Alternative line evaluation method, device and equipment for single-fiber bidirectional wavelength division system

Abstract

The invention relates to an alternative line evaluation method, device and equipment for a single-fiber bidirectional wavelength division system. The method comprises the steps of predicting a predicted environment parameter sequence of a current time point according to historical environment parameter sequences corresponding to M historical time points, and obtaining an environment parameter variation sequence according to the predicted environment parameter sequence of the current time point and the historical environment parameter sequence corresponding to the Mth historical time point, the correction parameter sequence is obtained through mapping of the environment parameter variable quantity sequence, the prediction line parameter sequence is corrected, the influence of the environment parameters on the line parameters is comprehensively considered, the accuracy of line parameter prediction is improved, fault prediction is carried out according to the target parameter matrix, the environment parameters and the line parameters at multiple time points are comprehensively considered, and the accuracy of line parameter prediction is improved. The accuracy of fault prediction is improved, and the accuracy of alternative line evaluation is further improved.

Description

Technical Field

[0001] The present invention is applicable to the field of optical communication technologies, and particularly relates to a method, device, and equipment for evaluating alternative lines in a single-fiber bidirectional wavelength division system. Background Art

[0002] A single-fiber bidirectional wavelength division system is a wavelength division multiplexing technology system that realizes bidirectional optical signal transmission in a single optical fiber. Generally, to ensure the stability and continuity of data transmission, it is necessary to monitor the transmission status of the optical fiber in real time and automatically switch to a backup line when a fault occurs in the optical path to ensure that data transmission is not interrupted. This function is usually achieved through an optical switch, which can complete the switching within milliseconds.

[0003] In the scenario of alternative line switching, it is necessary to automatically monitor parameters such as chromatic dispersion and attenuation of the optical cable, and determine the optimal backup line based on these parameters to ensure that the optimal backup line can be selected for switching when a fault occurs.

[0004] However, the evaluation of alternative lines usually needs to consider multiple parameters such as optical power, wavelength, bit error rate, and polarization mode dispersion. These parameters are interrelated and interact with each other. The state of the line also changes continuously over time, affected by various factors such as environmental temperature, humidity, fiber aging, and equipment performance degradation, resulting in a low accuracy of alternative line evaluation. In addition, there is uncertainty in the fault prediction of alternative lines, further reducing the accuracy of alternative line evaluation.

[0005] Therefore, how to improve the accuracy of alternative line evaluation has become an urgent problem to be solved. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide a method, device, and equipment for evaluating alternative lines in a single-fiber bidirectional wavelength division system to solve the problem.

[0007] In a first aspect, a method for evaluating alternative lines in a single-fiber bidirectional wavelength division system is provided. The method includes: Obtaining a historical environmental parameter sequence and a historical line parameter sequence respectively corresponding to an initial alternative line at M historical time points; Inputting the historical environmental parameter sequences respectively corresponding to the M historical time points into a trained environmental parameter prediction model to obtain a predicted environmental parameter sequence at the current time point; Obtaining an environmental parameter change amount sequence based on the predicted environmental parameter sequence at the current time point and the historical environmental parameter sequence corresponding to the Mth historical time point; Inputting the environmental parameter change amount sequence and the historical line parameter sequence corresponding to the Mth historical time point into a trained correction parameter mapping model to obtain a target correction parameter sequence; Input the historical line parameter sequences corresponding to M historical time points into the trained line parameter prediction model to obtain the predicted line parameter sequence at the current time point; According to the target correction parameter sequence and the predicted line parameter sequence, obtain the target line parameter sequence at the current time point; According to the historical line parameter sequences and historical environment parameter sequences corresponding to M historical time points, the target line parameter sequence and predicted environment parameter sequence at the current time point, and the preset sequence selection vector, determine the target parameter matrix; Input the target parameter matrix into the trained fault prediction model to obtain the fault prediction result at the current time point; If the current time point meets the first preset condition and the fault prediction result at the current time point meets the second preset condition, determine the initial alternative line as the target alternative line.

[0008] In a second aspect, there is provided an alternative line evaluation device for a single-fiber bidirectional wavelength division system, the device comprising: A parameter acquisition module for acquiring the historical environment parameter sequences and historical line parameter sequences corresponding to an initial alternative line at M historical time points; An environment parameter prediction module for inputting the historical environment parameter sequences corresponding to M historical time points into the trained environment parameter prediction model to obtain the predicted environment parameter sequence at the current time point; An environment parameter calculation module for obtaining the environment parameter change amount sequence according to the predicted environment parameter sequence at the current time point and the historical environment parameter sequence corresponding to the Mth historical time point; A parameter mapping module for inputting the environment parameter change amount sequence and the historical line parameter sequence corresponding to the Mth historical time point into the trained correction parameter mapping model to obtain the target correction parameter sequence; A line parameter prediction module for inputting the historical line parameter sequences corresponding to M historical time points into the trained line parameter prediction model to obtain the predicted line parameter sequence at the current time point; A line parameter determination module for obtaining the target line parameter sequence at the current time point according to the target correction parameter sequence and the predicted line parameter sequence; A matrix formation module for determining the target parameter matrix according to the historical line parameter sequences and historical environment parameter sequences corresponding to M historical time points, the target line parameter sequence and predicted environment parameter sequence at the current time point, and the preset sequence selection vector; A fault prediction module for inputting the target parameter matrix into the trained fault prediction model to obtain the fault prediction result at the current time point; A line selection module, configured to determine the initial alternative line as the target alternative line if the current time point meets the first preset condition and the fault prediction result at the current time point meets the second preset condition.

[0009] In a third aspect, an embodiment of the present invention provides a computer device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the alternative line evaluation method described in the first aspect is implemented.

[0010] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the alternative line evaluation method described in the first aspect is implemented.

[0011] The beneficial effects of the present invention compared with the prior art are as follows: Predict the predicted environmental parameter sequence at the current time point according to the historical environmental parameter sequences respectively corresponding to M historical time points. Obtain the environmental parameter change amount sequence according to the predicted environmental parameter sequence at the current time point and the historical environmental parameter sequence corresponding to the Mth historical time point. Map the environmental parameter change amount sequence to obtain the correction parameter sequence, and correct the predicted line parameter sequence. By comprehensively considering the influence of environmental parameters on line parameters, the accuracy of line parameter prediction is improved. And perform fault prediction according to the target parameter matrix, comprehensively considering the environmental parameters and line parameters of multiple time points, improve the accuracy of fault prediction, and further improve the accuracy of alternative line evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0013] Figure 1 is an application environment schematic diagram of an alternative line evaluation method for a single-fiber bidirectional wavelength division system provided in Embodiment 1 of the present invention; Figure 2 is a flowchart of an alternative line evaluation method for a single-fiber bidirectional wavelength division system provided in Embodiment 1 of the present invention; Figure 3 is a structural schematic diagram of an alternative line evaluation device for a single-fiber bidirectional wavelength division system provided in Embodiment 2 of the present invention; Figure 4It is a schematic structural diagram of a computer device for an alternative line evaluation method for a single-fiber bidirectional wavelength division system provided in Embodiment 3 of the present invention. Detailed implementation manners

[0014] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are presented to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0015] It should be understood that when used in the specification and appended claims of the present invention, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0016] It should also be understood that the term "and / or" as used in the specification and appended claims of the present invention refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0017] As used in the specification and appended claims of the present invention, the term "if" can be interpreted as "when" or "once" or "in response to determining" or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if detecting [the described condition or event]" can be interpreted as meaning "once determined" or "in response to determining" or "once detecting [the described condition or event]" or "in response to detecting [the described condition or event]" according to the context.

[0018] In addition, in the description of the specification and appended claims of the present invention, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0019] The reference to "an embodiment" or "some embodiments" or the like described in the specification of the present invention means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present invention. Thus, the statements "in an embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0020] It should be understood that the magnitudes of the sequence numbers of the steps in the following embodiments do not imply the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0021] In order to illustrate the technical solution of the present invention, the following specific embodiments are used for illustration.

[0022] An alternative line evaluation method for a single-fiber bidirectional wavelength division system provided in the first embodiment of the present invention can be applied in an application environment such as Figure 1 where the server communicates with the client. The client includes, but is not limited to, terminal devices such as a palm computer, a desktop computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cloud terminal device, and a personal digital assistant (PDA). The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0023] See Figure 2 , which is a schematic flowchart of an alternative line evaluation method for a single-fiber bidirectional wavelength division system provided in the first embodiment of the present invention. The above alternative line evaluation method can be applied to the server in Figure 1 . The server can obtain a historical environmental parameter sequence and a historical line parameter sequence at each historical time point through an optical line protection device, a sensor, etc. A trained environmental parameter prediction model, a trained correction parameter mapping model, a trained line parameter prediction model, and a trained fault prediction model are deployed inside the server. The above models are all trained and can be directly called during processing. As shown in Figure 2 , the alternative line evaluation method may include the following steps: Step S201, obtain a historical environmental parameter sequence and a historical line parameter sequence corresponding to the initial alternative line at M historical time points respectively.

[0024] Where M is an integer greater than zero. In the single-fiber bidirectional wavelength division system, there are multiple alternative lines other than the main line to quickly switch to an alternative line for optical signal transmission when the main line fails. The initial alternative line can be any one of the multiple alternative lines. The historical time point can refer to the acquisition time point. The sensor and the optical line protection device both collect data at the acquisition time point. In this embodiment, the time interval between two adjacent historical time points is the same, both being T.

[0025] The historical environmental parameter sequence can include historical values corresponding to several environmental parameter types. The environmental parameter types can include temperature, humidity, etc. The historical line parameter sequence can include historical values corresponding to several line parameter types. The line parameter types can include optical power, wavelength, bit error rate, polarization mode dispersion, etc.

[0026] Specifically, in this embodiment, the historical environmental parameter sequence can be represented as a vector of size N*1, where N is the number of environmental parameter types. The elements in this vector are the historical values of the environmental parameter types collected at the corresponding historical time points. The historical line parameter sequence can be represented as a vector of size K*1, where K is the number of line parameter types. The elements in this vector are the historical values of the line parameter types collected at the corresponding historical time points.

[0027] Step S202: Input the historical environmental parameter sequences corresponding to M historical time points into the trained environmental parameter prediction model to obtain the predicted environmental parameter sequence at the current time point.

[0028] Among them, the environmental parameter prediction model can adopt a recurrent neural network model, a long short-term memory network model, a time-domain convolution model, etc. The predicted environmental parameter sequence can represent the predicted environmental parameter sequence at the current time point.

[0029] Specifically, in this embodiment, the environmental parameter prediction model adopts a time-domain convolution model. The environmental parameter prediction model determines the input data in a sliding window manner. The size of the sliding window can be I. Then, the historical environmental parameter sequence corresponding to the (M - I + 1)-th historical time point to the historical environmental parameter sequence corresponding to the M-th historical time point is used as the input data, and the predicted environmental parameter sequence at the current time point is output. The time interval between the current time point and the M-th historical time point is T.

[0030] Step S203: Obtain the environmental parameter change amount sequence based on the predicted environmental parameter sequence at the current time point and the historical environmental parameter sequence corresponding to the M-th historical time point.

[0031] Among them, the environmental parameter change amount sequence can be used to characterize the change situation of the environmental parameters at the current time point compared with its adjacent previous historical time point.

[0032] Specifically, subtract the historical environmental parameter sequence corresponding to the M-th historical time point from the predicted environmental parameter sequence at the current time point point by point, and use the point-by-point subtraction result as the environmental parameter change amount sequence.

[0033] Step S204: Input the environmental parameter change amount sequence and the historical line parameter sequence corresponding to the M-th historical time point into the trained correction parameter mapping model to obtain the target correction parameter sequence.

[0034] Among them, the target correction parameter sequence includes target correction parameters corresponding to K types of line parameters respectively. That is, the input of the trained correction parameter mapping model is an N×1 - sized vector corresponding to the environmental parameter change amount sequence and a K×1 - sized vector corresponding to the historical line parameter sequence at the M - th historical time point, and the output is a K×1 - sized vector.

[0035] Step S205: Input the historical line parameter sequences corresponding to M historical time points into the trained line parameter prediction model to obtain the predicted line parameter sequence at the current time point.

[0036] Among them, the line parameter prediction model can also adopt a recurrent neural network model, a long - short - term memory network model, a time - domain convolution model, etc. In this embodiment, the time - domain convolution model is still adopted. The size of the sliding window of the line parameter prediction model is still set to I. Then, the historical line parameter sequences from the (M - I + 1) - th historical time point to the M - th historical time point are used as input data to output the predicted line parameter sequence at the current time point.

[0037] Step S206: Obtain the target line parameter sequence at the current time point according to the target correction parameter sequence and the predicted line parameter sequence.

[0038] Among them, the target line parameter sequence may include target line parameters corresponding to each type of line parameter respectively. The target line parameter may refer to the correction result of the predicted line parameter by the corresponding target correction parameter.

[0039] Specifically, in practical applications, usually, the prediction of environmental parameters is relatively reliable, but the accuracy of predicting line parameters is relatively poor. The reason is that line parameters are affected by environmental parameters, and only predicting the current line parameters based on historical line parameters cannot effectively obtain the information of environmental parameters, resulting in relatively poor accuracy of line parameter prediction.

[0040] In this embodiment, the line parameter prediction model essentially performs the line parameter prediction task under the condition of constant environmental parameters. To improve the accuracy of line parameter prediction, a target correction parameter sequence is provided for the predicted line parameter sequence according to the environmental parameter change amount sequence.

[0041] In the training stage, first train the environmental parameter prediction model to obtain a trained environmental parameter prediction model, and then co-train the line parameter prediction model and the correction parameter mapping model. Specifically, input the sample line parameter sequences corresponding to M sample time points into the line parameter prediction model to obtain the predicted sample line parameter sequence at the preset time point. Input the sample environmental parameter change amount sequence and the sample line parameter sequence corresponding to the Mth sample time point into the correction parameter mapping model to obtain the sample correction parameter sequence. Multiply the sample correction parameter sequence and the sample line parameter prediction sequence point by point to obtain the sample line correction sequence. According to the sample line correction sequence and the label sequence at the preset time point, calculate through the mean square error loss function to obtain the first training loss. According to this first training loss, use the gradient descent algorithm to adjust the parameters of the line parameter prediction model and the correction parameter mapping model until the first training loss converges, and obtain a trained line parameter prediction model and a trained correction parameter mapping model.

[0042] In one embodiment, in order to improve the training efficiency of the co-training of the line parameter prediction model and the correction parameter mapping model, the implementer can adopt an alternating training method, that is, first fix the parameters of the correction parameter mapping model, and according to the first training loss, use the gradient descent algorithm to adjust the parameters of the line parameter prediction model until the first training loss converges. Then fix the parameters of the line parameter prediction model, and according to the first training loss, use the gradient descent algorithm to adjust the parameters of the correction parameter mapping model until the first training loss converges, and so on, until the convergence value of the first training loss is less than the preset convergence value threshold.

[0043] Step S207, determine the target parameter matrix according to the historical line parameter sequences and historical environmental parameter sequences corresponding to M historical time points, the target line parameter sequence and predicted environmental parameter sequence at the current time point, and the preset sequence selection vector.

[0044] Among them, the target parameter matrix can include the line parameter information and environmental parameter information for fault prediction.

[0045] Optionally, determining the target parameter matrix according to the historical line parameter sequences and historical environmental parameter sequences corresponding to M historical time points, the target line parameter sequence and predicted environmental parameter sequence at the current time point, and the preset sequence selection vector includes: Form a temporary line parameter matrix from the historical line parameter sequences corresponding to M historical time points and the target line parameter sequence at the current time point; Form a temporary environmental parameter matrix from the historical environmental parameter sequences corresponding to M historical time points and the predicted environmental parameter sequence at the current time point; Concatenate the temporary line parameter matrix and the temporary environmental parameter matrix to obtain a temporary parameter matrix; Multiply each row in the temporary parameter matrix by the sequence selection vector respectively to obtain the target parameter matrix.

[0046] Among them, the historical line parameter sequences corresponding to M historical time points and the target line parameter sequence at the current time point are concatenated column by column in chronological order, and the obtained concatenation result is used as the temporary line parameter matrix. The temporary line parameter matrix can be represented as a matrix of size K*(M + 1).

[0047] The historical environmental parameter sequences corresponding to M historical time points and the predicted environmental parameter sequence at the current time point are concatenated column by column in chronological order, and the obtained concatenation result is used as the temporary environmental parameter matrix. The temporary environmental parameter matrix can be represented as a matrix of size N*(M + 1).

[0048] Concatenate the temporary line parameter matrix and the temporary environmental parameter matrix by rows to obtain the temporary parameter matrix. The temporary parameter matrix can be represented as a matrix of size (N + K)*(M + 1).

[0049] The sequence selection vector is a vector of size 1*(M + 1). Multiply the temporary parameter matrix row by row with the sequence selection vector to obtain the target parameter matrix. The target parameter matrix can be represented as a matrix of size (N + K)*(M + 1).

[0050] Optionally, according to the historical line parameter sequences and historical environmental parameter sequences corresponding to M historical time points, the target line parameter sequence and predicted environmental parameter sequence at the current time point, and the preset sequence selection vector, to determine the target parameter matrix, it further includes: Obtain the line parameter fluctuation evaluation value according to the temporary line parameter matrix; Obtain the environmental parameter fluctuation evaluation value according to the temporary environmental parameter matrix; Obtain the selection mapping value according to the line parameter fluctuation evaluation value, the environmental parameter fluctuation evaluation value and the preset mapping function; Determine the sequence selection vector according to the selection mapping value and the preset basic selection vector.

[0051] Among them, obtaining the line parameter fluctuation evaluation value according to the temporary line parameter matrix may refer to calculating the variance of each row of the temporary line parameter matrix to obtain the variance calculation result corresponding to each row of the temporary line parameter matrix, and performing a mean calculation on the variance calculation results of all rows of the temporary line parameter matrix to obtain the line parameter fluctuation evaluation value.

[0052] Similarly, according to the temporary environmental parameter matrix, the environmental parameter fluctuation evaluation value can be obtained. Specifically, variance calculation is performed on each row of the temporary environmental parameter matrix to obtain the variance calculation results corresponding to each row of the temporary environmental parameter matrix respectively. The mean value is calculated from the variance calculation results of all rows of the temporary environmental parameter matrix to obtain the environmental parameter fluctuation evaluation value.

[0053] The mapping function can be obtained by fitting. Specifically, sample data with faults at a preset time point is selected. In this sample data, according to the sample line parameter sequence, sample environmental parameter sequence, sample line parameter prediction sequence, and sample environmental parameter prediction sequence corresponding to the sample time point, the sample line parameter matrix can be determined, the sample line parameter fluctuation evaluation value can be obtained, and the sample environmental parameter matrix can be obtained, and the sample environmental parameter fluctuation evaluation value can be obtained. Then, the sample parameter matrix is obtained by splicing the sample line parameter matrix and the sample environmental parameter matrix.

[0054] Initialize the sample selection value Q to 1. Set the elements from the first column to the M + 1 - Q column in the sample parameter matrix to zero to obtain the sample intermediate matrix. Input the sample intermediate matrix into the trained fault prediction model to obtain the sample fault prediction result. If the sample fault prediction result is that there is a fault, determine the current Q value as the sample mapping value. Otherwise, update Q to Q + 1, and return to execute the step of setting the elements from the first column to the M + 1 - Q column in the sample parameter matrix to zero until the sample mapping value is obtained or Q = M + 1, and a set of sample environmental parameter fluctuation evaluation values, sample line parameter fluctuation evaluation values, and sample mapping values are obtained.

[0055] According to the above method, several groups of sample environmental parameter fluctuation evaluation values, sample line parameter fluctuation evaluation values, and sample mapping values are obtained. Using the sample environmental parameter fluctuation evaluation values and sample line parameter fluctuation evaluation values as independent variables and the sample mapping value as the dependent variable for function fitting, the function fitting method can adopt the least squares method, maximum likelihood estimation method, etc., to obtain the mapping function.

[0056] Input the line parameter fluctuation evaluation value and the environmental parameter fluctuation evaluation value into the preset mapping function to obtain the selection mapping value. The preset basic selection vector is a 1*(M + 1)-sized vector with all elements being 1. According to the selection mapping value and the preset basic selection vector, the sequence selection vector can be determined. Specifically, according to the selection mapping value P, set the first to the M + 1 - P elements in the basic selection vector to 0 to obtain the sequence selection vector, where P is an integer within the range of [1, M + 1].

[0057] Step S208, input the target parameter matrix into the trained fault prediction model to obtain the fault prediction result at the current time point.

[0058] Among them, by performing prediction through the target parameter matrix, the amount of non-zero data participating in the operation of the fault prediction model can be effectively reduced, and the computational load can be reduced without affecting the accuracy of fault prediction, thereby improving the computational efficiency, that is, improving the efficiency of fault prediction.

[0059] Specifically, the fault prediction model can adopt a binary classification model, and the binary classification model usually uses a binary cross-entropy loss function for training, which will not be elaborated here.

[0060] Step S209: If the current time point meets the first preset condition and the fault prediction result at the current time point meets the second preset condition, determine the initial alternative line as the target alternative line.

[0061] Among them, the target alternative line is the alternative line to be switched to.

[0062] Optionally, the method further includes: If the current time point does not meet the first preset condition, delete the historical environment parameter sequence and the historical line parameter sequence corresponding to the first historical time point respectively; Use the historical environment parameter sequences and historical line parameter sequences corresponding to the second historical time point to the Mth historical time point as the historical environment parameter sequences and historical line parameter sequences corresponding to the first historical time point to the (M - 1)th historical time point respectively; Use the target line parameter sequence at the current time point as the historical line parameter sequence corresponding to the Mth historical time point; Use the predicted environment parameter sequence at the current time point as the historical environment parameter sequence corresponding to the Mth historical time point; Update the current time point with the sum of the current time point and the preset time step; Return to execute the step of inputting the historical environment parameter sequences corresponding to M historical time points into the trained environment parameter prediction model to obtain the predicted environment parameter sequence at the current time point.

[0063] Among them, when evaluating alternative lines, it is often necessary to predict the line conditions after a period of time, rather than the line conditions at the next time point. Therefore, in combination with the time-domain convolutional model adopted in this embodiment, iterative prediction is performed using a sliding window.

[0064] Specifically, after obtaining the prediction result at the current time point, the historical environment parameter sequences and historical line parameter sequences corresponding to the second historical time point to the Mth historical time point can be used as the historical environment parameter sequences and historical line parameter sequences corresponding to the first historical time point to the (M - 1)th historical time point respectively. The target line parameter sequence at the current time point is used as the historical line parameter sequence corresponding to the Mth historical time point, and the predicted environment parameter sequence at the current time point is used as the historical environment parameter sequence corresponding to the Mth historical time point, so as to form the updated historical environment parameter sequences and historical line parameter sequences corresponding to the M historical time points respectively, and then perform the prediction for the next iteration round.

[0065] Optionally, the method further includes: If the current time point meets the first preset condition and the fault prediction result at the current time point does not meet the second preset condition, then update the initial alternative line, and return to execute the step of obtaining the historical environment parameter sequences and historical line parameter sequences corresponding to the initial alternative line at the M historical time points respectively.

[0066] Among them, when the current time point meets the first preset condition and the fault prediction result at the current time point does not meet the second preset condition, it indicates that the initial alternative line cannot meet the replacement requirement, and it is necessary to replace the initial alternative line for re - judgment.

[0067] Specifically, during the use by the implementer, the alternative lines can be pre - screened. For example, several alternative lines can be pre - selected according to conditions such as wavelength, and the initial alternative line can be determined from these alternative lines to meet the implementer's requirements for alternative lines.

[0068] In one implementation manner, when the computing power of the server is sufficient, the implementer can also select multiple initial alternative lines from the alternative lines and perform parallel computing according to the method provided in this embodiment, so as to improve the efficiency of alternative line evaluation.

[0069] Optionally, the first preset condition is: The current time point is greater than or equal to a preset reference time point.

[0070] Among them, the reference time point can be a time point determined according to the current time point and the expected usage duration of the alternative line. If the initial alternative line can still meet the requirements when the current time point is greater than or equal to the preset reference time point, it can be used as the target alternative line.

[0071] Optionally, the fault prediction result includes no fault or a fault; The second preset condition is: the fault prediction result at the current time point is no fault.

[0072] Among them, in this embodiment, only binary classification is performed on the fault prediction result, and the implementer can perform multi-classification prediction according to requirements, for example, including multiple fault types and no fault. Correspondingly, the second preset condition can be adjusted to that the fault prediction result at the current time point is a preset fault type or no fault.

[0073] In this embodiment, the predicted environmental parameter sequence at the current time point is predicted according to the historical environmental parameter sequences corresponding to M historical time points respectively. According to the predicted environmental parameter sequence at the current time point and the historical environmental parameter sequence corresponding to the Mth historical time point, an environmental parameter change amount sequence is obtained. A correction parameter sequence is obtained by mapping the environmental parameter change amount sequence, and the predicted line parameter sequence is corrected. By comprehensively considering the influence of environmental parameters on line parameters, the accuracy of line parameter prediction is improved. And fault prediction is performed according to the target parameter matrix, comprehensively considering the environmental parameters and line parameters at multiple time points, improving the accuracy of fault prediction, and further improving the accuracy of alternative line evaluation.

[0074] Corresponding to the method in the above embodiment, Figure 3 FIG. shows a schematic structural diagram of an alternative line evaluation device for a single-fiber bidirectional wavelength division system provided in the second embodiment of the present invention. The above alternative line evaluation device is applied to the server side. The server side can obtain the historical environmental parameter sequences and historical line parameter sequences at each historical time point through optical line protection devices, sensors, etc. A trained environmental parameter prediction model, a trained correction parameter mapping model, a trained line parameter prediction model, and a trained fault prediction model are deployed inside the server side. The above models are all trained and can be directly called during processing. For the sake of simplicity, only the parts related to the embodiments of the present invention are shown.

[0075] See Figure 3 , the alternative line evaluation device includes: A parameter acquisition module 31, configured to acquire the historical environmental parameter sequences and historical line parameter sequences corresponding to an initial alternative line at M historical time points respectively, where M is an integer greater than zero; An environmental parameter prediction module 32, configured to input the historical environmental parameter sequences corresponding to M historical time points respectively into the trained environmental parameter prediction model to obtain the predicted environmental parameter sequence at the current time point; An environmental parameter calculation module 33, configured to obtain an environmental parameter change amount sequence according to the predicted environmental parameter sequence at the current time point and the historical environmental parameter sequence corresponding to the Mth historical time point; A parameter mapping module 34, configured to input the environmental parameter change amount sequence and the historical line parameter sequence corresponding to the Mth historical time point into the trained correction parameter mapping model to obtain a target correction parameter sequence; The line parameter prediction module 35 is configured to input the historical line parameter sequences corresponding to M historical time points into the trained line parameter prediction model to obtain the predicted line parameter sequence at the current time point; The line parameter determination module 36 is configured to obtain the target line parameter sequence at the current time point according to the target correction parameter sequence and the predicted line parameter sequence; The matrix formation module 37 is configured to determine the target parameter matrix according to the historical line parameter sequences and historical environment parameter sequences corresponding to M historical time points respectively, the target line parameter sequence and the predicted environment parameter sequence at the current time point, and the preset sequence selection vector; The fault prediction module 38 is configured to input the target parameter matrix into the trained fault prediction model to obtain the fault prediction result at the current time point; The line selection module 39 is configured to determine the initial alternative line as the target alternative line if the current time point meets the first preset condition and the fault prediction result at the current time point meets the second preset condition.

[0076] Optionally, the alternative line evaluation device further includes: The sequence deletion module is configured to delete the historical environment parameter sequence and the historical line parameter sequence corresponding to the first historical time point if the current time point does not meet the first preset condition; The sequence change module is configured to use the historical environment parameter sequences and historical line parameter sequences corresponding to the second historical time point to the Mth historical time point as the historical environment parameter sequences and historical line parameter sequences corresponding to the first historical time point to the (M - 1)th historical time point respectively; The line parameter addition module is configured to use the target line parameter sequence at the current time point as the historical line parameter sequence corresponding to the Mth historical time point; The environment parameter addition module is configured to use the predicted environment parameter sequence at the current time point as the historical environment parameter sequence corresponding to the Mth historical time point; The time point update module is configured to update the current time point with the sum of the current time point and the preset time step; The first iteration execution module is configured to return and execute the step of inputting the historical environment parameter sequences corresponding to M historical time points into the trained environment parameter prediction model to obtain the predicted environment parameter sequence at the current time point.

[0077] Optionally, the alternative line evaluation device further includes: A second iteration execution module, configured to update the initial alternative line if the current time point meets the first preset condition and the fault prediction result at the current time point does not meet the second preset condition, and return to execute the step of obtaining the historical environment parameter sequences and historical line parameter sequences corresponding to the initial alternative line at M historical time points.

[0078] Optionally, in the above line selection module 39, the first preset condition is: The current time point is greater than or equal to a preset reference time point.

[0079] Optionally, the fault prediction result includes no fault or a fault; In the above line selection module 39, the second preset condition is: The fault prediction result at the current time point is no fault.

[0080] Optionally, the above matrix formation module 37 includes: A first matrix formation unit, configured to form a temporary line parameter matrix from the historical line parameter sequences corresponding to M historical time points and the target line parameter sequence at the current time point; A second matrix formation unit, configured to form a temporary environment parameter matrix from the historical environment parameter sequences corresponding to M historical time points and the predicted environment parameter sequence at the current time point; A matrix splicing unit, configured to splice the temporary line parameter matrix and the temporary environment parameter matrix to obtain a temporary parameter matrix; A matrix determination unit, configured to multiply each row in the temporary parameter matrix by the sequence selection vector to obtain a target parameter matrix.

[0081] Optionally, the above matrix formation module 37 further includes: A first fluctuation evaluation unit, configured to obtain a line parameter fluctuation evaluation value according to the temporary line parameter matrix; A second fluctuation evaluation unit, configured to obtain an environment parameter fluctuation evaluation value according to the temporary environment parameter matrix; A selection mapping unit, configured to obtain a selection mapping value according to the line parameter fluctuation evaluation value, the environment parameter fluctuation evaluation value, and a preset mapping function; A selection vector determination unit, configured to determine a sequence selection vector according to the selection mapping value and a preset basic selection vector.

[0082] It should be noted that for the information interaction, execution process, etc. among the above modules and units, since they are based on the same concept as the method embodiment of the present invention, their specific functions and the technical effects brought about are specifically described in the method embodiment part, and will not be elaborated here.

[0083] Figure 4Schematic diagram of the structure of a computer device for an alternative line evaluation method for a single-fiber bidirectional wavelength division system provided in Embodiment 3 of the present invention. As Figure 4 shown, the computer device of this embodiment includes: at least one processor ( Figure 4 only one is shown in the figure), a memory, and a computer program stored in the memory and executable on at least one processor. When the processor executes the computer program, it implements the steps in any of the above-described embodiments of the alternative line evaluation method for a single-fiber bidirectional wavelength division system.

[0084] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that Figure 4 this is only an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include a network interface, a display screen, and an input device, etc.

[0085] The so-called processor may be a CPU, and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0086] The memory includes a readable storage medium, an internal memory, etc. Among them, the internal memory may be the memory of the computer device, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be the hard disk of the computer device, and in some other embodiments, it may also be an external storage device of the computer device. For example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the memory may also include both the internal storage unit of the computer device and the external storage device. The memory is used to store the operating system, application programs, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or will be output.

[0087] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present invention. The specific working processes of the units and modules in the above-mentioned device can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned method embodiments of the present invention, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device capable of carrying the computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0088] All or part of the processes in the above-mentioned method embodiments of the present invention can also be completed by a computer program product. When the computer program product runs on a computer device, the computer device can be made to execute the steps in the above-mentioned method embodiments.

[0089] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0090] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0091] In the embodiments provided by the present invention, it should be understood that the disclosed apparatus / computer device and method can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed among each other can be through some interfaces. The indirect couplings or communication connections of the apparatus or unit can be in electrical, mechanical or other forms.

[0092] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0093] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for evaluating candidate lines for a single-fiber bidirectional wavelength division system, characterized in that: The method comprises: Obtaining historical environment parameter sequences and historical route parameter sequences corresponding to the initial candidate routes at M historical time points, where M is an integer greater than zero; Input the historical environmental parameter sequences corresponding to the M historical time points into the trained environmental parameter prediction model to obtain the predicted environmental parameter sequence at the current time point; According to the predicted environmental parameter sequence at the current time point and the historical environmental parameter sequence corresponding to the Mth historical time point, the environmental parameter change sequence is obtained; Input the environmental parameter variation sequence and the historical line parameter sequence corresponding to the Mth historical time point into the trained correction parameter mapping model to obtain a target correction parameter sequence; Input the historical line parameter sequences corresponding to the M historical time points into the trained line parameter prediction model to obtain the predicted line parameter sequence at the current time point; Obtaining a target line parameter sequence at a current time point according to the target correction parameter sequence and the predicted line parameter sequence; Determine the target parameter matrix according to the historical line parameter sequences and the historical environment parameter sequences corresponding to the M historical time points, the target line parameter sequence and the predicted environment parameter sequence at the current time point, and the preset sequence selection vector; Inputting the target parameter matrix into the trained fault prediction model to obtain the fault prediction result at the current time point; If the current time point satisfies the first preset condition, and the fault prediction result at the current time point satisfies the second preset condition, the initial candidate route is determined as the target candidate route.

2. The candidate route evaluation method according to claim 1, characterized in that: The method further comprises: If the current time point does not meet the first preset condition, the historical environment parameter sequence and the historical line parameter sequence corresponding to the first historical time point are deleted; The historical environment parameter sequence and historical line parameter sequence corresponding to the second historical time point to the Mth historical time point are used as the historical environment parameter sequence and historical line parameter sequence corresponding to the first historical time point to the M-1th historical time point; The target line parameter sequence at the current time point is used as the historical line parameter sequence corresponding to the Mth historical time point; The predicted environmental parameter sequence at the current time point is used as the historical environmental parameter sequence corresponding to the Mth historical time point; Update the current time point with the sum of the current time point and the preset time step; Return to the step of inputting the historical environmental parameter sequences corresponding to the M historical time points into the trained environmental parameter prediction model to obtain the predicted environmental parameter sequence at the current time point.

3. The candidate route evaluation method according to claim 1, characterized in that: The method further comprises: If the current time point satisfies the first preset condition and the fault prediction result at the current time point does not meet the second preset condition, the initial candidate line is updated, and the step of obtaining the historical environment parameter sequence and the historical line parameter sequence corresponding to the initial candidate line at M historical time points is returned to execute.

4. The candidate route evaluation method according to claim 1, characterized in that: The first preset condition is: The current time point is greater than or equal to a preset reference time point.

5. The candidate route evaluation method according to claim 1, characterized in that: The fault prediction result includes no fault or fault; The second preset condition is that the fault prediction result at the current time point is no fault.

6. The candidate route evaluation method according to claim 1, characterized in that: The target parameter matrix is ​​determined according to the historical line parameter sequences and the historical environment parameter sequences respectively corresponding to the M historical time points, the target line parameter sequence and the predicted environment parameter sequence at the current time point, and the preset sequence selection vector, including: A temporary line parameter matrix is ​​formed by the historical line parameter sequences corresponding to the M historical time points and the target line parameter sequence at the current time point; A temporary environmental parameter matrix is ​​formed by the historical environmental parameter sequences corresponding to the M historical time points and the predicted environmental parameter sequence at the current time point; Concatenate the temporary line parameter matrix and the temporary environment parameter matrix to obtain a temporary parameter matrix; Each row in the temporary parameter matrix is ​​multiplied by the sequence selection vector to obtain the target parameter matrix.

7. The candidate route evaluation method according to claim 6, characterized in that: The method of determining the target parameter matrix according to the historical line parameter sequences and the historical environment parameter sequences respectively corresponding to the M historical time points, the target line parameter sequence and the predicted environment parameter sequence at the current time point, and the preset sequence selection vector, further includes: Obtaining a line parameter fluctuation evaluation value according to the temporary line parameter matrix; Obtaining an environmental parameter fluctuation evaluation value according to the temporary environmental parameter matrix; Obtaining a selected mapping value according to the line parameter fluctuation evaluation value, the environmental parameter fluctuation evaluation value and a preset mapping function; The sequence selection vector is determined according to the selection mapping value and a preset basic selection vector.

8. A candidate line evaluation device for a single-fiber bidirectional wavelength division system, characterized in that: The device comprises: A parameter acquisition module, used to obtain historical environment parameter sequences and historical route parameter sequences corresponding to the initial candidate routes at M historical time points, where M is an integer greater than zero; The environmental parameter prediction module is used to input the historical environmental parameter sequences corresponding to the M historical time points into the trained environmental parameter prediction model to obtain the predicted environmental parameter sequence at the current time point; An environmental parameter calculation module is used to obtain an environmental parameter variation sequence based on the predicted environmental parameter sequence at the current time point and the historical environmental parameter sequence corresponding to the Mth historical time point; A parameter mapping module, used for inputting the environmental parameter variation sequence and the historical line parameter sequence corresponding to the Mth historical time point into the trained correction parameter mapping model to obtain a target correction parameter sequence; A line parameter prediction module is used to input the historical line parameter sequences corresponding to M historical time points into the trained line parameter prediction model to obtain the predicted line parameter sequence at the current time point; A line parameter determination module, used to obtain a target line parameter sequence at a current time point according to the target correction parameter sequence and the predicted line parameter sequence; A matrix forming module, for determining a target parameter matrix according to the historical line parameter sequences and the historical environment parameter sequences corresponding to the M historical time points, the target line parameter sequence and the predicted environment parameter sequence at the current time point, and a preset sequence selection vector; A fault prediction module is used to input the target parameter matrix into the trained fault prediction model to obtain a fault prediction result at a current time point; The line selection module is used to determine the initial candidate line as the target candidate line if the current time point meets the first preset condition and the fault prediction result at the current time point meets the second preset condition.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the alternative route evaluation method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the alternative route evaluation method according to any one of claims 1 to 7 is implemented.

Images