic; bending or aging of optical fibers will lead to an increase in bit error rates, and the retransmission mechanism will increase redundant traffic; strong electromagnetic fields will introduce noise and reduce the signal-to-noise ratio, which will lead to an increase in the optical communication bit error rate, and the retransmission mechanism will increase redundant traffic; high temperatures may cause laser wavelength deviation and increase optical power loss, and increased humidity may aggravate microbend losses, which will lead to an increase in bit error rates and increase redundant traffic.

[0076] In one embodiment, in step S2, based on the importance analysis result of each flow-related modal component, determining the corresponding correlation weight includes:

[0077] All flow-related modal components of each target flow-related data are input into the random forest algorithm to calculate the importance score of each flow-related modal component; the importance scores of all flow-related modal components of each target flow-related data are normalized to obtain the relevant weights of each flow-related modal component.

[0078] It should be noted that the random forest algorithm is a machine learning algorithm based on ensemble learning. It improves the accuracy and robustness of the model by constructing multiple decision trees and integrating their prediction results. The greater the contribution of a feature to the model prediction, the higher its importance. The random forest algorithm is a well-known technology and will not be described in detail in this embodiment.

[0079] This embodiment provides a method for predicting traffic in an electric power optical communication network. By setting different weights based on the importance scores of various traffic-related modal components, it is possible to clearly distinguish core factors and thereby improve the accuracy of subsequent traffic predictions for the electric power optical communication network.

[0080] In one embodiment, step S2 determines the traffic key modal component of each target traffic related data based on the relevant weights of each traffic related modal component of each target traffic related data, including steps S201 to S203.

[0081] Step S201: sorting the relevant weights of all flow-related modal components of each target flow-related data in descending order to obtain a component weight sequence of each target flow-related data;

[0082] Step S202: Inputting the relevant weight of each flow-related modal component in the component weight sequence into a cumulative contribution calculation expression to calculate a cumulative contribution sequence corresponding to the component weight sequence; wherein the cumulative contribution calculation expression is designed to sequentially accumulate the results of descending arrangement of the relevant weights of all flow-related modal components of each target flow-related data;

[0083] Step S203: taking the first element in the cumulative contribution sequence that is greater than a preset contribution rate threshold as a segmentation point, and obtaining the key modal component of the flow of each target flow-related data.

[0084] In one embodiment, the cumulative contribution calculation expression in step S202 is designed as:

[0085]

[0086] in, is the i-th element in the cumulative contribution sequence, is the jth element in the component weight sequence.

[0087] This embodiment provides a traffic prediction method for an electric power optical communication network. By sorting the relevant weights of all traffic-related modal components of each target traffic-related data in descending order, the core traffic-related modal components are clearly distinguished from the secondary traffic-related modal components, providing ordered input for subsequent cumulative contribution calculations. A recursive cumulative contribution calculation expression is used to intuitively display the overall contribution of the first N traffic-related modal components, avoiding the subjectivity of manual experience threshold setting.

[0088] In one embodiment, in step S3, the first traffic-critical modal component and the second traffic-critical modal component are sequentially input into the target communication traffic prediction model to obtain a component prediction result of each second traffic-critical modal component, including:

[0089] Inputting the first traffic key modal component obtained from the historical target traffic related data into the first target communication traffic prediction model for prediction training;

[0090] The second target communication traffic prediction model obtained by prediction training is used to perform prediction analysis on the second traffic key modal components obtained from the real-time target traffic related data to obtain component prediction results of each second traffic key modal component.

[0091] In one embodiment, a sparrow search algorithm is used to perform feedback optimization on the parameters of the first target communication traffic prediction model during the prediction training process to obtain a target parameter combination of the second target communication traffic prediction model.

[0092] This embodiment provides a method for traffic prediction in an electric power optical communication network. After dividing the data set, the method uses long short-term memory network technology to perform staged predictions. The method fully exploits the long-term patterns of the first traffic key modal component obtained from historical data, trains and optimizes the basic model, and uses the optimized model to perform real-time predictions on the second traffic key modal component obtained from real-time data, thereby improving the accuracy of traffic prediction for the electric power optical communication network.

[0093] In one embodiment, various performance evaluation indicators of the second target communication traffic prediction model are calculated based on the difference characteristics between the target traffic prediction results of real-time target traffic related data and the corresponding target monitoring results; and the target parameter combination of the second target communication traffic prediction model is feedback optimized using all performance evaluation indicators.

[0094] In one embodiment, the performance evaluation indicators include at least root mean square error, mean absolute error, mean absolute percentage error, and coefficient of determination.

[0095] Another embodiment of the present invention provides a traffic prediction system for an electric power optical communication network. Figure 2 , Figure 2 The figure shows a structural block diagram of a traffic prediction system for a power optical communication network according to one embodiment of the present invention, comprising:

[0096] The data modal decomposition module 11 is configured to obtain target flow-related data of the target electric power optical communication network, wherein the target flow-related data includes flow data and external influence data; perform modal decomposition on each target flow-related sequence data constructed from the target flow-related data to obtain each flow-related modal component of each target flow-related data; wherein the flow-related modal component reflects each factor that affects the target flow-related data;

[0097] The data modality screening module 12 is configured to determine a corresponding relevant weight based on the importance analysis result of each flow-related modal component; and determine a flow key modal component of each target flow-related data based on the relevant weight of each flow-related modal component of each target flow-related data;

[0098] The key mode prediction module 13 is used to divide the data set of all traffic key mode components to obtain a first traffic key mode component and a second traffic key mode component; the first traffic key mode component and the second traffic key mode component are sequentially input into the target communication traffic prediction model constructed by the long short-term memory network technology to obtain a component prediction result of each second traffic key mode component;

[0099] The prediction result reconstruction module 14 is configured to obtain a target traffic prediction result of the target electric power optical communication network based on the relevant weight of each second traffic key modal component and the corresponding component prediction result.

[0100] In one embodiment, the external impact data in the data modal decomposition module 11 includes at least grid load data, optical fiber status data, electromagnetic field data, and temperature and humidity data.

[0101] It should be noted that when the grid load increases, the power communication network needs to transmit more monitoring, protection and control instructions, resulting in an increase in traffic; bending or aging of optical fibers will lead to an increase in bit error rates, and the retransmission mechanism will increase redundant traffic; strong electromagnetic fields will introduce noise and reduce the signal-to-noise ratio, which will lead to an increase in the optical communication bit error rate, and the retransmission mechanism will increase redundant traffic; high temperatures may cause laser wavelength deviation and increase optical power loss, and increased humidity may aggravate microbend losses, which will lead to an increase in bit error rates and increase redundant traffic.

[0102] In one embodiment, the data modality screening module 12 determines the corresponding relevant weight based on the importance analysis result of each traffic-related modal component, including:

[0103] All flow-related modal components of each target flow-related data are input into the random forest algorithm to calculate the importance score of each flow-related modal component; the importance scores of all flow-related modal components of each target flow-related data are normalized to obtain the relevant weights of each flow-related modal component.

[0104] It should be noted that the random forest algorithm is a machine learning algorithm based on ensemble learning. It improves the accuracy and robustness of the model by constructing multiple decision trees and integrating their prediction results. The greater the contribution of a feature to the model prediction, the higher its importance. The random forest algorithm is a well-known technology and will not be described in detail in this embodiment.

[0105] This embodiment provides a traffic prediction system for an electric power optical communication network. By setting different weights according to the importance scores of various traffic-related modal components, it is possible to clearly distinguish core factors and thereby improve the accuracy of subsequent traffic predictions for the electric power optical communication network.

[0106] In one embodiment, the data modality screening module 12 determines the traffic key modal component of each target traffic-related data based on the relevant weights of each traffic-related modal component of each target traffic-related data, including:

[0107] Sort the relevant weights of all flow-related modal components of each target flow-related data in descending order to obtain a component weight sequence of each target flow-related data;

[0108] The relevant weight of each flow-related modal component in the component weight sequence is input into the cumulative contribution calculation expression to calculate the cumulative contribution sequence corresponding to the component weight sequence; wherein the cumulative contribution calculation expression is designed to accumulate the descending order of the relevant weights of all flow-related modal components of each target flow-related data;

[0109] The first element in the cumulative contribution sequence that is greater than the preset contribution rate threshold is used as the split point to obtain the key modal component of the flow rate of each target flow-related data.

[0110] In one embodiment, the cumulative contribution calculation expression is designed as:

[0111]

[0112] in, is the i-th element in the cumulative contribution sequence, is the jth element in the component weight sequence.

[0113] This embodiment provides a traffic prediction system for an electric power optical communication network. The system clearly distinguishes between core traffic-related modal components and secondary traffic-related modal components by sorting the relevant weights of all traffic-related modal components of each target traffic-related data in descending order, providing ordered input for subsequent cumulative contribution calculations. The system uses a recursive cumulative contribution calculation expression to intuitively display the overall contribution of the first N traffic-related modal components, avoiding the subjectivity of manual experience threshold setting.

[0114] In one embodiment, the key modal prediction module 13 sequentially inputs the first traffic key modal component and the second traffic key modal component into the target communication traffic prediction model to obtain a component prediction result of each second traffic key modal component, including:

[0115] Inputting the first traffic key modal component obtained from the historical target traffic related data into the first target communication traffic prediction model for prediction training;

[0116] The second target communication traffic prediction model obtained by prediction training is used to perform prediction analysis on the second traffic key modal components obtained from the real-time target traffic related data to obtain component prediction results of each second traffic key modal component.

[0117] In one embodiment, a sparrow search algorithm is used to perform feedback optimization on the parameters of the first target communication traffic prediction model during the prediction training process to obtain a target parameter combination of the second target communication traffic prediction model.

[0118] This embodiment provides a traffic prediction system for an electric power optical communication network. After dividing the data set, it uses long-short-term memory network technology to perform staged predictions. The first traffic key modal component obtained from historical data fully explores long-term patterns, trains and optimizes the basic model, and uses the optimized model to perform real-time predictions on the second traffic key modal component obtained from real-time data, thereby improving the accuracy of traffic prediction for the electric power optical communication network.

[0119] In one embodiment, various performance evaluation indicators of the second target communication traffic prediction model are calculated based on the difference characteristics between the target traffic prediction results of real-time target traffic related data and the corresponding target monitoring results; and the target parameter combination of the second target communication traffic prediction model is feedback optimized using all performance evaluation indicators.

[0120] In one embodiment, the performance evaluation indicators include at least root mean square error, mean absolute error, mean absolute percentage error, and coefficient of determination.

[0121] Yet another embodiment of the present invention provides a computer-readable storage medium storing a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the steps in the traffic prediction method for the electric power optical communication network as described above are implemented.

[0122] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for predicting traffic flow in an electric power optical communication network, characterized in that: The method comprises: Obtaining target flow-related data of a target electric power optical communication network; wherein the target flow-related data includes flow data and external influence data; performing modal decomposition on each target flow-related sequence data constructed from the target flow-related data to obtain each flow-related modal component of each target flow-related data; wherein the flow-related modal component reflects each factor that affects the target flow-related data; Determining a corresponding relevant weight based on an importance analysis result of each of the flow-related modal components; determining a flow key modal component of each of the target flow-related data based on the relevant weights of each of the flow-related modal components of each of the target flow-related data; Dividing all the traffic key modal components into a data set to obtain a first traffic key modal component and a second traffic key modal component; sequentially inputting the first traffic key modal component and the second traffic key modal component into a target communication traffic prediction model constructed using long short-term memory network technology to obtain a component prediction result for each of the second traffic key modal components; Obtaining a target traffic prediction result of the target electric power optical communication network based on the relevant weight of each second traffic key modal component and the corresponding component prediction result; The determining of the key flow modal component of each target flow related data based on the relevant weights of the respective flow related modal components of each target flow related data comprises: sorting the relevant weights of all the flow-related modal components of each target flow-related data in descending order to obtain a component weight sequence of each target flow-related data; Inputting the relevant weight of each of the flow-related modal components in the component weight sequence into a cumulative contribution calculation expression to calculate a cumulative contribution sequence corresponding to the component weight sequence; wherein the cumulative contribution calculation expression is designed to sequentially accumulate the results of descending arrangement of the relevant weights of all the flow-related modal components of each of the target flow-related data; The first element in the cumulative contribution sequence that is greater than a preset contribution rate threshold is used as a segmentation point to obtain the key modal component of the flow of each target flow-related data.

2. The method for predicting traffic flow in a power optical communication network according to claim 1, characterized in that: The external impact data at least includes grid load data, optical fiber status data, electromagnetic field data, and temperature and humidity data.

3. The method for predicting traffic flow in a power optical communication network according to claim 1, characterized in that: The determining of the corresponding relevant weight based on the importance analysis result of each of the flow-related modal components includes: Inputting all the flow-related modal components of each target flow-related data into a random forest algorithm to calculate the importance score of each flow-related modal component; The importance scores of all the flow-related modal components of each target flow-related data are normalized to obtain relevant weights of the respective flow-related modal components.

4. The method for predicting traffic flow in a power optical communication network according to claim 1, characterized in that: The cumulative contribution calculation expression is designed as: in, is the i-th element in the cumulative contribution sequence, is the jth element in the component weight sequence.

5. The method for predicting traffic flow in a power optical communication network according to claim 1, characterized in that: The step of sequentially inputting the first traffic critical modal component and the second traffic critical modal component into a target communication traffic prediction model to obtain a component prediction result of each second traffic critical modal component includes: Inputting the first traffic key modal component obtained from the historical target traffic related data into the first target communication traffic prediction model for prediction training; The second target communication traffic prediction model obtained by the prediction training is used to perform prediction analysis on the second traffic key modal components obtained from the real-time target traffic related data to obtain a component prediction result of each of the second traffic key modal components.

6. The method for predicting traffic flow in a power optical communication network according to claim 5, characterized in that: The method further comprises: The parameters of the first target communication flow prediction model are feedback optimized by using a sparrow search algorithm during the prediction training process to obtain a target parameter combination of the second target communication flow prediction model.

7. The method for predicting traffic flow in a power optical communication network according to claim 6, characterized in that: The method further comprises: Calculating various performance evaluation indicators of the second target communication traffic prediction model based on the difference characteristics between the target traffic prediction result and the corresponding target monitoring result of the real-time target traffic related data; Feedback optimization is performed on the target parameter combination of the second target communication traffic prediction model using all the performance evaluation indicators.

8. The method for predicting traffic flow in a power optical communication network according to claim 7, characterized in that: The performance evaluation indicators include at least root mean square error, mean absolute error, mean absolute percentage error and determination coefficient.

9. A traffic prediction system for an electric power optical communication network, characterized in that: The system comprises: a data modal decomposition module, configured to obtain target flow-related data of a target electric power optical communication network; wherein the target flow-related data includes flow data and external influence data; perform modal decomposition on each target flow-related sequence data constructed from the target flow-related data to obtain each flow-related modal component of each target flow-related data; wherein the flow-related modal component reflects each factor that affects the target flow-related data; a data modality screening module, configured to determine a corresponding relevant weight based on an importance analysis result of each of the flow-related modal components; and determine a flow key modal component of each of the target flow-related data based on the relevant weights of each of the flow-related modal components of each of the target flow-related data; A key modal prediction module is configured to divide the data set of all the traffic key modal components to obtain a first traffic key modal component and a second traffic key modal component; input the first traffic key modal component and the second traffic key modal component into a target communication traffic prediction model constructed using long short-term memory network technology in sequence to obtain a component prediction result of each second traffic key modal component; A prediction result reconstruction module for obtaining a target flow prediction result of the target power optical communication network based on the relevant weight of each of the second flow key modal components and the corresponding component prediction result; The determining of the key flow modal component of each target flow related data based on the relevant weights of the respective flow related modal components of each target flow related data comprises: sorting the relevant weights of all the flow-related modal components of each target flow-related data in descending order to obtain a component weight sequence of each target flow-related data; Inputting the relevant weight of each of the flow-related modal components in the component weight sequence into a cumulative contribution calculation expression to calculate a cumulative contribution sequence corresponding to the component weight sequence; wherein the cumulative contribution calculation expression is designed to sequentially accumulate the results of descending arrangement of the relevant weights of all the flow-related modal components of each of the target flow-related data; The first element in the cumulative contribution sequence that is greater than a preset contribution rate threshold is used as a segmentation point to obtain the key modal component of the flow of each target flow-related data.

10. The traffic prediction system for a power optical communication network according to claim 9, characterized in that: The external impact data at least includes grid load data, optical fiber status data, electromagnetic field data, and temperature and humidity data.

11. The traffic prediction system for a power optical communication network according to claim 9, characterized in that: The determining of the corresponding relevant weight based on the importance analysis result of each of the flow-related modal components includes: Inputting all the flow-related modal components of each target flow-related data into a random forest algorithm to calculate the importance score of each flow-related modal component; The importance scores of all the flow-related modal components of each target flow-related data are normalized to obtain relevant weights of the respective flow-related modal components.

12. The traffic prediction system for a power optical communication network according to claim 9, characterized in that: The cumulative contribution calculation expression is designed as: in, is the i-th element in the cumulative contribution sequence, is the jth element in the component weight sequence.

13. The traffic prediction system for a power optical communication network according to claim 9, characterized in that: The step of sequentially inputting the first traffic critical modal component and the second traffic critical modal component into a target communication traffic prediction model to obtain a component prediction result of each second traffic critical modal component includes: Inputting the first traffic key modal component obtained from the historical target traffic related data into the first target communication traffic prediction model for prediction training; The second target communication traffic prediction model obtained by the prediction training is used to perform prediction analysis on the second traffic key modal components obtained from the real-time target traffic related data to obtain a component prediction result of each of the second traffic key modal components.

14. A traffic prediction system for a power optical communication network according to claim 13, characterized in that: The system further comprises: The parameters of the first target communication flow prediction model are feedback optimized by using a sparrow search algorithm during the prediction training process to obtain a target parameter combination of the second target communication flow prediction model.

15. The traffic prediction system for a power optical communication network according to claim 14, characterized in that: The system further comprises: Calculating various performance evaluation indicators of the second target communication traffic prediction model based on the difference characteristics between the target traffic prediction result and the corresponding target monitoring result of the real-time target traffic related data; Feedback optimization is performed on the target parameter combination of the second target communication traffic prediction model using all the performance evaluation indicators.

16. A traffic prediction system for an electric power optical communication network according to claim 15, characterized in that: The performance evaluation indicators include at least root mean square error, mean absolute error, mean absolute percentage error and determination coefficient.

17. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the traffic prediction method for the power optical communication network according to any one of claims 1 to 8 is implemented.

Images