Substation planning method, electronic device, and storage medium

Abstract

This invention provides a substation planning method, electronic device, and storage medium. First, it acquires the electrical characteristics, area characteristics, and scale data of the target substation. Then, it inputs these characteristics into an improved random forest model to obtain a preliminary cost estimate for the target substation. The number of random forest splits and decision trees in the improved random forest model are determined using a differential evolution algorithm. Based on the preliminary cost estimate and preset planning standards, a planning scheme for the target substation is determined. By using a random forest model incorporating a differential evolution algorithm to estimate the project cost of the target substation, a simpler and faster method for determining the planning scheme can be achieved compared to traditional manual planning.

Description

Technical Field

[0001] This invention belongs to the field of substation planning technology, and particularly relates to a substation planning method, electronic equipment and storage medium. Background Technology

[0002] Substation engineering is a major component of power grid construction. During the planning and implementation phases of substation projects, cost estimations are typically required to determine the rationality of existing plans and to support optimized decision-making for substation project construction.

[0003] In the existing technology, the substation engineering planning stage requires calculation of engineering quantities, equipment and labor costs, and time planning, which involves a large workload and requires planners to have certain engineering experience. Therefore, the existing substation planning methods are relatively cumbersome. Summary of the Invention

[0004] In view of this, the present invention provides a substation planning method, electronic device and storage medium, aiming to solve the problem of cumbersome substation planning in the prior art.

[0005] A first aspect of this invention provides a substation planning method, comprising:

[0006] Obtain the electrical characteristics, area characteristics, and scale data of the target substation;

[0007] Electrical characteristics, area characteristics, and scale data are input into the improved random forest model to obtain the preliminary calculation results of the target substation; the number of random forest splits and the number of decision trees in the improved random forest model are determined according to the differential evolution algorithm.

[0008] Based on the preliminary cost estimate and pre-set planning standards for the target substation, the planning scheme for the target substation is determined.

[0009] A second aspect of the present invention provides a substation planning device, comprising:

[0010] The acquisition module is used to acquire the electrical characteristics, area characteristics, and scale data of the target substation;

[0011] The calculation module is used to input electrical characteristics, area characteristics, and scale data into the improved random forest model to obtain the preliminary calculation results of the target substation; wherein, the number of random forest splits and the number of decision trees in the improved random forest model are determined according to the differential evolution algorithm;

[0012] The determination module is used to determine the planning scheme for the target substation based on the preliminary cost estimate and preset planning standards.

[0013] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the substation planning method of the first aspect above.

[0014] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the substation planning method of the first aspect above.

[0015] This invention provides a substation planning method, electronic device, and storage medium. First, it acquires the electrical characteristics, area characteristics, and scale data of the target substation. Then, it inputs these data into an improved random forest model to obtain a preliminary cost estimate for the target substation. The number of random forest splits and decision trees in the improved random forest model are determined using a differential evolution algorithm. Based on the preliminary cost estimate and preset planning standards, a planning scheme for the target substation is determined. By using a random forest model incorporating a differential evolution algorithm to estimate the project cost of the target substation, a simpler and faster method for determining the planning scheme can be achieved compared to traditional manual planning. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0017] Figure 1 This is an application scenario diagram of the substation planning method provided in the embodiments of the present invention;

[0018] Figure 2 This is a flowchart illustrating the implementation of the substation planning method provided in this embodiment of the invention.

[0019] Figure 3 This is a flowchart of the substation engineering budget provided in an embodiment of the present invention;

[0020] Figure 4 This is a flowchart of the substation engineering cost estimate under the random forest model;

[0021] Figure 5 This is a flowchart of the substation engineering budget estimation under the improved random forest model provided in this embodiment of the invention;

[0022] Figure 6This is a comparison curve between the preliminary calculation results obtained by the traditional random forest model and the improved random forest model of this invention;

[0023] Figure 7 Comparison curves between the average relative errors of the preliminary calculation results obtained by the traditional random forest model and the improved random forest model of this invention;

[0024] Figure 8 This is a schematic diagram of the substation planning device provided in an embodiment of the present invention;

[0025] Figure 9 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0026] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0027] Figure 1 This is an application scenario diagram of the substation planning method provided in the embodiments of the present invention. For example... Figure 1 As shown, in some embodiments, the substation planning method provided by the present invention can be applied to, but is not limited to, this application scenario. In this embodiment of the invention, the system includes: at least one terminal 11 and an electronic device 12.

[0028] Terminal 11 is the terminal used by substation designers. After completing the design scheme of the target substation, the substation designers draw it into drawings in the corresponding format and upload it to electronic device 12. After receiving the drawings, electronic device 12 extracts the data in the drawings and performs cost estimation, thereby obtaining the planning scheme of the target substation under the estimated cost. Then, the planning scheme is sent to the terminal of the corresponding designer. The designer adjusts the design scheme according to the planning scheme and repeats the above process until the design scheme reaches the optimal level. If the calculated cost estimation result is not much different from the preset planning standard, the final design scheme of the target substation is determined.

[0029] Figure 2 This is a flowchart illustrating the implementation of the substation planning method provided in this embodiment of the invention. Figure 2 As shown, in some embodiments, the substation planning method is applied to Figure 1 The method of the electronic device 12 shown may include:

[0030] S210: Obtain the electrical characteristics, area characteristics, and scale data of the target substation.

[0031] In this embodiment of the invention, electrical characteristics may include voltage level, number of main transformers, single unit capacity, etc., and are not limited herein. Area characteristics may include overall area, area of ​​each region within the substation, etc., and are not limited herein. Scale data may include project quantity, total cost, etc., and are not limited herein.

[0032] S220: Input electrical characteristics, area characteristics, and scale data into the improved random forest model (Differential Evolution-Random Forest, DE-RF) to obtain the preliminary calculation results of the target substation; wherein, the number of random forest splits and the number of decision trees in the improved random forest model are determined according to the differential evolution algorithm.

[0033] In this embodiment of the invention, the estimated result of the target substation is specifically the estimated cost value of the target substation, which can be the overall estimated cost value of the target substation or the estimated cost value of each region, and is not limited here. The division of regions within the target substation can be based on importance or geographical location, and is not limited here.

[0034] S230. Based on the preliminary budget results and pre-set planning standards of the target substation, determine the planning scheme for the target substation.

[0035] In this embodiment of the invention, if the estimated result is specifically the estimated cost of the target substation, then the preset planning standard is the overall target cost of the target substation. The estimated cost is compared with the overall target cost to determine the specific planning scheme for the target substation.

[0036] If the preliminary cost estimate is for each region, the corresponding pre-set planning standard is the regional target cost for each region of the target substation. The preliminary cost estimate for each region is compared with the regional target cost for that region, and then the comparison results for each region are weighted and calculated to determine the specific planning scheme for the target substation.

[0037] In this embodiment of the invention, the project cost estimate of the target substation is realized by using a random forest model that incorporates differential evolution algorithm. Compared with the traditional manual planning method, the planning scheme of the target substation can be determined more simply and quickly.

[0038] In some embodiments, the expression for the Gini index of the improved random forest model is:

[0039]

[0040]

[0041] Among them, G D，A Let G be the Gini index, D be the dataset input to the improved random forest model, D1 be the first subset of the dataset, D2 be the second subset of the dataset, and G be the Gini index. Dj (D j Let be the j-th regression tree, where j = 1 or 2, m is the total number of data categories in the j-th subset, and p i Let be the frequency of occurrence of the i-th type of data.

[0042] Figure 3 This is a flowchart of a substation engineering cost estimate provided in an embodiment of the present invention. Figure 3 As shown, in some embodiments, before S220, the method may further include: acquiring historical engineering data corresponding to the target substation; determining the number of random forest splits and the number of decision trees based on the historical engineering data and the differential evolution algorithm; and establishing an improved random forest model based on the number of random forest splits and the number of decision trees.

[0043] In this embodiment of the invention, the differential evolution algorithm is a highly effective optimization algorithm. When building a random forest model, the initial number of random forest splits and the initial number of decision trees are first input, and then the differential evolution algorithm is used to iterate continuously to finally optimize and obtain the optimal number of random forest splits and the number of decision trees, thereby making the preliminary calculation results calculated by the improved random forest model more accurate.

[0044] In some embodiments, after determining the number of random forest splits and the number of decision trees based on historical engineering data and differential evolution algorithm, the method further includes: randomly sampling the historical engineering data according to guided aggregation algorithm to obtain the dataset corresponding to each decision tree.

[0045] In this embodiment of the invention, by introducing a bootstrap aggregating (Bagging) algorithm into the regression tree calculation and randomly sampling historical engineering data, the prediction accuracy of the regression tree calculation can be effectively improved.

[0046] In some embodiments, the fitness function of the improved random forest model is:

[0047]

[0048] Among them, E i For fitness, y(k) is the historical estimate obtained based on the kth historical project data, s(k) is the actual value corresponding to the kth historical project data, and M is the total number of historical project data.

[0049] In this embodiment of the invention, after determining the improved random forest model based on historical sample data of substation projects and the differential evolution algorithm, the historical project data can be predicted based on the improved random forest model to obtain the predicted value. Then, the difference between the predicted value and the actual value is calculated, the difference is squared and summed, and the reciprocal of the sum is taken to obtain the fitness value function optimized by the differential evolution algorithm (DE).

[0050] In some embodiments, the differential evolution algorithm includes a random operator, a crossover operator, and a selection operator.

[0051] In this embodiment of the invention, DE is a random, population-based selection tool that deals with continuous spatial domains. It is a parallel direct search method that uses a population size parameter vector, where the population consists of real-valued vectors.

[0052] If no known data is available, the initial population is randomly selected. The optimization process is carried out through three main operations: random mutation, crossover, and selection.

[0053] (1) Initialize the population:

[0054] There is a lower bound for each parameter j. and upper limit Initial parameter values ​​are usually in the range Randomly selected from among them.

[0055] (2) Random mutation:

[0056] For a given parameter vector V i,G Randomly select three vectors (X) r1,G ,X r2,G ,X r3,G This makes its exponents i, r1, r2, and r3 different. A donor vector V is created by adding the weighted difference between two vectors to a third vector. i,G+1 The formula for calculating the random operator can then be obtained:

[0057] V i，G+1 =X r1,G +F(X r2,G -X r3,G (4)

[0058] Where F is a constant between (0, 2).

[0059] (3) Crossover operator:

[0060] Three parents are selected for hybridization, with the offspring representing a perturbation of one of the parents. The experimental vector V... j,i,G+1 The elements of the target vector (Y) and the donor vector (X)j,i,G+1 The elements of the donor vector are composed of [variables]. The probability CR of an element of the donor vector entering the trial vector is:

[0061]

[0062] Among them, U j,i,G+1 I is the parameter vector after the crossover. rand Let be a random integer between (1, D), where D is the dimension of the solution, i.e., the number of control variables. rand Ensure V i,G+1 ≠V i,G .

[0063] (4) Selection Operator

[0064] The target vector V i,G With the test vector V i,G+1 The vectors with better fitness values ​​are compared and allowed to enter the next generation. The selection operation in DE can be represented by the following formula.

[0065]

[0066] Where i∈[1,N] p F() represents the function for calculating the fitness value.

[0067] In some embodiments, S230 may include: determining the optimizability level of the target substation based on the preliminary estimate and preset planning standards; and determining the optimization scheme of the target substation based on the optimizability level and the optimization priority of each item in the target substation.

[0068] In this embodiment of the invention, the estimated cost result specifically refers to the estimated cost value of each region, and the corresponding preset planning standard specifically refers to the regional target cost of each region of the target substation. The difference between the estimated cost value of each region and the regional target cost of that region is calculated, and then the difference is divided by the regional target cost to obtain the evaluation value of that region. The pre-set planning importance of each region is then used as a weight to perform a weighted calculation on the evaluation value to obtain the total evaluation value. Finally, the total evaluation value is placed within the evaluation interval corresponding to each preset optimizable level for comparison to determine the optimizable level of the target substation. Then, combined with the optimization priority of each project within the region, the final optimization scheme for the target substation is determined.

[0069] In some embodiments, S210 may include: acquiring drawings of the target substation; identifying the drawings of the target substation to obtain the electrical characteristics, area characteristics, structural parameters, and type of the target substation; establishing a building information engineering model of the target substation based on the structural parameters and type of the target substation; and determining the scale data of the target substation based on the building information engineering model of the target substation.

[0070] In this embodiment of the invention, the drawings of the target substation are drawn in an easily identifiable format at the initial design stage. When identifying the drawings, the basic parameters such as the electrical characteristics, area characteristics, structural parameters, and type of the target substation can be easily identified. Then, based on the structural parameters and type of the target substation, and combined with existing Building Information Modeling (BIM) construction methods, a Building Information Engineering Model is established, transforming the two-dimensional model in the form of planar drawings into a visual three-dimensional digital model. This allows for the rapid and simple calculation of the scale data of the target substation, namely the engineering quantity and total cost.

[0071] The following implementation example illustrates the effectiveness of the DE-RF model proposed in this invention, but it is not intended to be limiting. In this implementation example, both the traditional RF model and the DE-RF model of this invention are used to perform engineering cost estimates for a substation.

[0072] Figure 4 This is a flowchart of a substation engineering cost estimate using a random forest model. (Example:) Figure 4 As shown, the traditional method divides the acquired data into a training sample set and a test sample set. Then, the RF model is trained based on the training sample set. The trained model is used to predict the estimated value of the substation project. The predicted value is then compared with the real value in the test sample set, so that the test sample set outputs the corresponding independent variables to the RF model, thus completing the model correction.

[0073] Figure 5 This is a flowchart of the substation engineering cost estimation process using the improved random forest model provided in this embodiment of the invention. Figure 5 As shown, after acquiring the data, this invention first initializes and normalizes the dataset, then divides it into a training set and a test set, and builds an RF model based on the training set. During the model building process, the model parameters of the RF model are continuously optimized through the DE algorithm until the optimal solution is reached, that is, the predicted value of the RF model is very close to the true value in the test set. At this point, the DE-RF model is considered to have been built. The model is then used to calculate the estimated value of the target substation and then reverse-normalized to obtain the final estimated result.

[0074] After performing engineering estimates on the target substation using both the traditional RF model and the DE-RF model of this invention, the following results were obtained: Figure 6-7 The preliminary calculation results are shown. Figure 6 This is a comparison curve between the preliminary calculation results obtained from the traditional random forest model and the improved random forest model of this invention. The horizontal axis represents the number of samples, and the vertical axis represents the investment cost. Figure 6 As shown, the DE-RF model of this invention provides predictions that are closer to the true values ​​than those of the traditional RF model. Figure 7 A comparison curve showing the average relative error between the traditional random forest model and the improved random forest model of this invention. The horizontal axis represents the number of samples, and the vertical axis represents the average relative error compared to the true value. Figure 7 As shown in the example, the average relative error of substation engineering cost estimation based on traditional RF is 2.24%, while the average relative error of DE-RF is 0.79%, indicating that DE-RF has better computational accuracy. This is because DE-RF uses DE to optimize the RF feature parameters and decision tree, making the algorithm more suitable for the application scenario of substation engineering cost estimation and thus achieving higher accuracy.

[0075] In summary, the beneficial effects of the present invention are as follows:

[0076] 1. By using a random forest model that incorporates differential evolution algorithm to estimate the project cost of the target substation, the planning scheme for the target substation can be determined more simply and quickly compared to the traditional manual planning method.

[0077] 2. By iterating continuously through the differential evolution algorithm, the optimal number of random forest splits and decision trees is finally obtained, thereby making the preliminary calculation results calculated by the improved random forest model more accurate.

[0078] It should be understood that the sequence number of each step in the above embodiments 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.

[0079] Figure 8 This is a structural schematic diagram of the substation planning device provided in an embodiment of the present invention. Figure 8 As shown, in some embodiments, the substation planning device 8 includes:

[0080] The acquisition module 810 is used to acquire the electrical characteristics, area characteristics, and scale data of the target substation.

[0081] The calculation module 820 is used to input electrical characteristics, area characteristics, and scale data into the improved random forest model to obtain the preliminary calculation results of the target substation; wherein, the number of random forest splits and the number of decision trees in the improved random forest model are determined according to the differential evolution algorithm.

[0082] The determination module 830 is used to determine the planning scheme of the target substation based on the preliminary calculation results and preset planning standards.

[0083] Optionally, the expression for the Gini index of the improved random forest model is:

[0084]

[0085]

[0086] Among them, G D，A Let G be the Gini index, D be the dataset input to the improved random forest model, D1 be the first subset of the dataset, D2 be the second subset of the dataset, and G be the Gini index. Dj (D j Let be the j-th regression tree, where j = 1 or 2, m is the total number of data categories in the j-th subset, and p i Let be the frequency of occurrence of the i-th type of data.

[0087] Optionally, the substation planning device 8 also includes a model building module, which is used to obtain historical engineering data corresponding to the target substation; determine the number of random forest splits and the number of decision trees based on the historical engineering data and the differential evolution algorithm; and establish an improved random forest model based on the number of random forest splits and the number of decision trees.

[0088] Optionally, a model building module is used to randomly sample historical engineering data according to a guided aggregation algorithm to obtain the dataset corresponding to each decision tree.

[0089] Optionally, the fitness function of the improved random forest model can be:

[0090]

[0091] Among them, E i For fitness, y(k) is the historical estimate obtained based on the kth historical project data, s(k) is the actual value corresponding to the kth historical project data, and M is the total number of historical project data.

[0092] Optionally, the differential evolution algorithm can be configured with a random operator, a crossover operator, and a selection operator.

[0093] Optionally, based on the preliminary budget results and preset planning standards of the target substation, a planning scheme for the target substation is determined, including: determining the optimizability level of the target substation based on the preliminary budget results and preset planning standards; and determining the optimization scheme for the target substation based on the optimizability level and the optimization priority of each item in the target substation.

[0094] Optionally, module 810 is used to acquire drawings of the target substation; identify the drawings of the target substation to obtain the electrical characteristics, area characteristics, structural parameters and type of the target substation; establish a building information engineering model of the target substation based on the structural parameters and type of the target substation; and determine the scale data of the target substation based on the building information engineering model of the target substation.

[0095] The substation planning device provided in this embodiment can be used to execute the above method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0096] Figure 9 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. For example... Figure 9 As shown, an embodiment of the present invention provides an electronic device 9, which includes a processor 90, a memory 91, and a computer program 92 stored in the memory 91 and executable on the processor 90. When the processor 90 executes the computer program 92, it implements the steps described in the various substation planning method embodiments above, for example... Figure 1 Steps 210 to 230 are shown. Alternatively, when processor 90 executes computer program 92, it implements the functions of each module / unit in the above system embodiments, for example... Figure 8 The functions of modules 810 to 830 are shown.

[0097] For example, computer program 92 can be divided into one or more modules / units, one or more of which are stored in memory 91 and executed by processor 90 to complete the present invention. One or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 92 in electronic device 9.

[0098] Electronic device 9 can be a terminal or a server. The terminal can be a mobile phone, MCU, ECU, etc., without limitation. The server can be a physical server, cloud server, etc., without limitation. Electronic device 9 may include, but is not limited to, processor 90 and memory 91. Those skilled in the art will understand that... Figure 9This is merely an example of electronic device 9 and does not constitute a limitation on electronic device 9. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device may also include input / output devices, network access devices, buses, etc.

[0099] The processor 90 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0100] The memory 91 can be an internal storage unit of the electronic device 9, such as a hard disk or RAM. The memory 91 can also be an external storage device of the electronic device 9, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 91 can include both internal and external storage units of the electronic device 9. The memory 91 is used to store computer programs and other programs and data required by the electronic device. The memory 91 can also be used to temporarily store data that has been output or will be output.

[0101] This invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps described in the above-described substation planning method embodiment.

[0102] A computer-readable storage medium stores a computer program 92. The computer program 92 includes program instructions. When executed by the processor 90, the program instructions implement all or part of the processes in the methods described in the above embodiments. The computer program 92 can also instruct related hardware to complete the process. The computer program 92 can be stored in a computer-readable storage medium. When executed by the processor 90, the computer program 92 can implement the steps of the various method embodiments described above. The computer program 92 includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0103] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0104] It should be understood that the sequence number of each step in the above embodiments 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.

[0105] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0106] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0107] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0108] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / device and method can be implemented in other ways. For example, the apparatus / device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0109] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0110] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0111] If an integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0112] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A substation planning method, characterized by, include: Obtain the electrical characteristics, area characteristics, and scale data of the target substation; The electrical characteristics, area characteristics, and scale data are input into the improved random forest model to obtain the preliminary calculation results of the target substation; wherein, the number of random forest splits and the number of decision trees in the improved random forest model are determined according to the differential evolution algorithm; Based on the preliminary cost estimate and pre-set planning standards for the target substation, the planning scheme for the target substation is determined. Before inputting the electrical characteristics, area characteristics, and scale data into the improved random forest model to obtain the preliminary calculation results of the target substation, the method further includes: Obtain the historical engineering data corresponding to the target substation; The number of random forest splits and the number of decision trees are determined based on the historical engineering data and differential evolution algorithm. An improved random forest model is established based on the number of random forest splits and the number of decision trees.

2. The substation planning method according to claim 1, characterized in that, The expression for the Gini index of the improved random forest model is as follows: in, G D，A The Gini index is mentioned. D For the dataset input into the improved random forest model, D 1 represents the first subset of the dataset. D 2 is the second subset of the dataset. G Dj ( D j Let be the j-th regression tree, where j = 1 or 2. m For the first j The total number of data categories in each subset p i Let be the frequency of occurrence of the i-th type of data.

3. The substation planning method according to claim 1, characterized in that, After determining the number of random forest splits and the number of decision trees based on the historical engineering data and the differential evolution algorithm, the method further includes: The historical engineering data is randomly sampled using a guided aggregation algorithm to obtain the dataset corresponding to each decision tree.

4. The substation planning method according to claim 1, characterized in that, The fitness function of the improved random forest model is: in, E i Let y(k) be the fitness, and y(k) be the fitness value according to the first... k Historical estimates obtained from historical engineering data s ( k ) is the first k The actual value corresponding to each historical engineering data point, where M is the total number of historical engineering data points.

5. The substation planning method according to claim 1, characterized in that, The differential evolution algorithm includes a random operator, a crossover operator, and a selection operator.

6. The substation planning method according to claim 1, characterized in that, The step of determining the planning scheme for the target substation based on the preliminary cost estimate and pre-set planning standards includes: Based on the preliminary calculation results and the preset planning standards, the optimizability level of the target substation is determined; Based on the optimizability level and the optimization priority of each item in the target substation, the optimization scheme for the target substation is determined.

7. The substation planning method according to any one of claims 1-6, characterized in that, The acquisition of the electrical characteristics, area characteristics, and scale data of the target substation includes: Obtain the blueprints for the target substation; The drawings of the target substation are identified to obtain its electrical characteristics, area characteristics, structural parameters, and type. Based on the structural parameters and type of the target substation, a building information engineering model of the target substation is established; Based on the building information engineering model of the target substation, the scale data of the target substation is determined.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the substation planning method as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the substation planning method as described in any one of claims 1 to 7.

Images