DC transmission project loss assessment method, device, equipment and storage medium

By using a loss assessment method trained with a neural network model, the problem of balancing computation time and accuracy in loss assessment of DC transmission projects has been solved, achieving fast and accurate loss assessment and improving assessment efficiency.

CN114861542BActive Publication Date: 2024-11-15MAINTENANCE & TEST CENTRE CSG EHV POWER TRANSMISSION CO
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210527974.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-05-16
Publication Date
2024-11-15
Estimated Expiration
2042-05-16

AI Technical Summary

Technical Problem

Existing technologies struggle to balance computation time and accuracy when assessing losses in DC transmission projects. Simulation modeling is time-consuming and its accuracy depends on the precision of the simulation program, while analytical algorithms produce errors and require repeated parameter adjustments, resulting in low assessment efficiency.

Method used

A neural network model based on training operating condition parameters and line information from multiple DC transmission project samples is used to obtain a loss assessment model through training. This model can quickly acquire project loss information, learn the mapping relationship between operating conditions, lines, and losses, and reduce manual parameter adjustments.

Benefits of technology

It enables rapid and accurate assessment of DC transmission project losses under varying operating conditions and line conditions, improving assessment efficiency and accuracy while reducing calculation time and human error.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114861542B_ABST
    Figure CN114861542B_ABST
Patent Text Reader

Abstract

The present application relates to the field of power loss calculation, and provides a method, device, computer equipment, storage medium and computer program product for evaluating the loss of a DC transmission project, which can effectively improve the evaluation efficiency of the loss of a DC transmission project. The method comprises: obtaining the engineering operating parameters and engineering line information of the DC transmission project to be evaluated; inputting the engineering operating parameters and engineering line information into a pre-trained loss evaluation model; the loss evaluation model is used to determine the loss information of the DC transmission project based on the engineering operating parameters and engineering line information; the loss evaluation model is obtained by training a neural network model based on the training operating parameters, training line information and engineering loss labels of multiple different DC transmission project samples; obtaining the loss information of the DC transmission project output by the loss evaluation model, and determining the loss evaluation result of the DC transmission project based on the loss information.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of power loss calculation, and in particular to a method, device, computer equipment, storage medium and computer program product for evaluating loss in a direct current transmission project. Background Art

[0002] With the continuous development of power grid technology, DC transmission has the characteristics of low loss and high stability compared with AC transmission, and has been widely used in long-distance transmission projects. However, with the increase of DC transmission voltage level and capacity, the loss problem in the transmission process has become more and more prominent.

[0003] In related technologies, the loss of DC power transmission projects can be predicted through simulation modeling and analytical algorithms. Among them, the simulation modeling method can build a complete DC engineering system model, and the loss of different positions inside the project can be obtained with the help of real-time simulation curves; while the analytical algorithm can quickly obtain the overall loss of the DC engineering through the loading and unloading formula algorithm.

[0004] However, the simulation modeling method takes a long time to build a DC engineering system model, and often requires multiple iterative calculations, and a single iteration takes a long time. In reality, the operating conditions of DC transmission projects vary complexly. If the losses under various operating conditions need to be simulated, it will take a lot of time. Although the analytical algorithm can quickly obtain the overall loss of the DC transmission project, there is often a certain error between the result and the actual situation. It can be seen that the relevant technology is difficult to take into account both the calculation time and the calculation accuracy when evaluating the loss of DC transmission projects, and the overall evaluation efficiency is low. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for evaluating losses in a DC transmission project in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for evaluating losses in a DC power transmission project. The method comprises:

[0007] Obtain the engineering operating parameters and engineering line information of the DC transmission project to be evaluated;

[0008] The engineering operating parameters and engineering line information are input into a pre-trained loss assessment model; the loss assessment model is used to determine the loss information of the DC power transmission project based on the engineering operating parameters and engineering line information; the loss assessment model is obtained by training a neural network model based on training operating parameters, training line information and engineering loss labels of multiple different DC power transmission project samples;

[0009] The loss information of the DC power transmission project output by the loss assessment model is obtained, and a loss assessment result of the DC power transmission project is determined according to the loss information.

[0010] In one embodiment, it also includes:

[0011] Acquire a training sample set, wherein the training sample set includes training operating condition parameters and training line information of a plurality of different first direct current power transmission project samples, and an engineering loss label of each first direct current power transmission project sample;

[0012] Inputting the training operating condition parameters and training line information of a plurality of first DC power transmission project samples in the training sample set into the neural network model to be trained, and the neural network model outputs the predicted loss information of the first DC power transmission project sample based on the training operating condition parameters of each first DC power transmission project sample;

[0013] According to the predicted loss information and the engineering loss label, the model parameters of the neural network model are adjusted until the training end condition is met to obtain a trained loss assessment model.

[0014] In one embodiment, adjusting the model parameters of the neural network model according to the predicted loss information and the engineering loss label until a training end condition is met to obtain a trained loss assessment model includes:

[0015] Determine a loss value according to the predicted loss information of the plurality of first DC power transmission project samples and the project loss label of each first DC power transmission project sample;

[0016] The model parameters of the neural network model are adjusted according to the loss value and the back propagation algorithm until the training end condition is met to obtain a trained loss evaluation model.

[0017] In one embodiment, adjusting the model parameters of the neural network model to be trained according to the loss value and the back propagation algorithm until the training end condition is met to obtain a trained loss evaluation model includes:

[0018] Adjusting the model parameters of the neural network model according to the loss value and the back propagation algorithm to obtain an adjusted neural network model;

[0019] Acquire a test sample set; the test sample set includes training operating condition parameters and training line information of multiple second DC power transmission project samples, and an engineering loss label of each second DC power transmission project sample;

[0020] Inputting the training operating condition parameters and training line information of a plurality of second DC power transmission project samples in the test sample set into the neural network model, and having the neural network model output the predicted loss information of each second DC power transmission project sample based on the training operating condition parameters and training line information of the second DC power transmission project sample;

[0021] Determining a training error according to the predicted loss information of the plurality of second DC power transmission project samples and the project loss labels of the second DC power transmission project samples;

[0022] When the training error is greater than a preset error threshold, return to the step of obtaining the training sample set, and adjust the parameters of the neural network model again until the training error is no greater than the preset error threshold, thereby obtaining a trained loss evaluation model.

[0023] In one embodiment, it also includes:

[0024] Acquire training operating condition parameters and training line information of a plurality of DC power transmission project samples; the plurality of DC power transmission project samples are DC power transmission project samples with different training operating condition parameters and / or line information;

[0025] Determine the loss information of each DC power transmission project sample according to the training operating condition parameters, line information and a preset loss algorithm of each DC power transmission project sample, and use the loss information of each DC power transmission project sample as the project loss label of the DC power transmission project sample;

[0026] A training sample set and a test sample set are obtained according to the multiple direct current transmission project samples and their project loss labels.

[0027] In one embodiment, obtaining the engineering operating parameters of the DC power transmission project to be evaluated includes:

[0028] Obtaining power information, the number of full and half-bridge submodules, and the fundamental frequency of a converter station in the DC transmission project to be evaluated;

[0029] The engineering operating parameters of the direct current power transmission project are determined according to the power information, the number of full and half-bridge sub-modules and the fundamental frequency.

[0030] In a second aspect, the present application also provides a DC power transmission project loss assessment device. The device comprises:

[0031] An input information acquisition module is used to obtain the engineering operating parameters and engineering line information of the DC transmission project to be evaluated;

[0032] An input module is used to input the engineering operating parameters and engineering line information into a pre-trained loss assessment model; the loss assessment model is used to determine the loss information of the DC power transmission project based on the engineering operating parameters and engineering line information; the loss assessment model is obtained by training a neural network model based on training operating parameters, training line information and engineering loss labels of multiple different DC power transmission project samples;

[0033] The loss assessment result acquisition module is used to acquire the loss information of the DC power transmission project output by the loss assessment model, and determine the loss assessment result of the DC power transmission project according to the loss information.

[0034] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the methods described above.

[0036] In a fifth aspect, the present application also provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, the steps of the method described in any one of the above items are implemented.

[0037] The above-mentioned DC power transmission project loss assessment method, device, computer equipment, storage medium and computer program product obtain the engineering operating parameters and engineering line information of the DC power transmission project to be evaluated, and input the engineering operating parameters and engineering line information into a pre-trained loss assessment model, wherein the loss assessment model is used to determine the loss information of the DC power transmission project based on the engineering operating parameters and engineering line information, and the loss assessment model is obtained by training the neural network model based on the training operating parameters, training line information and engineering loss labels of multiple different DC power transmission project samples; and then the terminal can obtain the loss information of the DC power transmission project output by the loss assessment model, and determine the loss assessment result of the DC power transmission project according to the loss information. In this embodiment, by using multiple DC power transmission project samples to train the neural network model, a loss assessment model is obtained, which enables the loss assessment model to quickly learn the operating parameters of different DC power transmission projects and the mapping relationship between the engineering line and the loss of the DC power transmission project, so that when the operating conditions and lines are changed, there is no need to manually modify the parameters, while quickly obtaining the loss information, the accuracy of the loss information can be ensured, and the evaluation efficiency of the DC power transmission project loss can be effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1A schematic diagram of a flow chart of a method for evaluating loss of a DC power transmission project in one embodiment;

[0039] Figure 2 A schematic diagram of the structure of a neural network model in one embodiment;

[0040] Figure 3 A schematic diagram of a process of testing a neural network model in one embodiment;

[0041] Figure 4 It is a structural block diagram of a DC power transmission project loss assessment device in one embodiment;

[0042] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] In order to facilitate the understanding of the embodiments of the present application, a method for evaluating the loss of a DC power transmission project in the related art is first described.

[0045] With the continuous development of power grid technology, DC transmission has the characteristics of low loss and high stability compared with AC transmission, and has been widely used in long-distance power transmission projects. In DC transmission projects, flexible DC transmission systems have gradually become the mainstream with their excellent output characteristics and low switching losses. However, with the increase in the voltage level and capacity of flexible DC transmission, the converter loss problem of converter stations in DC transmission projects has become more and more prominent.

[0046] In the related art, the loss of DC power transmission projects can be predicted by simulation modeling and analytical algorithms. Among them, the simulation modeling method mainly builds a complete DC engineering system model on a simulation platform (such as PSCAD and MATLAB / Simulink, etc.), and obtains the loss of different positions inside the project with the help of real-time simulation curves. The accuracy of its loss results is proportional to the precision of the simulation program simulation. A more comprehensive and accurate simulation will produce more accurate results, but because the construction of the simulation system cycle is too long, it needs to go through multiple iterations and calculations, and a single time takes a long time, which is often only suitable for small engineering simulations. In addition, the real DC power transmission project usually has complex operating conditions. If the simulation modeling method wants to simulate all situations under different working conditions, it will take a lot of time and have high requirements for computer hardware configuration. There will also be different operating lines in the DC power transmission project. For different lines, the analytical algorithm needs to change different parameters, and the calculation process is relatively complicated. It can be seen that if the simulation modeling method is used to simulate and calculate the loss of a large DC power transmission project, it will take a lot of time and have high requirements for hardware. If multiple working conditions and losses of different lines are required during the engineering cycle, the parameters need to be changed and the simulation steps need to be repeated, which takes a very long time.

[0047] The analytical algorithm is mainly used for the calculation of converter valve losses in DC projects. By calculating the losses of each part of the converter valve and adding them up, the final loss can be obtained. The total loss of the DC transmission project can also be obtained by calculating the losses of each engineering component in the DC transmission project and adding them up. Under fixed power, the overall loss of the DC project can be quickly obtained through the analytical formula algorithm, but because the analytical algorithm uses the average bridge arm current as input and does not consider the sampling of the pulse waveform and nonlinear impedance, the calculation results have certain errors. Therefore, although the overall time consumption of the analytical algorithm is slightly shorter than that of the simulation modeling method, the algorithm also needs to be adjusted in the case of different working conditions and different lines. The calculation process is complicated. If different powers and line losses are required, the data needs to be changed repeatedly, which is cumbersome and prone to human errors.

[0048] It can be seen that the related technologies are difficult to balance the calculation time and calculation accuracy when evaluating the loss of DC transmission projects, and can only calculate a set of examples at a time. When the working conditions or lines of the DC transmission project change and multiple examples are formed, the above methods need to spend a lot of time to readjust the parameters, and the overall evaluation efficiency is low. Based on this, the present application provides a method for evaluating the loss of DC transmission projects.

[0049] In one embodiment, Figure 1As shown, a method for evaluating the loss of a DC power transmission project is provided. This embodiment uses the method applied to a terminal as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0050] S101, obtaining engineering operating parameters and engineering line information of a DC transmission project to be evaluated.

[0051] As an example, the DC transmission project to be evaluated may be any flexible DC project, and the project operating parameters may be the operating parameters of each project component during the operation of the DC transmission project; the project line information may be the transmission line corresponding to the DC transmission project. For example, the DC transmission project to be evaluated may be for the AB line, or it may be another DC transmission project for the BC line.

[0052] In a specific implementation, a user may input the engineering operating parameters and engineering line information of the DC transmission project to be evaluated in the terminal, and in response to the detected trigger operation, the terminal may obtain the engineering operating parameters and engineering line information of the DC transmission project to be evaluated.

[0053] S102, inputting the project operating parameters and project line information into a pre-trained loss assessment model; the loss assessment model is used to determine the loss information of the DC transmission project based on the project operating parameters and project line information; the loss assessment model is obtained by training a neural network model based on the training operating parameters, training line information and project loss labels of multiple different DC transmission project samples.

[0054] As an example, the loss information of the DC transmission project can be a specific loss value, such as the overall power loss of the DC transmission project, or can include the loss of each engineering component in the DC transmission project. For example, it can include the loss of at least one of the following engineering components: valve group loss, converter transformer loss, DC reactor loss, AC filter loss, DC filter loss, valve cooling system loss, bridge arm reactor loss, converter transformer loss, transmission line loss. Alternatively, the loss information can also be a loss range, such as the loss of the DC transmission project is between a% and b%.

[0055] In practical applications, the training operating parameters, training line information and engineering loss labels of multiple different DC transmission project samples can be used to pre-train the neural network model to obtain a trained loss assessment model. After obtaining the engineering operating parameters and engineering line information, the engineering operating parameters and engineering line information can be input into the pre-trained loss assessment model, and the model determines the loss information of the DC transmission project based on the input engineering operating parameters and engineering line information.

[0056] Specifically, during the training process, since a large number of DC transmission project samples are used to train the neural network model, this model can learn all the combinations of engineering operating parameters and engineering lines of the DC transmission project during training, and determine one or more loss characteristics that affect the loss of the DC transmission project in the engineering operating parameters and engineering lines under different conditions, and assign corresponding weights to one or more loss characteristics. When the training is completed, the trained neural network model, that is, the loss assessment model, can obtain the mapping relationship between the engineering operating parameters and engineering line information and the DC transmission project loss information, so that when the operating conditions and lines are changed, there is no need to manually modify the parameters, and accurate loss information can be quickly obtained.

[0057] S103, acquiring loss information of the DC power transmission project output by the loss assessment model, and determining a loss assessment result of the DC power transmission project according to the loss information.

[0058] In practical applications, when the loss assessment model inputs the loss information of the DC transmission project, the terminal can obtain the loss information and determine the loss assessment result of the DC transmission project based on the loss information. Specifically, the terminal can directly use the loss information of the DC transmission project as the loss assessment result of the DC transmission project, or can also make a qualitative or quantitative evaluation of the loss situation of the DC transmission project based on the loss information, such as an evaluation grade or evaluation score, and then generate an evaluation report based on the evaluation and output it as a loss evaluation result.

[0059] In this embodiment, the engineering operating parameters and engineering line information of the DC transmission project to be evaluated can be obtained, and the engineering operating parameters and engineering line information are input into a pre-trained loss evaluation model, wherein the loss evaluation model is used to determine the loss information of the DC transmission project based on the engineering operating parameters and engineering line information, and the loss evaluation model is obtained by training the neural network model based on the training operating parameters, training line information and engineering loss labels of multiple different DC transmission project samples; and then the terminal can obtain the loss information of the DC transmission project output by the loss evaluation model, and determine the loss evaluation result of the DC transmission project according to the loss information. In this embodiment, by using multiple DC transmission project samples to train the neural network model, the loss evaluation model is obtained, which enables the loss evaluation model to quickly learn the operating parameters of different DC transmission projects and the mapping relationship between the engineering line and the loss of the DC transmission project, so that when the operating conditions and lines are changed, there is no need to manually modify the parameters, and while quickly obtaining the loss information, the accuracy of the loss information can be ensured, effectively improving the evaluation efficiency of the loss of the DC transmission project.

[0060] In an optional embodiment, the loss assessment model can be encapsulated as an interface and embedded in the monitoring interface of the DC transmission project. When the user needs to evaluate the loss of the DC transmission project under different operating conditions or lines, the user can input the project operating parameters and project line information and call the interface, so as to quickly and conveniently obtain the loss information output by the loss assessment model for the DC transmission project.

[0061] In an exemplary embodiment, the method may further include the following steps:

[0062] S201, obtaining a training sample set, where the training sample set includes training operating condition parameters and training line information of a plurality of different first direct current transmission project samples, and a project loss label of each first direct current transmission project sample.

[0063] Among them, the DC transmission project samples are DC transmission projects used as samples to train the neural network model. In order to distinguish the DC transmission project samples in the training sample set from the DC transmission project samples in the test sample set described later, the DC transmission project samples in the training sample set are called the first DC transmission project samples.

[0064] In practical applications, before obtaining the engineering operating parameters and engineering line information of the DC transmission project to be evaluated, the terminal can train the neural network model. Specifically, a training sample set can be obtained, which includes a large number of first DC transmission project samples, and multiple first DC transmission project samples can be different, so as to cover DC transmission projects under different operating conditions and lines. At the same time, in the training sample set, an engineering loss label can be associated with each first DC transmission project, and the engineering loss label records the loss of the first DC transmission project sample during operation.

[0065] Exemplarily, the training operating condition parameters, training line information and engineering loss labels of a plurality of first DC transmission engineering samples in the training sample set may have a structure as shown in Table 1 below:

[0066] Table 1

[0067]

[0068]

[0069] Among them, the input data 1-1, 1-2...1-i are i input information of the first DC transmission project sample, which includes the training operating parameters and training line information of the first DC transmission project sample, such as the active power, reactive power, number of full half-bridge sub-modules, baseband frequency, etc. of the converter station; the output data is the project loss label.

[0070] S202, inputting the training operating condition parameters and training line information of multiple first DC power transmission project samples in the training sample set into the neural network model to be trained, and the neural network model outputs the predicted loss information of the first DC power transmission project sample based on the training operating condition parameters of each first DC power transmission project sample.

[0071] S203, adjusting the model parameters of the neural network model according to the predicted loss information and the engineering loss label until the training end condition is met to obtain a trained loss evaluation model.

[0072] After obtaining the training sample set, the training operating condition parameters and training line information of multiple first DC power transmission project samples in the training sample set can be input into the neural network model to be trained. The neural network model is based on the training operating condition parameters of each first DC power transmission project sample and outputs the predicted loss information of the first DC power transmission project sample. According to the predicted loss information and the project loss label, the model parameters of the neural network model are adjusted until the training end conditions are met to obtain a trained loss assessment model.

[0073] Specifically, the neural network model in this embodiment can be a BP (Back-propagation) neural network model. The BP neural network model is a multi-level neural network whose structure includes an input layer, a hidden layer and an output layer. Each layer of neurons is independent of each other, and the neurons between layers are interconnected by nerve lines. The nerve lines can be assigned different weights. In the process of training the neural network, the training operating parameters and training line information of the first DC power transmission project sample input into the neural network model are propagated backward from the input layer and the hidden layer. As the input signal continues to change, the neural network will continuously update the weights and thresholds of the network model, and continuously reduce the error of the final result through self-learning.

[0074] Figure 2 The structure of a neural network model is shown. In practical applications, multiple first DC transmission project samples x1, x2, x3...xj can be input through the input layer of the neural network model, and the data can be input into the hidden layer of the model through forward propagation.

[0075] For example, the i-th node (also called neuron) f in the hidden layer i Input1 i for:

[0076]

[0077] Among them, w ij For the i-th node of the input layer, for input x j The weight assigned, θ i is the threshold of the node.

[0078] The i-th node f in the hidden layer i The output of i for:

[0079] o i =f(input1 i )

[0080] Input2 of the kth node in the output layer k for:

[0081]

[0082] Among them, w ki For the kth node of the output layer, for input o i The weight assigned, a k is the threshold of the node.

[0083] The output o of the kth node in the output layer k for:

[0084]

[0085] Among them, it is used to calculate the node output o i The function f(x) and the function used to calculate the output layer output o k Function Can be an activation function.

[0086] In this embodiment, by obtaining a training sample set, the training operating condition parameters and training line information of multiple first DC power transmission project samples in the training sample set are input into the neural network model to be trained, and the neural network model is based on the training operating condition parameters of each first DC power transmission project sample and outputs the predicted loss information of the first DC power transmission project sample, and then adjusts the model parameters of the neural network model according to the predicted loss information and the project loss label until the training end condition is met, and a trained loss assessment model is obtained, which enables the neural network model to learn the losses of DC power transmission projects under various working conditions and lines, and then fits the mapping relationship between the working condition parameters, line information and the losses of the DC power transmission project, so that the losses of the DC power transmission projects under different working conditions or lines can be quickly obtained without modifying the parameters later.

[0087] In an exemplary embodiment, S203 adjusts the model parameters of the neural network model according to the predicted loss information and the engineering loss label until the training end condition is met to obtain a trained loss assessment model, which may include the following steps:

[0088] The loss value is determined according to the predicted loss information of multiple first direct current transmission project samples and the project loss label of each first direct current transmission project sample; the model parameters of the neural network model are adjusted according to the loss value and the back propagation algorithm until the training end conditions are met, thereby obtaining a trained loss assessment model.

[0089] In practical applications, after obtaining the predicted loss information of multiple first DC transmission project samples, for each first DC transmission project sample, the predicted loss information of the first DC transmission project sample can be compared with the engineering loss label of the first DC transmission project sample to determine the difference between the two, and then the loss value of the neural network model can be determined based on the difference between the multiple first DC transmission project samples and their engineering loss labels.

[0090] After obtaining the loss value, the model parameters of the neural network model can be adjusted according to the loss value and the back propagation algorithm. In other words, the loss value (also called error) and the engineering loss label (expected value) can be propagated backwards to make the neural network model adjust its model parameters accordingly. In the process of adjusting the model parameters, the weights and thresholds in the model parameters are adjusted by calculating the error between the output of all neurons in the output layer (i.e., predicted loss information) and the actual (engineering loss label). In this project, the error can be used to enable the neural network to determine how to correct the weights and thresholds of the neurons in each layer of the model. After that, the training is repeated using different first DC transmission project samples until the number of iterations or the error between the predicted loss information of the first DC transmission project sample and the engineering label is lower than the preset threshold, then it can be determined that the training is completed.

[0091] In this embodiment, the loss value can be determined according to the predicted loss information of multiple first DC power transmission project samples and the project loss label of each first DC power transmission project sample, and the model parameters of the neural network model can be adjusted according to the loss value and the back propagation algorithm until the training end condition is met to obtain a trained loss assessment model. The back propagation algorithm (i.e., error back propagation) is used for training to fit a nonlinear function. In a DC power transmission project (such as a flexible DC power transmission project), the impact of changes in operating conditions and lines on the loss of the DC power transmission project is also nonlinear. Therefore, the nonlinear relationship between the engineering operating conditions, lines and losses can be fitted according to the loss value and combined with the back propagation algorithm, so as to achieve rapid estimation of the loss of the DC power transmission project under different operating conditions or lines.

[0092] In one embodiment, adjusting the model parameters of the neural network model according to the loss value and the back propagation algorithm until the training end condition is met to obtain a trained loss evaluation model may include the following steps:

[0093] S301, adjusting the model parameters of the neural network model according to the loss value and the back propagation algorithm to obtain an adjusted neural network model.

[0094] In a specific implementation, the model parameters of the neural network model can be adjusted according to the loss value and the back propagation algorithm. When the number of iterations meets the preset number or the error between the predicted loss information of the first DC transmission project sample and the project label is lower than the preset threshold, the current neural network model can be used as the adjusted neural network model.

[0095] S302, obtaining a test sample set; the test sample set includes training operating condition parameters and training line information of multiple second DC power transmission project samples, and an engineering loss label of each second DC power transmission project sample.

[0096] Among them, the DC power transmission project sample in the test sample set is called the second DC power transmission project sample.

[0097] In practical applications, a test sample set can be pre-built, which can be used to test the trained neural network model and verify whether the current neural network model has been trained. After one or more trainings are completed using the data in the training sample set, the accuracy of the trained neural network model can be tested using the data in the test sample set.

[0098] Exemplarily, the training operating condition parameters, training line information and engineering loss labels of a plurality of first DC transmission engineering samples in the training sample set may have a structure as shown in Table 2 below:

[0099] Table 2

[0100]

[0101] Among them, the input data m+1-1, m+1-2…m+1-i are the i input information of the first DC transmission project sample, which includes the training operating parameters and training line information of the second DC transmission project sample, such as the active power, reactive power, number of full and half-bridge sub-modules, baseband frequency, etc. of the converter station; the output data is the engineering loss label of the second DC transmission project sample.

[0102] S303, inputting the training operating condition parameters and training line information of multiple second DC power transmission project samples in the test sample set into the neural network model, and the neural network model outputs the predicted loss information of each second DC power transmission project sample based on the training operating condition parameters and training line information of the second DC power transmission project sample.

[0103] S304: Determine a training error according to the predicted loss information of the plurality of second DC power transmission project samples and the project loss labels of the second DC power transmission project samples.

[0104] After obtaining the test sample set, the training operating condition parameters and training line information of multiple second DC power transmission project samples in the test sample set can be input into the neural network model to be trained, and the neural network model outputs the predicted loss information of the second DC power transmission project sample based on the training operating condition parameters of each second DC power transmission project sample, and then the training error can be determined according to the predicted loss information of the second DC power transmission project sample and its engineering loss label. Exemplarily, when determining the training error, the training errors of multiple second DC power transmission project samples can be summed to obtain the total training error D sum , and the total training error D sum The average value D mean As the final determined training error.

[0105] S305, when the training error is greater than the preset error threshold, return to the step of obtaining the training sample set, and adjust the parameters of the neural network model again until the training error is no greater than the preset error threshold, thereby obtaining a trained loss evaluation model.

[0106] As an example, the error threshold may be set according to different DC transmission projects, for example, may be set to 1%.

[0107] After obtaining the training error, it can be determined whether the training error is greater than the preset error threshold. When the training error is greater than the preset error threshold, it indicates that the accuracy of the currently trained neural network model is low, and the step of obtaining the training sample set can be returned again, and the data of the training sample set and the test sample set can be updated again, and the above steps can be repeated to continue training the neural network model. Until the adjusted neural network model is tested using a new test sample set, and the obtained training error is not greater than the error threshold, it indicates that the model error of the current neural network model is within an acceptable range, and the current neural network model can be used as a trained loss evaluation model.

[0108] For example, Figure 3 As shown, a test sample set and a training sample set can be obtained. For the training sample set, the first DC transmission project sample in the training sample set can be input into the neural network model after the model parameters are initialized to start training. After multiple iterations, the current neural network model is used as the adjusted neural network model, and the second DC transmission project sample in the test sample set is input into it to verify the accuracy of the neural network model. Then, according to the model output result, it can be judged whether it is close to the engineering loss label. If so, the loss assessment model can be obtained. If not, the neural network model continues to be trained.

[0109] After the training is completed, it can also be encapsulated into an application module so that the user can subsequently call the application module to obtain the loss information of the DC transmission project to be evaluated. For example, the operating parameters and line information of the DC transmission project are input into the trained neural network model (i.e., the loss evaluation model). Even if the operating parameters and line information are not calculated by the algorithm, the trained neural network model can also give an interval of approximately accurate results. For example, the training sample set and the test sample set only include several loss results of 800MW, 900MW, 1000MW, 3500MW, and 5000MW under the AB line and the BC line. If it is necessary to calculate the loss under specified working conditions that have not been simulated in the early stage, for example: AB line, the loss under an active power of 2000MW, there is no need to waste time changing the parameters, but the operating parameters and line information of the DC transmission project to be evaluated can be directly input into the neural network model to quickly obtain accurate loss information.

[0110] In this embodiment, by using the second DC transmission project sample in the test sample set to test the adjusted neural network model, the accuracy of the current neural network model can be verified by simulating the actual usage scenario, and training can be continued when the training error is greater than the preset error threshold, thereby effectively improving the accuracy and reliability of the loss assessment model finally obtained.

[0111] In one embodiment, the method may further include the following steps:

[0112] Acquire training operating condition parameters and training line information of multiple DC transmission project samples; determine the loss information of each DC transmission project sample according to the training operating condition parameters, line information and a preset loss algorithm of each DC transmission project sample, and use the loss information of each DC transmission project sample as the engineering loss label of the DC transmission project sample; acquire a training sample set and a test sample set according to the multiple DC transmission project samples and their engineering loss labels.

[0113] The multiple DC power transmission project samples are DC power transmission project samples with different training operating condition parameters and / or line information.

[0114] In practical applications, a large number (e.g., 10,000) of operating parameters and line information of DC transmission project samples can be collected as training operating parameters and training line information of the corresponding DC transmission project samples. After obtaining the training operating parameters and training line information of the DC transmission project samples, a preset fast loss algorithm can be used to determine the loss information of the DC transmission project samples based on the training operating parameters and training line information, and the loss information is used as the engineering loss label of the corresponding DC transmission project samples. In a specific implementation, the fast loss algorithm can be an existing algorithm for calculating the loss of DC transmission projects, and those skilled in the art can select it according to actual conditions.

[0115] After obtaining the engineering loss label, the engineering loss label can be associated with the corresponding DC power transmission engineering sample, and multiple power transmission engineering samples with the engineering loss label can be associated to obtain a training sample set and a test sample set. Exemplarily, multiple power transmission engineering samples can be randomly allocated as a test sample set and a training sample set according to a preset ratio (such as 2:8). For example, if there are 10,000 groups of power transmission engineering samples, there are 8,000 groups in the training sample set and 2,000 groups in the test sample set.

[0116] In this embodiment, a training sample set and a test sample set can be constructed according to a plurality of DC power transmission project samples and their project loss labels, so as to provide a basis for subsequent training of a power consumption evaluation model.

[0117] In one embodiment, obtaining the engineering operating parameters of the DC power transmission project to be evaluated in S101 may include:

[0118] The power information, the number of full-half-bridge submodules and the fundamental frequency of the converter station in the DC transmission project to be evaluated are obtained; and the engineering operating parameters of the DC transmission project are determined according to the power information, the number of full-half-bridge submodules and the fundamental frequency.

[0119] The full-half-bridge submodule may include a full-bridge submodule and a half-bridge submodule.

[0120] In practical applications, power information of the converter station in the DC transmission project to be evaluated, such as active power and / or reactive power, can be obtained. The number of full and half-bridge sub-modules in the DC transmission project and the fundamental frequency used by the DC transmission project can also be obtained. Then, the engineering operating parameters of the DC transmission project can be determined based on the power information, the number of full and half-bridge sub-modules and the fundamental frequency. For example, the power information, the number of full and half-bridge sub-modules and the fundamental frequency can be used as engineering operating parameters, or the engineering operating parameters can be generated in combination with parameters of other engineering components.

[0121] In this embodiment, the engineering operating parameters of the DC power transmission project can be determined based on power information, the number of full and half-bridge sub-modules, and the fundamental frequency, providing a basis for a subsequent loss assessment module to determine the loss information of the DC power transmission project under different operating conditions.

[0122] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0123] Based on the same inventive concept, the embodiment of the present application also provides a DC power transmission project loss assessment device for implementing the DC power transmission project loss assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more DC power transmission project loss assessment device embodiments provided below can refer to the above limitations on a DC power transmission project loss assessment method, and will not be repeated here.

[0124] In one embodiment, Figure 4 As shown, a DC transmission project loss assessment device is provided, comprising:

[0125] An input information acquisition module 401 is used to acquire the engineering operating parameters and engineering line information of the DC transmission project to be evaluated;

[0126] An input module 402 is used to input the engineering operating parameters and engineering line information into a pre-trained loss assessment model; the loss assessment model is used to determine the loss information of the DC power transmission project based on the engineering operating parameters and engineering line information; the loss assessment model is obtained by training a neural network model based on training operating parameters, training line information and engineering loss labels of multiple different DC power transmission project samples;

[0127] The loss assessment result acquisition module 403 is used to acquire the loss information of the DC power transmission project output by the loss assessment model, and determine the loss assessment result of the DC power transmission project according to the loss information.

[0128] In an exemplary embodiment, the apparatus further comprises:

[0129] A training sample set acquisition module is used to acquire a training sample set, wherein the training sample set includes training operating condition parameters and training line information of a plurality of different first direct current power transmission project samples, and an engineering loss label of each first direct current power transmission project sample;

[0130] A training sample input module, used for inputting the training operating condition parameters and training line information of a plurality of first DC power transmission project samples in the training sample set into the neural network model to be trained, and the neural network model outputs the predicted loss information of the first DC power transmission project sample based on the training operating condition parameters of each first DC power transmission project sample;

[0131] The parameter adjustment module is used to adjust the model parameters of the neural network model according to the predicted loss information and the engineering loss label until the training end condition is met to obtain a trained loss assessment model.

[0132] In an exemplary embodiment, the parameter adjustment module includes:

[0133] A loss value determination module, configured to determine a loss value according to the predicted loss information of the plurality of first DC power transmission project samples and a project loss label of each first DC power transmission project sample;

[0134] The training module is used to adjust the model parameters of the neural network model according to the loss value and the back propagation algorithm until the training end condition is met to obtain a trained loss evaluation model.

[0135] In an exemplary embodiment, the training module is specifically used to:

[0136] Adjusting the model parameters of the neural network model according to the loss value and the back propagation algorithm to obtain an adjusted neural network model;

[0137] Acquire a test sample set; the test sample set includes training operating condition parameters and training line information of multiple second DC power transmission project samples, and an engineering loss label of each second DC power transmission project sample;

[0138] Inputting the training operating condition parameters and training line information of a plurality of second DC power transmission project samples in the test sample set into the neural network model, and having the neural network model output the predicted loss information of each second DC power transmission project sample based on the training operating condition parameters and training line information of the second DC power transmission project sample;

[0139] Determining a training error according to the predicted loss information of the plurality of second DC power transmission project samples and the project loss labels of the second DC power transmission project samples;

[0140] When the training error is greater than a preset error threshold, return to the step of obtaining the training sample set, and adjust the parameters of the neural network model again until the training error is no greater than the preset error threshold, thereby obtaining a trained loss evaluation model.

[0141] In an exemplary embodiment, the apparatus further comprises:

[0142] A training sample parameter acquisition module is used to acquire training operating condition parameters and training line information of multiple DC power transmission project samples; the multiple DC power transmission project samples are DC power transmission project samples with different training operating condition parameters and / or line information;

[0143] A label determination module, used to determine the loss information of each DC power transmission project sample according to the training operating condition parameters, line information and a preset loss algorithm of each DC power transmission project sample, and use the loss information of each DC power transmission project sample as the project loss label of the DC power transmission project sample;

[0144] The sample set construction module is used to obtain a training sample set and a test sample set according to the multiple direct current transmission project samples and their project loss labels.

[0145] In an exemplary embodiment, the input information acquisition module 401 is specifically used to:

[0146] Obtaining power information, the number of full and half-bridge submodules, and the fundamental frequency of a converter station in the DC transmission project to be evaluated;

[0147] The engineering operating parameters of the direct current power transmission project are determined according to the power information, the number of full and half-bridge sub-modules and the fundamental frequency.

[0148] Each module in the above-mentioned DC transmission project loss assessment device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0149] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for evaluating the loss of a direct current transmission project is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0150] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0151] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0152] Obtain the engineering operating parameters and engineering line information of the DC transmission project to be evaluated;

[0153] The engineering operating parameters and engineering line information are input into a pre-trained loss assessment model; the loss assessment model is used to determine the loss information of the DC power transmission project based on the engineering operating parameters and engineering line information; the loss assessment model is obtained by training a neural network model based on training operating parameters, training line information and engineering loss labels of multiple different DC power transmission project samples;

[0154] The loss information of the DC power transmission project output by the loss assessment model is obtained, and a loss assessment result of the DC power transmission project is determined according to the loss information.

[0155] In one embodiment, when the processor executes the computer program, the steps in the other embodiments described above are also implemented.

[0156] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0157] Obtain the engineering operating parameters and engineering line information of the DC transmission project to be evaluated;

[0158] The engineering operating parameters and engineering line information are input into a pre-trained loss assessment model; the loss assessment model is used to determine the loss information of the DC power transmission project based on the engineering operating parameters and engineering line information; the loss assessment model is obtained by training a neural network model based on training operating parameters, training line information and engineering loss labels of multiple different DC power transmission project samples;

[0159] The loss information of the DC power transmission project output by the loss assessment model is obtained, and a loss assessment result of the DC power transmission project is determined according to the loss information.

[0160] In one embodiment, when the computer program is executed by a processor, the steps in the other embodiments described above are also implemented.

[0161] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0162] Step 1: Obtain the engineering operating parameters and engineering line information of the DC transmission project to be evaluated;

[0163] The engineering operating parameters and engineering line information are input into a pre-trained loss assessment model; the loss assessment model is used to determine the loss information of the DC power transmission project based on the engineering operating parameters and engineering line information; the loss assessment model is obtained by training a neural network model based on training operating parameters, training line information and engineering loss labels of multiple different DC power transmission project samples;

[0164] The loss information of the DC power transmission project output by the loss assessment model is obtained, and a loss assessment result of the DC power transmission project is determined according to the loss information.

[0165] In one embodiment, when the computer program is executed by a processor, the steps in the other embodiments described above are also implemented.

[0166] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0167] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0168] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0169] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for evaluating loss of a DC power transmission project, characterized in that: include: Acquire a training sample set, wherein the training sample set includes training operating condition parameters and training line information of a plurality of different first direct current power transmission project samples, and an engineering loss label of each first direct current power transmission project sample; Inputting the training operating condition parameters and training line information of a plurality of first DC power transmission project samples in the training sample set into the neural network model to be trained, and the neural network model outputs the predicted loss information of the first DC power transmission project sample based on the training operating condition parameters of each first DC power transmission project sample; According to the predicted loss information and the engineering loss label, the model parameters of the neural network model are adjusted until the training end condition is met to obtain a trained loss assessment model; Acquire engineering line information of a DC power transmission project to be evaluated, and acquire power information, the number of full-half-bridge submodules, and the fundamental frequency of a converter station in the DC power transmission project to be evaluated, and determine engineering operating parameters of the DC power transmission project according to the power information, the number of full-half-bridge submodules, and the fundamental frequency; Inputting the engineering operating parameters and engineering line information into the loss assessment model, and allowing the loss assessment model to determine the loss information of the DC power transmission project based on the engineering operating parameters and engineering line information; The loss information of the DC power transmission project output by the loss assessment model is obtained, and a loss assessment result of the DC power transmission project is determined according to the loss information.

2. The method according to claim 1, characterized in that The adjusting the model parameters of the neural network model according to the predicted loss information and the engineering loss label until the training end condition is met to obtain a trained loss assessment model includes: Determine a loss value according to the predicted loss information of the plurality of first DC power transmission project samples and the project loss label of each first DC power transmission project sample; The model parameters of the neural network model are adjusted according to the loss value and the back propagation algorithm until the training end condition is met to obtain a trained loss evaluation model.

3. The method according to claim 2, characterized in that The step of adjusting the model parameters of the neural network model to be trained according to the loss value and the back propagation algorithm until the training end condition is met to obtain a trained loss evaluation model includes: Adjusting the model parameters of the neural network model according to the loss value and the back propagation algorithm to obtain an adjusted neural network model; Acquire a test sample set; the test sample set includes training operating condition parameters and training line information of multiple second DC power transmission project samples, and an engineering loss label of each second DC power transmission project sample; Inputting the training operating condition parameters and training line information of a plurality of second DC power transmission project samples in the test sample set into the neural network model, and having the neural network model output the predicted loss information of each second DC power transmission project sample based on the training operating condition parameters and training line information of the second DC power transmission project sample; Determining a training error according to the predicted loss information of the plurality of second DC power transmission project samples and the project loss labels of the second DC power transmission project samples; When the training error is greater than a preset error threshold, return to the step of obtaining the training sample set, and adjust the parameters of the neural network model again until the training error is no greater than the preset error threshold, thereby obtaining a trained loss evaluation model.

4. The method according to claim 3, characterized in that Also includes: Obtaining training operating condition parameters and training line information of multiple DC transmission project samples; The plurality of DC power transmission project samples are DC power transmission project samples with different training operating condition parameters and / or line information; Determine the loss information of each DC power transmission project sample according to the training operating condition parameters, line information and a preset loss algorithm of each DC power transmission project sample, and use the loss information of each DC power transmission project sample as the project loss label of the DC power transmission project sample; A training sample set and a test sample set are obtained according to the multiple direct current transmission project samples and their project loss labels.

5. A DC power transmission project loss assessment device, characterized in that: The device comprises: A training sample set acquisition module is used to acquire a training sample set, wherein the training sample set includes training operating condition parameters and training line information of a plurality of different first direct current power transmission project samples, and an engineering loss label of each first direct current power transmission project sample; A training sample input module, used for inputting the training operating condition parameters and training line information of a plurality of first DC power transmission project samples in the training sample set into the neural network model to be trained, and the neural network model outputs the predicted loss information of the first DC power transmission project sample based on the training operating condition parameters of each first DC power transmission project sample; A parameter adjustment module, used to adjust the model parameters of the neural network model according to the predicted loss information and the engineering loss label until the training end condition is met to obtain a trained loss assessment model; An input information acquisition module is used to acquire engineering line information of a DC power transmission project to be evaluated, and to acquire power information, the number of full-half-bridge submodules, and the fundamental frequency of a converter station in the DC power transmission project to be evaluated, and to determine engineering operating parameters of the DC power transmission project according to the power information, the number of full-half-bridge submodules, and the fundamental frequency; An input module, used for inputting the engineering operating parameters and engineering line information into the loss assessment model, and the loss assessment model determines the loss information of the DC power transmission project based on the engineering operating parameters and engineering line information; The loss assessment result acquisition module is used to acquire the loss information of the DC power transmission project output by the loss assessment model, and determine the loss assessment result of the DC power transmission project according to the loss information.

6. The device according to claim 5, characterized in that The parameter adjustment module comprises: A loss value determination module, configured to determine a loss value according to the predicted loss information of the plurality of first DC power transmission project samples and a project loss label of each first DC power transmission project sample; The training module is used to adjust the model parameters of the neural network model according to the loss value and the back propagation algorithm until the training end condition is met to obtain a trained loss evaluation model.

7. The device according to claim 6, characterized in that The training module is specifically used for: Adjusting the model parameters of the neural network model according to the loss value and the back propagation algorithm to obtain an adjusted neural network model; Acquire a test sample set; the test sample set includes training operating condition parameters and training line information of multiple second DC power transmission project samples, and an engineering loss label of each second DC power transmission project sample; Inputting the training operating condition parameters and training line information of a plurality of second DC power transmission project samples in the test sample set into the neural network model, and having the neural network model output the predicted loss information of each second DC power transmission project sample based on the training operating condition parameters and training line information of the second DC power transmission project sample; Determining a training error according to the predicted loss information of the plurality of second DC power transmission project samples and the project loss labels of the second DC power transmission project samples; When the training error is greater than a preset error threshold, return to the step of obtaining the training sample set, and adjust the parameters of the neural network model again until the training error is no greater than the preset error threshold, thereby obtaining a trained loss evaluation model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.