Method and apparatus for predicting the risk of current imbalance in parallel cables in the same direction

Abstract

This application relates to a method and apparatus for predicting the current imbalance risk of parallel cables in the same direction. The method includes: acquiring historical current data of the circuit corresponding to the parallel cable in the same direction; identifying the sending-end data parameters and receiving-end data parameters of the parallel cable in the same direction based on the historical current data; constructing a grayscale prediction model of the parallel cable in the same direction based on the sending-end and receiving-end data parameters; adjusting the grayscale prediction model through a model optimization strategy to obtain a target grayscale prediction model; predicting the predicted current imbalance of the parallel cable in the same direction based on the sending-end and receiving-end data parameters and the target grayscale prediction model; and identifying the current imbalance risk information of the parallel cable in the same direction based on the predicted current imbalance. This method can improve the accuracy of analyzing the current imbalance risk of parallel cables in the same direction.

Description

Technical Field

[0001] This application relates to the field of parallel cables in the same direction, and in particular to a method and apparatus for predicting the risk of current imbalance in parallel cables in the same direction. Background Technology

[0002] With the development of power systems, transformer capacity is constantly changing and showing an increasing trend. In new substations, the incoming current of the main transformer is often very large. At this time, a single cable cannot meet the circuit current requirements, and multiple cables are usually used in parallel. However, in practice, the current distribution is not uniform. There is often a current difference of tens of amperes or more between two cables of the same phase. This leads to an imbalance in the current carrying capacity of the parallel cables in the same direction. Therefore, monitoring and early warning of unbalanced phase current is crucial for the control and fault alarm rate of the power grid, especially the distribution network.

[0003] Current methods for detecting and warning of unbalanced phase currents target the impact mechanisms of voltage deviation and three-phase imbalance on cable core losses. They quantify and analyze cable line losses under the influence of voltage deviation and three-phase imbalance based on simulation data to obtain unbalanced phase current data. However, this method relies on historical cable laying data and known cable loads. Since the output current of substations is not always balanced in actual operation, the accuracy of analyzing the risk of current imbalance in parallel cables in the same direction is low. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for predicting the current imbalance risk of parallel cables in the same direction, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for predicting the risk of current imbalance in parallel cables connected in the same direction. The method includes:

[0006] Obtain historical current data of the circuit corresponding to the parallel cable in the same phase, and based on the historical current data, identify the sending end data parameters and the receiving end data parameters of the parallel cable in the same direction.

[0007] Based on the sending end data parameters and the receiving end data parameters, a grayscale prediction model for the parallel cable in the same direction is constructed, and the grayscale prediction model is adjusted through a model optimization strategy to obtain a target grayscale prediction model.

[0008] Based on the sending-end data parameters and the receiving-end data parameters, the predicted current imbalance of the parallel cable in the same phase is predicted using the target grayscale prediction model, and the risk information of the current imbalance of the parallel cable in the same direction is identified based on the predicted current imbalance.

[0009] Optionally, identifying the sending-end data parameters and receiving-end data parameters of the parallel cable in the same direction based on the historical current data includes:

[0010] Obtain the impedance information of the parallel cables in the same direction, and construct the network equation of the parallel cables in the same direction based on the impedance information;

[0011] The network equations are matrixed to obtain the impedance matrix of the parallel cable in the same direction. Based on the historical current data, the sending-end data parameters and receiving-end data parameters of the parallel cable in the same direction are calculated using the impedance matrix.

[0012] Optionally, the step of constructing a grayscale prediction model for the parallel cable in the same direction based on the sending-end data parameters and the receiving-end data parameters includes:

[0013] The sending end data parameters and the receiving end data parameters are arranged in chronological order to obtain the first data column of the sending end and the second data column of the receiving end.

[0014] Based on the first data column of the sending end and the second data column of the receiving end, a grayscale prediction model for the parallel cable in the same direction is constructed using an exponential curve expression.

[0015] Optionally, adjusting the grayscale prediction model through a model optimization strategy to obtain the target grayscale prediction model includes:

[0016] The average relative residual value of the gray-scale prediction model is calculated using a residual test strategy, and the average level ratio deviation value of the gray-scale prediction model is calculated using a level ratio deviation test strategy.

[0017] When the average relative residual value is not less than a preset residual threshold, or the average stage ratio deviation value is not less than a preset deviation threshold, the process returns to the step of constructing the gray-scale prediction model of the parallel cable in the same direction based on the first data column of the sending end and the second data column of the receiving end through an exponential curve expression. This process continues until the average relative residual value is less than a preset residual threshold and the average stage ratio deviation value is less than a preset deviation threshold. Then, the gray-scale prediction model obtained in the last iteration is used as the target gray-scale prediction model.

[0018] Optionally, the step of predicting the predicted current-carrying imbalance of the parallel-connected cable based on the sending-end data parameters and the receiving-end data parameters using the target grayscale prediction model includes:

[0019] Based on the sending end data parameters and the receiving end data parameters, the target grayscale prediction model is used to predict the predicted data of the sending end and the predicted data of the receiving end.

[0020] Based on the predicted data from the sending end and the predicted data from the receiving end, the unbalance degree of each phase of the parallel cable, the average unbalance degree of the parallel cable, and the unbalance degree of the receiving end of the parallel cable are calculated using an unbalance degree algorithm.

[0021] The phase imbalance, the average imbalance, and the receiving end imbalance are used as the predicted current-carrying imbalance of the parallel cable in the same phase.

[0022] Optionally, identifying the risk information of current-carrying imbalance of the parallel cables in the same direction based on the predicted current-carrying imbalance includes:

[0023] Obtain the setting values ​​for each type of unbalance of the parallel cable in the same direction, and determine the deviation index value corresponding to each setting value based on the historical unbalance information of the parallel cable in the same phase.

[0024] Based on the predicted cable imbalance, the imbalance of each type is identified, and based on the imbalance of each type, the setting value of each type, and the deviation index value corresponding to each setting value, abnormal imbalance types are screened.

[0025] The abnormal imbalance type and the imbalance corresponding to the abnormal imbalance type are used as the current-carrying imbalance risk information of the parallel cable in the same direction.

[0026] Secondly, this application also provides a device for predicting the risk of current imbalance in parallel cables in the same direction. The device includes:

[0027] The acquisition module is used to acquire historical current data of the circuit corresponding to the parallel cable in the same phase, and based on the historical current data, identify the sending end data parameters and the receiving end data parameters of the parallel cable in the same phase.

[0028] The adjustment module is used to construct a grayscale prediction model of the parallel cable in the same direction based on the sending end data parameters and the receiving end data parameters, and adjust the grayscale prediction model through a model optimization strategy to obtain a target grayscale prediction model.

[0029] The prediction module is used to predict the predicted current imbalance of the parallel cable in the same phase based on the sending end data parameters and the receiving end data parameters, using the target grayscale prediction model, and to identify the risk information of the current imbalance of the parallel cable in the same phase based on the predicted current imbalance.

[0030] Optionally, the acquisition module is specifically used for:

[0031] Obtain the impedance information of the parallel cables in the same direction, and construct the network equation of the parallel cables in the same direction based on the impedance information;

[0032] The network equations are matrixed to obtain the impedance matrix of the parallel cable in the same direction. Based on the historical current data, the sending-end data parameters and receiving-end data parameters of the parallel cable in the same direction are calculated using the impedance matrix.

[0033] Optionally, the adjustment module is specifically used for:

[0034] The sending end data parameters and the receiving end data parameters are arranged in chronological order to obtain the first data column of the sending end and the second data column of the receiving end.

[0035] Based on the first data column of the sending end and the second data column of the receiving end, a grayscale prediction model for the parallel cable in the same direction is constructed using an exponential curve expression.

[0036] Optionally, the adjustment module is specifically used for:

[0037] The average relative residual value of the gray-scale prediction model is calculated using a residual test strategy, and the average level ratio deviation value of the gray-scale prediction model is calculated using a level ratio deviation test strategy.

[0038] When the average relative residual value is not less than a preset residual threshold, or the average stage ratio deviation value is not less than a preset deviation threshold, the process returns to the step of constructing the gray-scale prediction model of the parallel cable in the same direction based on the first data column of the sending end and the second data column of the receiving end through an exponential curve expression. This process continues until the average relative residual value is less than a preset residual threshold and the average stage ratio deviation value is less than a preset deviation threshold. Then, the gray-scale prediction model obtained in the last iteration is used as the target gray-scale prediction model.

[0039] Optionally, the prediction module is specifically used for:

[0040] Based on the sending end data parameters and the receiving end data parameters, the target grayscale prediction model is used to predict the predicted data of the sending end and the predicted data of the receiving end.

[0041] Based on the predicted data from the sending end and the predicted data from the receiving end, the unbalance degree of each phase of the parallel cable, the average unbalance degree of the parallel cable, and the unbalance degree of the receiving end of the parallel cable are calculated using an unbalance degree algorithm.

[0042] The phase imbalance, the average imbalance, and the receiving end imbalance are used as the predicted current-carrying imbalance of the parallel cable in the same phase.

[0043] Optionally, the prediction module is specifically used for:

[0044] Obtain the setting values ​​for each type of unbalance of the parallel cable in the same direction, and determine the deviation index value corresponding to each setting value based on the historical unbalance information of the parallel cable in the same phase.

[0045] Based on the predicted cable imbalance, the imbalance of each type is identified, and based on the imbalance of each type, the setting value of each type, and the deviation index value corresponding to each setting value, abnormal imbalance types are screened.

[0046] The abnormal imbalance type and the imbalance corresponding to the abnormal imbalance type are used as the current-carrying imbalance risk information of the parallel cable in the same direction.

[0047] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0048] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0049] Fifthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0050] The aforementioned method and apparatus for predicting the current imbalance risk of parallel cables in the same direction involves acquiring historical current data of the circuit corresponding to the parallel cable in the same direction, and identifying the sending-end data parameters and receiving-end data parameters of the parallel cable in the same direction based on the current data; constructing a gray-scale prediction model of the parallel cable in the same direction based on the sending-end data parameters and the receiving-end data parameters, and adjusting the gray-scale prediction model through a model optimization strategy to obtain a target gray-scale prediction model; predicting the predicted current imbalance of the parallel cable in the same direction based on the sending-end data parameters and the receiving-end data parameters, and identifying the current imbalance risk information of the parallel cable in the same direction based on the predicted current imbalance. This solution uses historical current data to identify the sending-end and receiving-end parameters of the parallel cable in the same direction, thereby constructing a grayscale prediction model for the cable. This model is then optimized to ensure the accuracy of the predicted current imbalance. By analyzing the predicted current imbalance of the parallel cable in the same direction, the solution identifies the risk information related to current imbalance, avoiding the problem of reduced current load and lower power transmission utilization caused by phase-to-phase current carrying capacity differences due to parameter imbalance at the sending and receiving ends. By analyzing the current imbalance of the cable based on parameter imbalance at both ends, this solution ensures the accuracy of the acquired risk information while maximizing the current carrying capacity of each cable in the same phase, thus improving the cable's current carrying capacity utilization and comprehensively enhancing the accuracy of the analysis of current imbalance risks in parallel cables in the same direction. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating a method for predicting the risk of current imbalance in parallel cables in the same direction, as shown in one embodiment.

[0052] Figure 2 This is a flowchart illustrating a parallel cable circuit model in one embodiment.

[0053] Figure 3 This is a flowchart illustrating an example of predicting the risk of current imbalance in parallel cables in the same direction, as shown in one embodiment.

[0054] Figure 4 This is a structural block diagram of a current imbalance risk prediction device for parallel cables in the same direction in one embodiment.

[0055] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] The current imbalance risk prediction method for parallel cables in the same direction provided in this application embodiment can be applied to application environments where the current imbalance risk of parallel cables in the same direction is a concern. This method can be applied to a terminal, a server, or a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, etc. The terminal identifies the sending-end and receiving-end data parameters of the parallel cable in the same direction using historical current data, thereby constructing a grayscale prediction model for the parallel cable in the same direction. This grayscale prediction model is then optimized to ensure the accuracy of the predicted current imbalance. Finally, by using the predicted current imbalance of the parallel cable in the same direction, the risk information of the current imbalance is identified, avoiding the problem of reduced current load and lower power transmission utilization caused by phase-to-phase current carrying capacity differences due to parameter imbalance at the sending and receiving ends. This solution analyzes the current-carrying imbalance of cables by considering the imbalance of parameters at the sending and receiving ends. It ensures the accuracy of the current-carrying imbalance risk information of parallel cables in the same direction while maximizing the utilization of the current-carrying capacity of each cable in the same phase. This improves the current-carrying capacity utilization of the cables and thus comprehensively enhances the accuracy of the analysis of the current-carrying imbalance risk of parallel cables in the same direction.

[0058] In one embodiment, such as Figure 1 As shown, a method for predicting the current imbalance risk of parallel cables in the same direction is provided. Taking the application of this method to a terminal as an example, the method includes the following steps:

[0059] Step S101: Obtain historical current data of the circuit corresponding to the parallel cable in the same phase, and based on the historical current data, identify the sending end data parameters and receiving end data parameters of the parallel cable in the same direction.

[0060] In this embodiment, the terminal uses data collected over historical periods by a current detection device installed in the parallel cable to identify the current data of each phase cable and the voltage data of each cable in the parallel cable circuit, thereby obtaining historical current data. For example, Figure 2The diagram shows a circuit model of a parallel cable in the same direction, where a, b, and c are the phase identifiers for each of the three phases in the parallel cable. Then, based on this historical current data, the terminal identifies the sending-end data parameters and the receiving-end data parameters of the parallel cable. The sending-end data parameters are the sending-end voltage parameters, and the receiving-end data parameters are the receiving-end load information parameters. The specific identification process will be explained in detail later.

[0061] Step S102: Based on the data parameters of the sending end and the data parameters of the receiving end, construct a gray-scale prediction model for parallel cables in the same direction, and adjust the gray-scale prediction model through a model optimization strategy to obtain the target gray-scale prediction model.

[0062] In this embodiment, the terminal constructs a grayscale prediction model for the parallel cables in the same direction based on the data parameters from the sending end and the data parameters from the receiving end. Then, through a model optimization strategy, the grayscale prediction model is adjusted to obtain the target grayscale prediction model. The specific construction process will be described in detail later. This grayscale prediction model is a function model based on an exponential fitting curve.

[0063] Step S103: Based on the sending end data parameters and the receiving end data parameters, the predicted current imbalance of the parallel cable in the same phase is predicted through the target grayscale prediction model, and the risk information of the current imbalance of the parallel cable in the same direction is identified based on the predicted current imbalance.

[0064] In this embodiment, the terminal, based on the sending-end data parameters and the receiving-end data parameters, uses a target grayscale prediction model to predict the predicted current-carrying imbalance of the parallel cables in the same phase, and identifies the risk information of the current-carrying imbalance of the parallel cables in the same direction based on the predicted current-carrying imbalance. The predicted current-carrying imbalance includes the imbalance of each phase, the average imbalance, and the receiving-end imbalance. The receiving-end imbalance characterizes the imbalance between the currents in two phases compared to the other two phases; the specific identification process will be explained in detail later.

[0065] Based on the above scheme, historical current data is used to identify the sending-end and receiving-end parameters of the parallel cable in the same direction, thereby constructing a gray-scale prediction model for the parallel cable. This gray-scale prediction model is then optimized to ensure the accuracy of the predicted current imbalance. By using the predicted current imbalance of the parallel cable in the same direction, the risk information of current imbalance is identified, avoiding the problem of reduced current load and lower power transmission utilization caused by phase-to-phase current carrying capacity differences due to parameter imbalance at the sending and receiving ends. This scheme analyzes the current imbalance of the cable based on parameter imbalance at the sending and receiving ends, ensuring the accuracy of the obtained risk information while maximizing the current carrying capacity of each cable in the same phase, thus improving the cable's current carrying capacity utilization and comprehensively enhancing the accuracy of analyzing the risk of current imbalance in parallel cables in the same direction.

[0066] Optionally, based on historical current data, the sending-end data parameters and receiving-end data parameters of the parallel cable in the same direction are identified, including: obtaining the impedance information of the parallel cable in the same direction, and constructing the network equation of the parallel cable in the same direction based on the impedance information; performing matrix processing on the network equation to obtain the impedance matrix of the parallel cable in the same direction, and calculating the sending-end data parameters and receiving-end data parameters of the parallel cable in the same direction based on historical current data and the impedance matrix.

[0067] In this embodiment, the terminal acquires the impedance information of the parallel cables in the same direction and constructs the network equation of the parallel cables based on the impedance information. Then, the terminal performs matrix processing on the network equation to obtain the impedance matrix of the parallel cables in the same direction, and calculates the sending-end data parameters and receiving-end data parameters of the parallel cables in the same direction using the impedance matrix based on historical current data.

[0068] Specifically, such as Figure 2 As shown, if only the series impedance of the cable is considered, the following network equation can be obtained:

[0069] E a =Z C1C1 I C1 +Z C1C2 I C2 +Z C1C3 I C3 +Z C1C4 I C4 +Z C1C5 I C5 +Z C1C6 I C6

[0070] +Z C1S1 IS1 +Z C1S2 I S2 +z C1S3 I S3 +Z C1S4 I S4 +Z C1S5 I S5 +Z C1S6 I S6 +Z a I C1 +U N

[0071] In the above formula, E a U is the voltage at the sending end of cable core 1. C1 and U' C1 These are the voltage phasors of the sending and receiving ends, respectively; I C1 I C2 , ..., I C6 For the current of the 6 sub-cable cores, I S1 I S2 , ..., I S6 Z represents the sheath current of the corresponding sub-cable; C1C1 The self-impedance of cable core #1; Z C1S2 Z represents the mutual impedance between cable core 1 and cable sheath 2, and so on. a For phase A load, Z N This is the resistance at the neutral point. Similarly, similar equations apply to the sheath of cable #1, as well as the cores and sheaths of the remaining sub-cables.

[0072] Represented in matrix form, we obtain a 12×12 impedance matrix, which can then be divided into four 6×6 block matrices:

[0073]

[0074] In the above formula, By analogy, we can obtain ΔU S Z CS Z SC Z SS , and I S The expression:

[0075] U N =(I C1 +I C2 +I C3 +I C4 +I C5 +I C6 )Z N

[0076] The terminal can obtain the sending-end voltage and receiving-end load information parameters by measuring the current and neutral point voltage of the three-phase six-circuit line.

[0077] Based on the above scheme, the sending-end voltage and receiving-end load information parameters can be obtained by acquiring historical current data, which improves the efficiency and accuracy of acquiring sending-end voltage and receiving-end load information parameters.

[0078] Optionally, based on the data parameters of the sending end and the data parameters of the receiving end, a gray-scale prediction model for the parallel cable in the same direction is constructed, including: arranging the data parameters of the sending end and the data parameters of the receiving end in chronological order to obtain a first data column of the sending end and a second data column of the receiving end; and constructing a gray-scale prediction model for the parallel cable in the same direction using an exponential curve expression based on the first data column of the sending end and the second data column of the receiving end.

[0079] In this embodiment, the terminal arranges the sending-end data parameters and the receiving-end data parameters in chronological order to obtain a first data column for the sending end and a second data column for the receiving end. Then, based on the first data column for the sending end and the second data column for the receiving end, the terminal constructs a grayscale prediction model for the parallel cables in the same direction using an exponential curve expression.

[0080] Specifically, the terminal determines the data parameters based on the sending end and the receiving end, such as... Figure 2 As shown, taking the voltage of phase A at the sending end as an example, its observed data on sequence k is denoted as x. i (k), where k = 1, 2, 3, ..., n. This can be denoted as X. i =(x i (1),x i (2),…,x i (n)). By summing them up, we get a new data column x. (1) (t), using the expression of an exponential curve to approximate the sequence x. (1) (t) Correspondingly, a first-order ordinary differential equation can be constructed to solve for the functional expression of the fitted exponential curve:

[0081]

[0082] To eliminate data randomness, the following definition is defined:

[0083] z i =(z i (1),z i (2),…,z i (n))

[0084] in:

[0085] z i (m)=δx (1) (m)+(1-δ)x(1) (m-1)

[0086] The differential equation is changed to:

[0087] x (0) (t)=-az(t)+u

[0088] That is, the gray-scale prediction model.

[0089] Based on the above scheme, by fitting exponential curves, the first data column corresponding to the sending data parameters and the second data column corresponding to the receiving data parameters are fitted to construct a gray-scale prediction model, which improves the accuracy and simplicity of the constructed gray-scale prediction model.

[0090] Optionally, the grayscale prediction model is adjusted through a model optimization strategy to obtain a target grayscale prediction model, including: calculating the average relative residual value of the grayscale prediction model through a residual test strategy, and calculating the average level ratio deviation value of the grayscale prediction model through a level ratio deviation test strategy; when the average relative residual value is not less than a preset residual threshold, or the average level ratio deviation value is not less than a preset deviation threshold, the step of reverting to the execution of constructing a grayscale prediction model for a parallel cable in the same direction based on the first data column of the sending end and the second data column of the receiving end through an exponential curve expression is repeated until the average relative residual value is less than a preset residual threshold and the average level ratio deviation value is less than a preset deviation threshold, and the grayscale prediction model obtained in the last iteration is used as the target grayscale prediction model.

[0091] In this embodiment, the terminal calculates the average relative residual value of the grayscale prediction model through a residual test strategy, and calculates the average level ratio deviation value of the grayscale prediction model through a level ratio deviation test strategy.

[0092] Specifically, the terminal residual testing strategy requires calculation.

[0093] 1. Absolute residual

[0094] 2. Relative residuals

[0095] 3. Mean relative residual

[0096] when The gray-scale prediction model is considered to meet the residual requirements.

[0097] The grade ratio deviation test strategy requires calculation

[0098] Grade ratio deviation

[0099] Average grade ratio deviation

[0100] When the average grade ratio deviation The gray-scale prediction model is considered to meet the residual requirements.

[0101] Then, the terminal determines the relationship between the average relative residual value and the preset residual threshold, and the relationship between the average grade ratio deviation value and the preset deviation threshold. When the average relative residual value is not less than the preset residual threshold, or the average grade ratio deviation value is not less than the preset deviation threshold, the terminal returns to execute the step of constructing a grayscale prediction model for the parallel cable in the same direction based on the first data column of the sending end and the second data column of the receiving end through an exponential curve expression. This process continues until the average relative residual value is less than the preset residual threshold and the average grade ratio deviation value is less than the preset deviation threshold. At this point, the grayscale prediction model obtained from the last iteration is used as the target grayscale prediction model.

[0102] Based on the above scheme, when the model's prediction effect is not good, the gray-scale prediction model is adjusted and the model's prediction effect is re-tested, thereby ensuring that the prediction effect of the obtained target gray-scale prediction model is better and improving the prediction effect of the target gray-scale prediction model.

[0103] Optionally, based on the sending-end data parameters and the receiving-end data parameters, the predicted current-carrying imbalance of the parallel cable in the same phase is predicted using a target grayscale prediction model. This includes: predicting the predicted data at the sending end and the predicted data at the receiving end using the target grayscale prediction model based on the sending-end data parameters and the receiving-end data parameters; calculating the phase imbalance of the parallel cable in the same phase, the average imbalance of the parallel cable in the same direction, and the receiving-end imbalance of the parallel cable in the same phase using an imbalance algorithm based on the predicted data at the sending end and the receiving end; and using the phase imbalance, the average imbalance, and the receiving-end imbalance as the predicted current-carrying imbalance of the parallel cable in the same phase.

[0104] In this embodiment, the terminal predicts the data sent from the sending end and the data received from the receiving end based on the data parameters of the receiving end and the target grayscale prediction model.

[0105] Specifically, the terminal solves the target gray-scale prediction model using the least squares method. The least squares method is used to minimize the sum of squared deviations between the observed and estimated values ​​of the dependent variable to obtain the relevant parameters. Substituting these parameters back into the differential equation yields the following:

[0106]

[0107] Based on solving the equations, the predicted values ​​can be obtained. These are the transmission voltage (i.e., the predicted data at the sending end) and the predicted load at the receiving end. (i.e., the predicted data at the receiving end).

[0108] Then, based on the predicted data from the sending end and the receiving end, the terminal calculates the phase imbalance of the parallel cable in the same phase, the average imbalance of the parallel cable in the same direction, and the receiving end imbalance of the parallel cable in the same phase using an imbalance algorithm. Finally, the terminal uses the phase imbalance, the average imbalance, and the receiving end imbalance as the predicted current-carrying imbalance of the parallel cable in the same phase.

[0109] Specifically, such as Figure 2 As shown, the terminal calculates the cable imbalance for the next time period based on the predicted data from the sending end and the receiving end. The calculation formula is as follows:

[0110]

[0111] In the above formula, the predicted value Predicted value By analogy, we can obtain ΔU S Z CS Z SC Z SS , and I S The expression:

[0112] U N =(I C1 +I C2 +I C3 +I C4 +I C5 +I C6 )Z N

[0113] The cable core current can be calculated.

[0114] Further calculations are performed on the unbalance of each phase and the average unbalance. Taking phase A as an example, the two unbalances of phase A are:

[0115] UF a =|I C1 / I C2 -1|

[0116] In-phase unbalance is:

[0117]

[0118] When the receiving end is unbalanced, that is, when the current in two currents of one phase is too large compared to the other two phases, an early warning is also required. Therefore, the receiving end unbalance degree is defined as:

[0119]

[0120] Based on the above scheme, the predicted current-carrying imbalance is determined by calculating the imbalance of each phase, the average imbalance, and the receiving-end imbalance, thereby improving the comprehensiveness of the determined predicted current-carrying imbalance.

[0121] Optionally, based on the predicted current-carrying imbalance, the risk information of the current-carrying imbalance of parallel cables in the same direction is identified, including: obtaining the setting values ​​for each type of imbalance of the parallel cables in the same direction, and determining the deviation index value corresponding to each setting value based on the historical imbalance information of the parallel cables in the same phase; identifying the imbalance of each type of imbalance based on the predicted cable imbalance, and filtering abnormal imbalance types based on the imbalance of each type of imbalance, the setting value of each type of imbalance, and the deviation index value corresponding to each setting value; and using the abnormal imbalance types and the imbalance corresponding to the abnormal imbalance types as the risk information of the current-carrying imbalance of the parallel cables in the same direction.

[0122] In this embodiment, the terminal acquires the setting values ​​for each unbalance type of the parallel cables in the same direction, and determines the deviation index value corresponding to each setting value based on the historical unbalance information of the parallel cables in the same phase. Then, based on the predicted cable unbalance, the terminal identifies the unbalance of each unbalance type, and filters abnormal unbalance types based on the unbalance of each unbalance type, the setting value of each unbalance type, and the deviation index value corresponding to each setting value. The unbalance types include phase unbalance type, average unbalance type, and receiving-end unbalance type.

[0123] The process of determining the deviation index value corresponding to each setting value based on the historical unbalance information of parallel cables of the same phase is as follows: the terminal identifies the current-carrying unbalance corresponding to each unbalance type in the historical unbalance information, identifies the normal current-carrying unbalance range of each unbalance type, and then calculates the deviation index value corresponding to each setting value through the setting value of each unbalance type and the normal current-carrying unbalance range of each unbalance type.

[0124] Finally, the terminal uses the abnormal imbalance type and the corresponding imbalance as the current-carrying imbalance risk information of the parallel cable in the same direction.

[0125] Based on the above scheme, by analyzing the current-carrying imbalance of different unbalance types of parallel cables in the same direction, the abnormal compensation imbalance type and the corresponding compensation imbalance are determined, thereby improving the accuracy and comprehensiveness of identifying the risk information of current-carrying imbalance of parallel cables in the same direction.

[0126] This application also provides an example of predicting the risk of current imbalance in parallel cables in the same direction, such as... Figure 3As shown, the specific processing procedure includes the following steps:

[0127] Step S301: Obtain historical current data of the circuit corresponding to the parallel cable in the same phase.

[0128] Step S302: Obtain the impedance information of the parallel cables in the same direction, and construct the network equation of the parallel cables in the same direction based on the impedance information.

[0129] Step S303: The network equations are matrixed to obtain the impedance matrix of the parallel cables in the same direction. Based on historical current data, the sending-end data parameters and receiving-end data parameters of the parallel cables in the same direction are calculated using the impedance matrix.

[0130] Step S304: Arrange the sending end data parameters and the receiving end data parameters in chronological order to obtain the first data column of the sending end and the second data column of the receiving end.

[0131] Step S305: Based on the first data column of the sending end and the second data column of the receiving end, a gray-scale prediction model for parallel cables in the same direction is constructed using an exponential curve expression.

[0132] Step S306: Calculate the average relative residual value of the gray-scale prediction model using the residual test strategy, and calculate the average level ratio deviation value of the gray-scale prediction model using the level ratio deviation test strategy.

[0133] Step S307: When the average relative residual value is not less than the preset residual threshold or the average stage ratio deviation value is not less than the preset deviation threshold, return to the execution step of constructing the gray-scale prediction model of the parallel cable in the same direction based on the first data column of the sending end and the second data column of the receiving end through the exponential curve expression, until the average relative residual value is less than the preset residual threshold and the average stage ratio deviation value is less than the preset deviation threshold, and the gray-scale prediction model obtained in the last iteration is used as the target gray-scale prediction model.

[0134] Step S308: Based on the sending end data parameters and the receiving end data parameters, the target grayscale prediction model is used to predict the sending end data and the receiving end data.

[0135] Step S309: Based on the predicted data from the sending end and the predicted data from the receiving end, the unbalance of each phase of the parallel cable in the same phase, the average unbalance of the parallel cable in the same direction, and the unbalance of the receiving end of the parallel cable in the same phase are calculated using the unbalance algorithm.

[0136] Step S310: The phase imbalance, average imbalance, and receiving-end imbalance are used as the predicted current-carrying imbalance of the parallel cable in the same phase.

[0137] Step S311: Obtain the setting values ​​for each type of unbalance of the parallel cables in the same direction, and determine the deviation index value corresponding to each setting value based on the historical unbalance information of the parallel cables in the same phase.

[0138] Step S312: Based on the predicted cable unbalance, identify the unbalance of each unbalance type, and based on the unbalance of each unbalance type, the setting value of each unbalance type, and the deviation index value corresponding to each setting value, filter the abnormal unbalance types.

[0139] Step S313: The abnormal imbalance type and the imbalance corresponding to the abnormal imbalance type are used as the current-carrying imbalance risk information of the parallel cable in the same direction.

[0140] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0141] Based on the same inventive concept, this application also provides a device for predicting the current imbalance risk of parallel cables in the same direction, used to implement the aforementioned method for predicting the risk of current imbalance in parallel cables. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the device for predicting the current imbalance risk of parallel cables provided below can be found in the limitations of the method for predicting the current imbalance risk of parallel cables in the above text, and will not be repeated here.

[0142] In one embodiment, such as Figure 4 As shown, a device for predicting the current imbalance risk of parallel cables in the same direction is provided, comprising: an acquisition module 410, an adjustment module 420, and a prediction module 430, wherein:

[0143] The acquisition module 410 is used to acquire historical current data of the circuit corresponding to the parallel cable in the same phase, and based on the historical current data, identify the sending end data parameters and the receiving end data parameters of the parallel cable in the same phase.

[0144] The adjustment module 420 is used to construct a grayscale prediction model of the parallel cable in the same direction based on the sending end data parameters and the receiving end data parameters, and adjust the grayscale prediction model through a model optimization strategy to obtain a target grayscale prediction model.

[0145] The prediction module 430 is used to predict the predicted current imbalance of the parallel cable in the same phase based on the sending end data parameters and the receiving end data parameters, through the target grayscale prediction model, and to identify the risk information of the current imbalance of the parallel cable in the same phase based on the predicted current imbalance.

[0146] Optionally, the acquisition module 410 is specifically used for:

[0147] Obtain the impedance information of the parallel cables in the same direction, and construct the network equation of the parallel cables in the same direction based on the impedance information;

[0148] The network equations are matrixed to obtain the impedance matrix of the parallel cable in the same direction. Based on the historical current data, the sending-end data parameters and receiving-end data parameters of the parallel cable in the same direction are calculated using the impedance matrix.

[0149] Optionally, the adjustment module 420 is specifically used for:

[0150] The sending end data parameters and the receiving end data parameters are arranged in chronological order to obtain the first data column of the sending end and the second data column of the receiving end.

[0151] Based on the first data column of the sending end and the second data column of the receiving end, a grayscale prediction model for the parallel cable in the same direction is constructed using an exponential curve expression.

[0152] Optionally, the adjustment module 420 is specifically used for:

[0153] The average relative residual value of the gray-scale prediction model is calculated using a residual test strategy, and the average level ratio deviation value of the gray-scale prediction model is calculated using a level ratio deviation test strategy.

[0154] When the average relative residual value is not less than a preset residual threshold, or the average stage ratio deviation value is not less than a preset deviation threshold, the process returns to the step of constructing the gray-scale prediction model of the parallel cable in the same direction based on the first data column of the sending end and the second data column of the receiving end through an exponential curve expression. This process continues until the average relative residual value is less than a preset residual threshold and the average stage ratio deviation value is less than a preset deviation threshold. Then, the gray-scale prediction model obtained in the last iteration is used as the target gray-scale prediction model.

[0155] Optionally, the prediction module 430 is specifically used for:

[0156] Based on the sending end data parameters and the receiving end data parameters, the target grayscale prediction model is used to predict the predicted data of the sending end and the predicted data of the receiving end.

[0157] Based on the predicted data from the sending end and the predicted data from the receiving end, the unbalance degree of each phase of the parallel cable, the average unbalance degree of the parallel cable, and the unbalance degree of the receiving end of the parallel cable are calculated using an unbalance degree algorithm.

[0158] The phase imbalance, the average imbalance, and the receiving end imbalance are used as the predicted current-carrying imbalance of the parallel cable in the same phase.

[0159] Optionally, the prediction module 430 is specifically used for:

[0160] Obtain the setting values ​​for each type of unbalance of the parallel cable in the same direction, and determine the deviation index value corresponding to each setting value based on the historical unbalance information of the parallel cable in the same phase.

[0161] Based on the predicted cable imbalance, the imbalance of each type is identified, and based on the imbalance of each type, the setting value of each type, and the deviation index value corresponding to each setting value, abnormal imbalance types are screened.

[0162] The abnormal imbalance type and the imbalance corresponding to the abnormal imbalance type are used as the current-carrying imbalance risk information of the parallel cable in the same direction.

[0163] Each module in the aforementioned risk prediction device for current imbalance of parallel cables can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0164] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for predicting the risk of current imbalance in parallel cables in the same direction. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse.

[0165] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0166] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any one of the first aspects.

[0167] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0168] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0169] 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, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0170] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this 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), magnetic 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0171] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0172] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for predicting the risk of current imbalance in parallel cables in the same direction, characterized in that, The method includes: Obtain historical current data of the circuit corresponding to the parallel cable in the same phase, and based on the historical current data, identify the sending end data parameters and the receiving end data parameters of the parallel cable in the same direction. The sending end data parameters and the receiving end data parameters are arranged in chronological order to obtain the first data column of the sending end and the second data column of the receiving end. Based on the first data column of the sending end and the second data column of the receiving end, a gray-scale prediction model for the parallel cable in the same direction is constructed using an exponential curve expression. By adjusting the grayscale prediction model through a model optimization strategy, a target grayscale prediction model is obtained. Based on the sending-end data parameters and the receiving-end data parameters, the predicted current imbalance of the parallel cable in the same phase is predicted using the target grayscale prediction model. Based on the predicted current imbalance, the risk information of the current imbalance of the parallel cable in the same direction is identified. The risk information of the current imbalance includes the abnormal imbalance type and the imbalance corresponding to the abnormal imbalance type.

2. The method according to claim 1, characterized in that, The step of identifying the sending-end data parameters and receiving-end data parameters of the parallel cable in the same direction based on the historical current data includes: Obtain the impedance information of the parallel cables in the same direction, and construct the network equation of the parallel cables in the same direction based on the impedance information; The network equations are matrixed to obtain the impedance matrix of the parallel cable in the same direction. Based on the historical current data, the sending-end data parameters and receiving-end data parameters of the parallel cable in the same direction are calculated using the impedance matrix.

3. The method according to claim 1, characterized in that, The step of adjusting the grayscale prediction model through a model optimization strategy to obtain the target grayscale prediction model includes: The average relative residual value of the gray-scale prediction model is calculated using a residual test strategy, and the average level ratio deviation value of the gray-scale prediction model is calculated using a level ratio deviation test strategy. When the average relative residual value is not less than a preset residual threshold, or the average stage ratio deviation value is not less than a preset deviation threshold, the process returns to the step of constructing the gray-scale prediction model of the parallel cable in the same direction based on the first data column of the sending end and the second data column of the receiving end through an exponential curve expression. This process continues until the average relative residual value is less than a preset residual threshold and the average stage ratio deviation value is less than a preset deviation threshold. Then, the gray-scale prediction model obtained in the last iteration is used as the target gray-scale prediction model.

4. The method according to claim 1, characterized in that, The step of predicting the predicted current-carrying imbalance of the parallel-connected cable based on the sending-end data parameters and the receiving-end data parameters, using the target grayscale prediction model, includes: Based on the sending end data parameters and the receiving end data parameters, the target grayscale prediction model is used to predict the predicted data of the sending end and the predicted data of the receiving end. Based on the predicted data from the sending end and the predicted data from the receiving end, the unbalance degree of each phase of the parallel cable, the average unbalance degree of the parallel cable, and the unbalance degree of the receiving end of the parallel cable are calculated using an unbalance degree algorithm. The phase imbalance, the average imbalance, and the receiving end imbalance are used as the predicted current-carrying imbalance of the parallel cable in the same phase.

5. The method according to claim 1, characterized in that, The step of identifying the risk information of current imbalance of the parallel cables in the same direction based on the predicted current imbalance includes: Obtain the setting values ​​for each type of unbalance of the parallel cable in the same direction, and determine the deviation index value corresponding to each setting value based on the historical unbalance information of the parallel cable in the same phase. Based on the predicted cable imbalance, the imbalance of each type is identified, and based on the imbalance of each type, the setting value of each type, and the deviation index value corresponding to each setting value, abnormal imbalance types are screened. The abnormal imbalance type and the imbalance corresponding to the abnormal imbalance type are used as the current-carrying imbalance risk information of the parallel cable in the same direction.

6. A device for predicting the risk of current imbalance in parallel cables in the same direction, characterized in that, The device includes: The acquisition module is used to acquire historical current data of the circuit corresponding to the parallel cable in the same phase, and based on the historical current data, identify the sending end data parameters and the receiving end data parameters of the parallel cable in the same phase. The adjustment module is used to arrange the sending-end data parameters and the receiving-end data parameters in chronological order to obtain a first data column for the sending end and a second data column for the receiving end; based on the first data column for the sending end and the second data column for the receiving end, a grayscale prediction model for the parallel cable in the same direction is constructed using an exponential curve expression; and the grayscale prediction model is adjusted using a model optimization strategy to obtain a target grayscale prediction model. The prediction module is used to predict the predicted current imbalance of the parallel cable in the same phase based on the sending end data parameters and the receiving end data parameters, using the target grayscale prediction model, and to identify the current imbalance risk information of the parallel cable in the same phase based on the predicted current imbalance; the current imbalance risk information includes the abnormal imbalance type and the imbalance corresponding to the abnormal imbalance type.

7. The apparatus according to claim 6, characterized in that, The acquisition module is specifically used for: Obtain the impedance information of the parallel cables in the same direction, and construct the network equation of the parallel cables in the same direction based on the impedance information; The network equations are matrixed to obtain the impedance matrix of the parallel cable in the same direction. Based on the historical current data, the sending-end data parameters and receiving-end data parameters of the parallel cable in the same direction are calculated using the impedance matrix.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images