A method for predicting and optimizing resource consumption in power distribution network maintenance plans.

Abstract

This invention proposes a method for predicting and optimizing resource consumption in distribution network maintenance plans, comprising: establishing an associated network topology based on the distribution network maintenance plan; determining resource consumption points based on the associated network topology; identifying the influencing factors of each resource consumption point; performing a correlation analysis between the resource consumption of each resource consumption point and its influencing factors; calculating the standard consumption of each resource consumption point based on the analysis results; performing horizontal and lateral predictions for each maintenance step based on the standard consumption; integrating the horizontal and lateral predictions to obtain the predicted resource consumption results for each resource consumption point; and deleting or replacing resource consumption points whose predicted resource consumption results exceed the standard consumption based on their type. This invention breaks down the maintenance plan and analyzes the corresponding influencing factors for each resource consumption point in the maintenance steps, thereby improving the accuracy of resource consumption prediction and optimization in maintenance plans.

Description

Technical Field

[0001] This invention belongs to the field of distribution network maintenance technology, and particularly relates to a method for predicting and optimizing resource consumption in distribution network maintenance plans. Background Technology

[0002] Distribution network maintenance is an essential part of power grid operation, and with the continuous expansion of the power grid, the frequency and number of maintenance operations are also increasing. Along with the increasing number of maintenance operations, the required resource consumption is also constantly rising. To utilize resources more rationally, accurate and reasonable prediction and optimization of resource consumption in maintenance plans are necessary. However, due to the different maintenance objects and work content, the influencing factors of resource consumption vary, and the relationship between resource consumption and various influencing factors is difficult to describe with a simple linear relationship. If resource consumption cannot be obtained in advance, distribution network maintenance work may not be able to proceed normally, and the reliability and safety of distribution network operation cannot be guaranteed. Currently, resource consumption prediction for distribution network maintenance is often done through empirical estimation. This method has a large margin of error and cannot guarantee the accuracy of the prediction results, thus affecting the optimization effect of the distribution network maintenance plan. Summary of the Invention

[0003] To address the shortcomings and deficiencies in existing technologies, this invention proposes a method for predicting and optimizing resource consumption in distribution network maintenance plans, comprising:

[0004] Establish the associated network topology according to the distribution network maintenance plan, and determine the resource consumption points based on the associated network topology;

[0005] Identify the influencing factors of resource consumption points, conduct a correlation analysis between the resource consumption at each resource consumption point and the influencing factors, and calculate the standard consumption at each resource consumption point based on the analysis results.

[0006] Based on the standard consumption, the maintenance steps are predicted horizontally and laterally. The horizontal and lateral predictions are integrated and processed to obtain the resource consumption prediction results of the resource consumption points.

[0007] Resource consumption points whose predicted resource consumption exceeds the standard consumption amount are identified as resource consumption points to be optimized, and are then deleted or replaced based on their type.

[0008] Optionally, the step of establishing an associated network topology based on the distribution network maintenance plan and determining resource consumption points based on the associated network topology includes: extracting the detection steps in the distribution network maintenance plan, taking the smallest basic work unit in the detection steps as the object, decomposing the resource consumption points, and establishing an associated network topology of maintenance steps and resource consumption.

[0009] Optionally, the step of performing a correlation analysis between the resource consumption at each resource consumption point and the influencing factors, and calculating the standard consumption at each resource consumption point based on the analysis results, includes:

[0010] For each resource consumption point, set the time series corresponding to its resource consumption as X0(k), k = 1, 2, ..., N, where k is the sequence number and N is the total number of sequences;

[0011] Let X be the time series group of m influencing factors corresponding to the resource consumption point. i (k), k=1, 2,...,N, i=1, 2,...,m;

[0012] Time series X0(k) of resource consumption and time series X of influencing factors i (k) Perform standardization processing, and calculate the time series x′0(k) of resource consumption and the time series group x′ of influencing factors after standardization. i The grey relational coefficient δ(k) of (k);

[0013] The grey relational degree r is calculated based on the calculated grey relational coefficient. i According to the grey relational degree r i The factors are ranked in descending order based on their magnitude.

[0014] Calculate the standard consumption amount of resource consumption points based on the ranked influencing factors.

[0015] Optionally, the formula for calculating the grey relational coefficient δ(k) is as follows:

[0016]

[0017] Among them, Δ i (k) represents the sum of the elements in the sequence x0'(k). i The difference between elements within (k), Δ i (k)-|x0'(k)-x i '(k)|, ρ is the preset resolution coefficient.

[0018] Optionally, the gray relational degree r i The calculation formula is:

[0019]

[0020] Optionally, before determining the influencing factors of resource consumption points, the prediction and optimization method further includes:

[0021] Obtain all factors influencing resource consumption, determine the contribution weight of each factor to resource consumption, and filter the factors according to their contribution weight.

[0022] Optionally, the step of making horizontal and lateral predictions of maintenance steps based on standard consumption includes:

[0023] Based on the operation time of each step, the resource consumption points of the maintenance steps, and the standard consumption, the resource consumption of each maintenance step is predicted horizontally, and the horizontal prediction subsequence is obtained based on the prediction parameters of the horizontal prediction.

[0024] Based on the life stage of the maintenance object, the resource consumption points of the maintenance steps, and the standard consumption, the resource consumption of each maintenance step is predicted longitudinally, and the longitudinal prediction subsequence is obtained based on the prediction parameters of the longitudinal prediction.

[0025] Optionally, after obtaining the resource consumption prediction results of the resource consumption points, the prediction and optimization method further includes: obtaining the resource consumption calculation results of each maintenance step when implementing the maintenance plan in real time;

[0026] If the deviation between the predicted resource consumption and the calculated resource consumption exceeds the preset fluctuation threshold range, then the maintenance process data is acquired, and the correlation between the maintenance process data and the calculated resource consumption is analyzed.

[0027] Based on the analysis results, the prediction parameters for both horizontal and vertical predictions were optimized.

[0028] Optionally, the deletion or replacement based on the type of resource consumption point includes:

[0029] Determine whether there are any alternative resource consumption points of the same type in the maintenance steps where the resource consumption point to be optimized is located.

[0030] If there are no alternative resource consumption points, the resource consumption points to be optimized are deleted or retained according to the content of the maintenance work. If there are alternative resource consumption points, the alternative resource consumption points whose resource consumption prediction results are lower than the standard consumption amount of the resource consumption points to be optimized are selected, and the resource consumption points with the lowest resource consumption prediction results are selected to replace the resource consumption points to be optimized. If all alternative resource consumption points are not lower than the standard consumption amount, the resource consumption points to be optimized are not processed.

[0031] Optionally, the step of deleting or retaining resource consumption points to be optimized based on the content of the maintenance work includes:

[0032] Extract the maintenance results of the maintenance steps where the resource consumption points to be optimized are located based on the content of the maintenance work;

[0033] Determine the impact of directly deleting the resource consumption point to be optimized on the maintenance results. If the impact on the maintenance results is within the preset controllable range, then directly delete the resource consumption point to be optimized; otherwise, retain the resource consumption point to be optimized.

[0034] The beneficial effects of the technical solution provided by this invention are:

[0035] (1) It can break down the maintenance steps of the maintenance plan, analyze the corresponding influencing factors of resource consumption points in each maintenance step, refine resource consumption, construct the network topology of resource consumption and maintenance steps, and predict the resource consumption of each maintenance step to improve the accuracy of resource consumption prediction for the maintenance plan. After completing the resource consumption prediction, it also optimizes the network topology based on the prediction results to further reduce the resource consumption of the maintenance plan.

[0036] (2) By using grey relational analysis to obtain the correlation between resource consumption and influencing factors, it can adapt to different situations, analyze the relationship between variable influencing factors and resource consumption, and ensure the accuracy of resource consumption prediction for maintenance steps.

[0037] (3) Based on the resource consumption prediction results, resource consumption monitoring can be carried out to monitor the deviation of resource consumption. When a deviation occurs, the deviation can be analyzed and the parameters of the prediction sequence can be optimized based on the analysis results to improve the prediction accuracy. Attached Figure Description

[0038] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating a method for predicting and optimizing resource consumption in a distribution network maintenance plan, as proposed in an embodiment of the present invention.

[0040] Figure 2 This is the original network topology diagram of the maintenance steps and resource consumption of a certain power equipment according to an embodiment of the present invention;

[0041] Figure 3 This is an optimized network topology diagram of the maintenance steps and resource consumption of a certain power equipment according to an embodiment of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein.

[0044] It should be understood that in the various embodiments of the present invention, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0045] It should be understood that in this invention, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.

[0046] It should be understood that in this invention, "multiple" refers to two or more. "And / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, "and / or B" can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "Contains A, B, and C", "Contains A, B, and C" means that all three A, B, and C are contained; "Contains A, B, or C" means that one of A, B, and C is contained; "Contains A, B, and / or C" means that any one, two, or three of A, B, and C are contained.

[0047] It should be understood that in this invention, "B corresponding to A", "B corresponding to A", "A and B correspond", or "B and A correspond" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information. Matching A and B is defined as a similarity between A and B that is greater than or equal to a preset threshold.

[0048] Depending on the context, "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection."

[0049] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0050] Example:

[0051] like Figure 1 As shown in the figure, this embodiment proposes a method for predicting and optimizing resource consumption in distribution network maintenance plans, including:

[0052] S1: Establish the associated network topology according to the distribution network maintenance plan, and determine the resource consumption points based on the associated network topology;

[0053] S2: Determine the influencing factors of resource consumption points, conduct correlation analysis between resource consumption at each resource consumption point and influencing factors, and calculate the standard consumption at each resource consumption point based on the analysis results;

[0054] S3: Based on the standard consumption, perform horizontal and lateral predictions for the maintenance steps, integrate the horizontal and lateral predictions, and obtain the resource consumption prediction results for the resource consumption points.

[0055] S4: Resource consumption points whose predicted resource consumption exceeds the standard consumption amount are identified as resource consumption points to be optimized, and are deleted or replaced according to the type of resource consumption points to be optimized.

[0056] Considering that resource consumption includes investment costs for maintenance projects and replacement of aging equipment during maintenance, in this embodiment, the resource consumption points include spare parts consumption for equipment required for the repair, maintenance and protection of power facilities, transportation resource consumption for equipment spare parts, and corresponding human resource consumption.

[0057] In this embodiment, influencing factors are analyzed from four dimensions: operation level, project level, equipment level, and asset level. This allows for the analysis of influencing factors at each resource consumption point based on the dimensions involved in the maintenance steps, ensuring that the acquisition of influencing factors is comprehensive and accurate.

[0058] In this embodiment, the step of establishing an associated network topology based on the distribution network maintenance plan and determining resource consumption points based on the associated network topology includes: extracting the detection steps in the distribution network maintenance plan, taking the smallest basic work unit in the detection steps as the object, decomposing the resource consumption points, and establishing an associated network topology of maintenance steps and resource consumption.

[0059] In this embodiment, in S2, the resource consumption of each resource consumption point is obtained through grey relational analysis based on its correlation with influencing factors. The specific process of obtaining the standard consumption amount through grey relational analysis is as follows:

[0060] S21: For each resource consumption point, set the time series corresponding to its resource consumption as X0(k), k = 1, 2, ..., N, where k is the sequence number and N is the total number of sequences.

[0061] S22: Set the time series group of the m influencing factors corresponding to the resource consumption point as X. i (k), k=1, 2,...,N, i=1, 2,...,m.

[0062] S23: Time series X0(k) of resource consumption and time series group X of influencing factors i (k) Perform standardization processing, and calculate the time series x0'(k) of resource consumption and the time series group x of influencing factors after standardization. i The grey relational coefficient δ(k) of '(k) is calculated using the following formula:

[0063]

[0064] Among them, Δ i (k) represents the sum of the elements in the sequence x0'(k). i The difference between elements within (k), Δ i (k)-|x0'(k)-x i '(k)|, ρ is the preset resolution coefficient. D min and D max These are the maximum and minimum differences between the two ranges, respectively. ρ is the resolution coefficient. The smaller ρ is, the greater the resolution. Generally, the value range of ρ is (0, 1). In this embodiment, the value of ρ is 0.5.

[0065] S24: Calculate the grey relational degree r based on the calculated grey relational coefficient. i According to the grey relational degree r i The influencing factors are ranked in descending order based on their magnitude. The grey relational degree r... i The calculation formula is:

[0066]

[0067] S25: Calculate the standard consumption of resource consumption points based on the ranked influencing factors. Specifically, the conversion factor can be determined according to the ranking of the influencing factors. The higher the ranking, the greater the impact of the influencing factor on resource consumption, and the smaller the conversion factor should be set for it. Calculate the product of the basic resource consumption corresponding to each influencing factor and the conversion factor, and add all the products together to obtain the standard consumption of the resource consumption point.

[0068] In this embodiment, before determining the influencing factors of resource consumption points, all influencing factors of resource consumption can be obtained, the contribution weight of each influencing factor to resource consumption can be determined, and the influencing factors can be screened according to their contribution weights. Grey relational analysis can then be performed on the screened influencing factors. Screening the influencing factors effectively reduces the computational load of subsequent grey relational analysis, further improving prediction efficiency and speed.

[0069] In this embodiment, a decomposition-integration method is used for prediction based on the point-line relationships in the interconnected network topology. Firstly, regarding decomposition, resource consumption is sequentially decomposed according to correlation relationships. By calculating the standard consumption value between each resource consumption point and its influencing factors, a standard resource consumption system is constructed, providing systematic support for the resource consumption prediction of each maintenance step. Secondly, regarding integration, the horizontal and vertical prediction results are mutually corrected, and the corrected resource consumption prediction results of each step are integrated to obtain the overall resource consumption prediction result for the maintenance plan.

[0070] Considering that resource consumption at the same resource consumption point can fluctuate over time—for example, longer operation times for the same maintenance item or shorter remaining service life of the maintenance item will lead to greater resource consumption—this embodiment decomposes and predicts resource consumption across two time dimensions: horizontal and vertical. Specifically, based on the operation time, resource consumption points of the maintenance steps, and standard consumption, the resource consumption of each maintenance step is predicted horizontally, and a horizontal prediction subsequence is obtained based on the prediction parameters of the horizontal prediction.

[0071] Based on the life stage of the maintenance object, the resource consumption points of the maintenance steps, and the standard consumption, the resource consumption of each maintenance step is predicted longitudinally, and the longitudinal prediction subsequence is obtained based on the prediction parameters of the longitudinal prediction.

[0072] Both the horizontal and vertical predictions are achieved through a pre-trained time-series prediction model. During the training phase, the time-series prediction model is trained based on historical resource consumption data at each resource consumption point, using two time dimensions: step operation time and maintenance object means stage. This embodiment uses conventional model training methods, which will not be elaborated here.

[0073] In this embodiment, an ensemble is trained by integrating horizontal and lateral predictions using ensemble learning methods in machine learning. The lateral and vertical prediction subsequences are input into the ensemble, and the lateral and vertical prediction results are fused to obtain the resource consumption prediction results of the integrated sequence resource consumption points.

[0074] This embodiment also includes: after obtaining the resource consumption prediction results for resource consumption points, setting a corresponding fluctuation threshold range for resource consumption during the implementation of each step based on the predicted resource consumption results for each step, and calculating the resource consumption in real time during the implementation of each step, comparing it with the resource consumption fluctuation threshold range, and detecting resource consumption deviations in real time. Specifically:

[0075] The system acquires real-time resource consumption calculations for each maintenance step during the implementation of the maintenance plan. If the deviation between the predicted and calculated resource consumption exceeds a preset fluctuation threshold range, maintenance process data is acquired, and the correlation between the maintenance process data and the calculated resource consumption is analyzed. Based on the analysis results, the prediction parameters for both horizontal and vertical predictions are optimized. Simultaneously, the fluctuation threshold range is modified based on the optimized integrated prediction sequence.

[0076] After the prediction is completed, the accuracy of the prediction is judged during the implementation process, and deviations are detected in real time. When deviations occur, the cause of the deviation and the type and quantity of resources consumed due to the deviation are analyzed by the correlation between maintenance process data and resource consumption data. This allows for the optimization of the integrated prediction sequence and the improvement of the accuracy of subsequent resource consumption predictions.

[0077] In this embodiment, if the predicted resource consumption exceeds the standard consumption, one of the optimization methods will be deleted or replaced, including:

[0078] Determine whether there are any alternative resource consumption points of the same type in the maintenance steps where the resource consumption point to be optimized is located.

[0079] If there are no alternative resource consumption points, the resource consumption points to be optimized are deleted or retained according to the content of the maintenance work. Specifically, the maintenance results of the maintenance steps where the resource consumption points to be optimized are located are extracted according to the content of the maintenance work. The impact of directly deleting the resource consumption points to be optimized on the maintenance results is judged. If the impact on the maintenance results is within the preset controllable range, the resource consumption points to be optimized are directly deleted; otherwise, the resource consumption points to be optimized are retained.

[0080] If there are alternative resource consumption points, select those whose predicted resource consumption is lower than the standard consumption of the resource consumption point to be optimized, and replace the resource consumption point to be optimized with the one whose predicted resource consumption is the lowest. If all alternative resource consumption points are not lower than the standard consumption, then the resource consumption point to be optimized will not be processed.

[0081] The following example uses a maintenance plan for a power equipment. The plan includes four maintenance steps, each with several resource consumption points. Based on the maintenance work content, these resource consumption points are identified, and using these points as nodes, an original network topology diagram relating the maintenance steps and resource consumption is established. The original network topology diagram is shown below. Figure 2 As shown, the specific resource consumption points are: resource consumption point A in maintenance step one, resource consumption point B in maintenance step two, resource consumption point C in maintenance step three, and resource consumption points D, E, and F in maintenance step four. According to the resource consumption prediction results, the predicted resource consumption amounts for each point are: resource consumption point A = 10, resource consumption point B = 10, resource consumption point C = 30, resource consumption point D = 1, resource consumption point E = 15, and resource consumption point F = 30. Since the standard consumption value for each point is 20, resource consumption points C and F can be identified as nodes with excessive resource consumption.

[0082] Taking the optimization of resource consumption point C as an example, firstly, the type of resources consumed by resource consumption point C is determined, and the maintenance results of maintenance step three are obtained based on the maintenance work content of maintenance step three. Then, the resource consumption types of other resource consumption points in step three are judged, and resource consumption points G and H, which are of the same type as resource consumption point C, are selected. Based on the obtained maintenance results, the predicted resource consumption of resource consumption point G is determined to be 10, and the predicted resource consumption of resource consumption point H is 21. Although the predicted resource consumption of resource consumption point H is less than that of resource consumption point C, it is higher than the standard consumption value. Therefore, resource consumption point G is used here to replace the node corresponding to resource consumption point C, realizing the network topology optimization for resource consumption point C.

[0083] Taking resource consumption point F as an example, the type of resource consumed by resource consumption point F is determined, and the maintenance result of maintenance step four is obtained based on the maintenance work content of maintenance step four. Then, the resource consumption types of other resource consumption points in step four are judged, and it is determined that there are no resource consumption points of the same type as resource consumption point F. At this point, resource consumption point F is pre-deleted. Based on the resource consumption of resource consumption points D and E and the maintenance work content, the maintenance result of step four is estimated. It can be seen that after deleting resource consumption point F, the required maintenance result can still be obtained through the resource consumption of resource consumption points D and E. Therefore, resource consumption point F is directly deleted, realizing the network topology optimization for resource consumption point F.

[0084] Finally, the optimized network topology of resource consumption points C and F is as follows: Figure 3 As shown, resource consumption point C was replaced by resource consumption point G, which consumes less resources, and resource consumption point F was deleted.

[0085] The serial numbers in the above embodiments are for descriptive purposes only and do not represent the order in which the components are assembled or used.

[0086] The above description is merely an embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for predicting and optimizing resource consumption in distribution network maintenance plans, characterized in that, The prediction and optimization method includes: Establish the associated network topology according to the distribution network maintenance plan, and determine the resource consumption points based on the associated network topology; Identify the influencing factors of resource consumption points, conduct a correlation analysis between the resource consumption at each resource consumption point and the influencing factors, and calculate the standard consumption at each resource consumption point based on the analysis results. Based on the standard consumption, the maintenance steps are predicted horizontally and laterally. The horizontal and lateral predictions are integrated and processed to obtain the resource consumption prediction results of the resource consumption points. Resource consumption points whose predicted resource consumption exceeds the standard consumption amount are identified as resource consumption points to be optimized, and are deleted or replaced according to the type of resource consumption points to be optimized. The method of making horizontal and lateral predictions of maintenance steps based on standard consumption includes: Based on the operation time of each step, the resource consumption points of the maintenance steps, and the standard consumption, the resource consumption of each maintenance step is predicted horizontally, and the horizontal prediction subsequence is obtained based on the prediction parameters of the horizontal prediction. Based on the life stage of the maintenance object, the resource consumption points of the maintenance steps, and the standard consumption, the resource consumption of each maintenance step is predicted longitudinally, and the longitudinal prediction subsequence is obtained based on the prediction parameters of the longitudinal prediction. After obtaining the resource consumption prediction results for the resource consumption points, the prediction and optimization method further includes: Real-time acquisition of resource consumption calculation results for each maintenance step during the implementation of the maintenance plan; If the deviation between the predicted resource consumption and the calculated resource consumption exceeds the preset fluctuation threshold range, then the maintenance process data is acquired, and the correlation between the maintenance process data and the calculated resource consumption is analyzed. Based on the analysis results, the prediction parameters for both horizontal and vertical predictions were optimized.

2. The method for predicting and optimizing resource consumption in distribution network maintenance plans according to claim 1, characterized in that, The step of establishing an associated network topology based on the distribution network maintenance plan and determining resource consumption points based on the associated network topology includes: extracting the detection steps in the distribution network maintenance plan, taking the smallest basic work unit in the detection steps as the object, decomposing the resource consumption points, and establishing an associated network topology between the maintenance steps and resource consumption.

3. The method for predicting and optimizing resource consumption in distribution network maintenance plans according to claim 1, characterized in that, The process of performing a correlation analysis between resource consumption and influencing factors at each resource consumption point, and calculating the standard consumption at each resource consumption point based on the analysis results, includes: For each resource consumption point, set the time series corresponding to its resource consumption as follows: k = 1, 2, ..., N, where k is the sequence number and N is the total number of sequences; Set the time series group of m influencing factors corresponding to the resource consumption point as follows: ,k=1,2,…,N,i=1,2,…,m; Time series of resource consumption Time series of influencing factors Perform standardization processing and calculate the time series of resource consumption after standardization. and time series groups of influencing factors Grey relational coefficient ; The grey relational degree is calculated based on the calculated grey relational coefficient. According to grey relational degree The factors are ranked in descending order based on their magnitude. Calculate the standard consumption amount of resource consumption points based on the ranked influencing factors.

4. The method for predicting and optimizing resource consumption in distribution network maintenance plans according to claim 3, characterized in that, The grey relational coefficient The calculation formula is: in, For sequence Inner elements and Difference between inner elements , , , This is the preset resolution coefficient.

5. The method for predicting and optimizing resource consumption in distribution network maintenance plans according to claim 3, characterized in that, The gray relational degree The calculation formula is: 。 6. The method for predicting and optimizing resource consumption in distribution network maintenance plans according to claim 1, characterized in that, Before determining the influencing factors of resource consumption points, the prediction and optimization method further includes: Obtain all factors influencing resource consumption, determine the contribution weight of each factor to resource consumption, and filter the factors according to their contribution weight.

7. The method for predicting and optimizing resource consumption in distribution network maintenance plans according to claim 1, characterized in that, The deletion or replacement based on the type of resource consumption point includes: Determine whether there are any alternative resource consumption points of the same type in the maintenance steps where the resource consumption point to be optimized is located. If there are no alternative resource consumption points, the resource consumption points to be optimized should be deleted or retained according to the content of the maintenance work. If there are alternative resource consumption points, filter out alternative resource consumption points whose resource consumption prediction results are lower than the standard consumption of the resource consumption point to be optimized, and select the resource consumption point to be optimized with the lowest resource consumption prediction results to replace the resource consumption point to be optimized. If all candidate resource consumption points are not lower than the standard consumption amount, then the resource consumption points to be optimized will not be processed.

8. The method for predicting and optimizing resource consumption in distribution network maintenance plans according to claim 7, characterized in that, The process of deleting or retaining resource consumption points to be optimized based on the content of the maintenance work includes: Extract the maintenance results of the maintenance steps where the resource consumption points to be optimized are located based on the content of the maintenance work; Determine the impact of directly deleting the resource consumption point to be optimized on the maintenance results. If the impact on the maintenance results is within the preset controllable range, then directly delete the resource consumption point to be optimized; otherwise, retain the resource consumption point to be optimized.

Images