Distribution transformer simulation gear shifting method and system based on machine learning and medium
Through the machine learning-based distribution simulation transfer method, the uncertainty problem caused by the dependence of manual experience on distribution transfer transfer in the existing technology is solved, and the pre-evaluation and optimization of the transfer results are achieved, and the quality and reliability of the power supply of the power grid are improved.
Patent Information
- Application Number
- CN202411569658.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-05
- Publication Date
- 2025-03-25
AI Technical Summary
The existing distribution and configuration adjustment solutions rely on manual experience, resulting in high uncertainty and the pre-evaluation of adjustment results cannot be achieved, affecting the quality and reliability of power supply in the power grid.
The matching simulation metering method based on machine learning is adopted, and the pre-evaluation and optimization of the metering effect is achieved through steps such as data collection, preliminary metering scheme formation, result simulation, and voltage pass rate calculation.
The pre-evaluation of the performance of the gear adjustment is achieved, which reduces the uncertainty of manual operation, improves the quality and reliability of the power supply of the power grid, and ensures the effectiveness of the gear adjustment operation and the safe and stable operation of the power grid.
Smart Images
Figure CN119692159A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of electric power grid technology, and in particular to a distribution transformer simulation gear adjustment method, system and medium based on machine learning. Background Art
[0002] Carrying out precise adjustment of distribution transformers can not only ensure that the voltage at the user end is stable within the specified range, improve the voltage quality, and meet the user's requirements for power quality, but also reduce unnecessary power loss, optimize the operation status of the power grid, and improve the operation efficiency of the power grid. At present, the adjustment plan of distribution transformers mainly relies on manual analysis of the voltage quality in the area based on multi-dimensional data such as bus side voltage, user side voltage, power factor, etc., and the adjustment work of distribution transformers is carried out after the adjustment demand is clarified.
[0003] At present, manual distribution transformer adjustment relies heavily on the experience of operators. The operations of different operators may lead to different results, which increases uncertainty. At the same time, the existing distribution transformer adjustment scheme cannot pre-evaluate the adjustment effect, which may lead to inaccurate adjustment results and affect the power supply quality and reliability of the power grid. Summary of the invention
[0004] The purpose of the embodiments of the present application is to provide a distribution transformer simulation gear adjustment method, system and medium based on machine learning, which can carry out distribution transformer and user voltage measurement after distribution transformer gear adjustment according to the machine learning algorithm and distribution transformer gear type, and realize preliminary evaluation of gear adjustment effect. Grassroots personnel can perform on-site voltage adjustment measurement according to the gear adjustment suggestions, complete "calculation before adjustment", and avoid blind gear adjustment.
[0005] To achieve the above objectives, this application provides the following technical solutions:
[0006] In a first aspect, an embodiment of the present application provides a distribution transformer simulation gear adjustment method based on machine learning, comprising the following steps:
[0007] Data collection: collect all data on users’ voltage quality not meeting the standards and classify and count them according to whether the voltage is above the upper limit or below the lower limit;
[0008] Form a preliminary distribution transformer adjustment plan, determine the distribution transformers that need to be adjusted and the distribution transformer adjustment form according to the classification of the collected data, and form a preliminary adjustment plan;
[0009] Conduct preliminary simulation on the effectiveness of the distribution transformer adjustment scheme, build and train a simulation model for the effectiveness of the distribution transformer adjustment scheme, and use the trained model to automatically output the voltage data of all users carried by the distribution transformer after the adjustment;
[0010] Calculate the voltage qualification rate and construct evaluation indicators to determine the feasibility of the current gear adjustment plan;
[0011] Output the current file transfer plan.
[0012] The specific method of collecting all the data of the voltage quality not meeting the standard of users and classifying and counting them according to the voltage exceeding the upper limit and the voltage exceeding the lower limit is as follows:
[0013]
[0014]
[0015] In the above formulas (1)-(2), YHC u Indicates that the voltage exceeds the upper limit user statistics, YHC d Indicates the voltage exceeds the lower limit of the distribution transformer statistics;
[0016] Count the total number of users served by the same distribution transformer and the number of users with voltage exceeding the limit, and classify and count according to the voltage exceeding the upper limit and the voltage exceeding the lower limit, and locate the distribution transformer that needs to be adjusted.
[0017]
[0018]
[0019] PBC′={PBC 1 ′,PBC 2 ′,...,PBC i ′} (5)
[0020] In the above formula (3), PBC 1 Represents a single distribution transformer, It means that the voltage of the users exceeds the upper limit and the number of users is large and needs to be adjusted. Indicates that the number of users whose voltage exceeds the lower limit is large and needs to be adjusted. 1 Indicates the number of users under this distribution transformer, YHUN 1 Indicates the number of users whose voltage exceeds the upper limit of the distribution transformer, YHDN 1 represents the number of users whose voltage exceeds the lower limit of the distribution transformer, γ is a custom parameter ranging from 0 to 1; in the above formula (5), PBC′ represents the set of distribution transformers that need to be adjusted,
[0021] Collect all the historical 96-point voltage, current, and power factor data of the low-voltage side of the distribution transformer that needs to be adjusted for one month, and the historical 96-point voltage, current, and power factor data of the users served by the distribution transformer,
[0022] PBCU 1 ′={PBCU 1(1,1) ′,PBCU 1(1,2) ′,...,PBCU 1(30,96) ′} (6)
[0023] PBCI 1 ′={PBCI 1(1,1) ′,PBCI1(1,2) ′,...,PBCI 1(30,96) ′} (7)
[0024] PBCG 1 ′={PBCG 1(1,1) ′,PBCG 1(1,2) ′,...,PBCG 1(30,96) ′} (8)
[0025] YHCU 1 ′={YHCU 1(1,1) ′,YHCU 1(1,2) ′,...,YHCU 1(30,96) ′} (9)
[0026] YHCU′={YHCU 1 ′,YHCU 2 ′,...,YHCU x ′} (10)
[0027] In the above formulas (6)-(10), PBCU 1 ′ represents the 96-point voltage data of the low-voltage side of a single distribution transformer that needs to be adjusted for one month, a total of 96*30=2880 items; PBCI 1 ′ represents the 96-point current data of the low-voltage side of a single distribution transformer that needs to be adjusted for one month, a total of 96*30=2880 items; PBCG 1 ' represents the 96-point power factor data of the low-voltage side of a single distribution transformer that needs to be adjusted for one month, a total of 96*30=2880 items; YHCU 1 ′ represents the 96-point voltage data of a single voltage-limit-exceeding user for one month, totaling 96*30=2880 items; YHCU′ represents PBCU 1 'It contains 96 points of voltage data for all users in one month.
[0028] The voltage qualification rate calculation and the construction of evaluation indicators to determine the feasibility of the current gear adjustment plan are specifically as follows:
[0029] Assuming that the number of users with voltage exceeding the limit before the distribution transformer is adjusted is M, and the number after the adjustment is M', the evaluation index β is constructed to determine the feasibility of the current adjustment plan.
[0030]
[0031] In the above formula (11), FAKX=1 indicates that the current gear shifting scheme is feasible, and the process directly jumps to step 5; FAKX=0 indicates that the current gear shifting scheme is not feasible, and the gear shifting scheme is replaced and the preliminary gear shifting scheme effectiveness simulation steps are repeated.
[0032] In a second aspect, an embodiment of the present application provides a distribution transformer simulation gear adjustment system based on machine learning, comprising:
[0033] The data collection module collects all the data of users’ voltage quality not meeting the standards and classifies and counts them according to the voltage exceeding the upper limit and the voltage exceeding the lower limit;
[0034] The module for forming a preliminary distribution transformer adjustment plan determines the distribution transformers that need to be adjusted and the adjustment form of the distribution transformers according to the classification of the collected data and forms a preliminary adjustment plan;
[0035] Initial distribution transformer adjustment scheme effectiveness simulation module, build distribution transformer adjustment scheme effectiveness simulation model and train it, and use the trained model to automatically output all user voltage data of the distribution transformer after adjustment;
[0036] The feasibility determination module is used to calculate the voltage qualification rate and construct evaluation indicators to determine the feasibility of the current gear adjustment plan;
[0037] The file adjustment plan output module is used to output the current file adjustment plan.
[0038] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the distribution transformer simulation gear adjustment method based on machine learning as described above are implemented.
[0039] Compared with the prior art, the present invention has the following beneficial effects:
[0040] This proposal uses machine learning algorithms to complete the calculation of voltage qualification rate and over-limit conditions after voltage regulation, and realizes preliminary evaluation of the effectiveness of voltage regulation.
[0041] It can realize the “calculate first, then adjust” of the distribution transformer gear adjustment work, ensuring the effectiveness of the gear adjustment operation and the safe and stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0043] Figure 1 It is a flow chart of the method of the present invention.
[0044] Figure 2 It is a system block diagram of the present invention. DETAILED DESCRIPTION
[0045] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.
[0046] The terms "comprises," "comprising," or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.
[0047] The terms "first", "second", etc. are only used to distinguish one entity or operation from another entity or operation, and should not be understood as indicating or implying relative importance, nor should they be understood as requiring or implying any such actual relationship or order between these entities or operations.
[0048] like Figure 1 A distribution transformer simulation shifting method based on machine learning is shown, comprising the following steps:
[0049] The specific process is as follows:
[0050] 1. Data Collection
[0051] (1) Collect all data on users’ voltage quality that does not meet the standards and classify and count them according to whether the voltage exceeds the upper limit or the lower limit.
[0052]
[0053]
[0054] In the above formulas (1)-(2), YHC u Indicates that the voltage exceeds the upper limit user statistics, YHC d Indicates the voltage exceeds the lower limit of the distribution transformer statistics.
[0055] Count the total number of users served by the same distribution transformer and the number of users with voltage exceeding the limit, classify and count according to the voltage exceeding the upper limit and the voltage exceeding the lower limit, and locate the distribution transformer that needs to be adjusted.
[0056]
[0057]
[0058] PBC′={PBC 1 ′,PBC2 ′,...,PBC i ′} (5)
[0059] In the above formula (3), PBC 1 Represents a single distribution transformer, It means that the voltage of the users exceeds the upper limit and the number of users is large and needs to be adjusted. Indicates that the number of users whose voltage exceeds the lower limit is large and needs to be adjusted. 1 Indicates the number of users under this distribution transformer, YHUN 1 Indicates the number of users whose voltage exceeds the upper limit of the distribution transformer, YHDN 1 represents the number of users whose voltage exceeds the lower limit of the distribution transformer, γ is a custom parameter ranging from 0 to 1; in the above formula (5), PBC′ represents the set of distribution transformers that need to be adjusted.
[0060] Collect 96 points of voltage, current, and power factor data for one month on the low-voltage side of all distribution transformers that need to be adjusted, as well as 96 points of voltage, current, and power factor data for one month on the low-voltage side of all distribution transformers that need to be adjusted.
[0061] PBCU 1 ′={PBCU 1(1,1) ′,PBCU 1(1,2) ′,...,PBCU 1(30,96) ′} (6)
[0062] PBCI 1 ′={PBCI 1(1,1) ′,PBCI 1(1,2) ′,...,PBCI 1(30,96) ′} (7)
[0063] PBCG 1 ′={PBCG 1(1,1) ′,PBCG 1(1,2) ′,...,PBCG 1(30,96) ′} (8)
[0064] YHCU 1 ′={YHCU 1(1,1) ′,YHCU 1(1,2) ′,...,YHCU 1(30,96) ′} (9)
[0065] YHCU′={YHCU 1 ′,YHCU 2 ′,...,YHCU x ′} (10)
[0066] In the above formulas (6)-(10), PBCU 1′ represents the 96-point voltage data of the low-voltage side of a single distribution transformer that needs to be adjusted for one month, a total of 96*30=2880 items; PBCI 1 ′ represents the 96-point current data of the low-voltage side of a single distribution transformer that needs to be adjusted for one month, a total of 96*30=2880 items; PBCG 1 ' represents the 96-point power factor data of the low-voltage side of a single distribution transformer that needs to be adjusted for one month, a total of 96*30=2880 items; YHCU 1 ′ represents the 96-point voltage data of a single voltage-limit-exceeding user for one month, totaling 96*30=2880 items; YHCU′ represents PBCU 1 'It contains 96 points of voltage data for all users in one month.
[0067] 2. Form a preliminary transmission adjustment plan
[0068] Based on formula (5), the distribution transformer that needs to be adjusted is determined, and based on formula (3), the distribution transformer adjustment form is determined (increasing the voltage on the low-voltage side of the distribution transformer by adjusting the voltage or reducing the voltage on the low-voltage side of the distribution transformer) and a preliminary adjustment plan is formed.
[0069] 3. Preliminary simulation of the effectiveness of the transmission adjustment plan
[0070] (1) Model establishment
[0071] Assume that a single PBC needs to be adjusted 1 ′The number of users is X, combined with the random forest algorithm, based on PBCI 1 ′、PBCG 1 'Establish feature engineering and convert PBCU 1 ′ is regarded as the input of the model, and YHCU′ is regarded as the output of the model to construct a one-dimensional input and X-dimensional output distribution transformer adjustment scheme effectiveness simulation model.
[0072] Model Training
[0073] Conduct model training and explore PBCU 1 The corresponding relationship between ′ and YHCU′
[0074] Simulation of the effectiveness of the transmission gear adjustment plan
[0075] Using the trained model, the voltage on the low-voltage side of the distribution transformer after the preliminary distribution transformer adjustment plan is implemented is input. The voltage of a five-speed transformer is changed by 2.5% per gear (or a three-speed transformer is changed by 5%). The model automatically outputs the voltage data of all users carried by the distribution transformer after the adjustment.
[0076] 4. Calculation of voltage qualification rate
[0077] Assuming that the number of users with voltage exceeding the limit before the distribution transformer is adjusted is M, and the number after the adjustment is M', the evaluation index β is constructed to determine the feasibility of the current adjustment plan.
[0078]
[0079] In the above formula (11), FAKX=1 indicates that the current shifting scheme is feasible, and the process directly jumps to step 5; FAKX=0 indicates that the current shifting scheme is not feasible, and the process changes the shifting scheme and repeats step 3.
[0080] 5. Output file adjustment plan
[0081] Output the current file transfer plan.
[0082] 6. Example Analysis
[0083] Taking the distribution network in a certain area of Hubei Province as an example, the distribution network contains 29,687 distribution transformers that need to be adjusted, affecting 1,577,190 users. Combined with the random Senli algorithm in the present invention, the simulation analysis of the preliminary adjustment plan is completed, and the distribution transformer adjustment is carried out using the simulation results. The distribution transformer adjustment plan is adjusted according to the simulation results to achieve the improvement of the voltage quality of the distribution network in the target area. The key indicators of the area before and after the transformation are shown in Table 1:
[0084] Table 1 Statistics of key indicators before and after the transformation of distribution transformers in a certain area of Hubei Province
[0085] Distribution transformer overload rate (%) Distribution transformer light no-load rate (%) Voltage qualification rate (%) Before renovation 61.22 2.75 93.74 After the transformation of traditional solution 56.75 2.05 95.07 After the scheme of the present invention is transformed 48.46 1.43 97.23
[0086] It can be seen from the contents in Table 1 that, compared with the traditional distribution transformer shifting scheme, after the shifting scheme of the present invention is applied, the heavy overload rate, light no-load rate and voltage qualification rate of the distribution transformer are greatly reduced, which has better shifting effect and can effectively guide the development of the distribution transformer shifting work.
[0087] The embodiment of the present application provides a distribution transformer simulation gear adjustment system based on machine learning, comprising:
[0088] Data collection module 1 collects all data of users’ voltage quality not meeting the standards and classifies and counts them according to whether the voltage exceeds the upper limit or the lower limit;
[0089] A preliminary distribution transformer adjustment plan forming module 2 determines the distribution transformer to be adjusted and the distribution transformer adjustment form according to the classification of the collected data and forms a preliminary adjustment plan;
[0090] The preliminary distribution transformer adjustment scheme effectiveness simulation module 3 builds and trains the distribution transformer adjustment scheme effectiveness simulation model, and uses the trained model to automatically output the voltage data of all users carried by the distribution transformer after the adjustment;
[0091] The feasibility determination module 4 is used to calculate the voltage qualification rate and construct evaluation indicators to determine the feasibility of the current gear adjustment plan;
[0092] The file adjustment plan output module 5 is used to output the current file adjustment plan.
[0093] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the distribution transformer simulation gear adjustment method based on machine learning as described above are implemented.
[0094] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0095] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0096] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0098] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0099] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0100] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0101] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims
1. A distribution transformer simulation shifting method based on machine learning, characterized in that: The steps include: Data collection: collect all data on users’ voltage quality not meeting the standards and classify and count them according to whether the voltage is above the upper limit or below the lower limit; Form a preliminary distribution transformer adjustment plan, determine the distribution transformers that need to be adjusted and the distribution transformer adjustment form according to the classification of the collected data, and form a preliminary adjustment plan; Conduct preliminary simulation on the effectiveness of the distribution transformer adjustment scheme, build and train a simulation model for the effectiveness of the distribution transformer adjustment scheme, and use the trained model to automatically output the voltage data of all users carried by the distribution transformer after the adjustment; Calculate the voltage qualification rate and construct evaluation indicators to determine the feasibility of the current gear adjustment plan; Output the current file transfer plan.
2. A distribution transformer simulation shifting method based on machine learning as claimed in claim 1, characterized in that: The specific method of collecting all the data of the voltage quality not meeting the standard of users and classifying and counting them according to the voltage exceeding the upper limit and the voltage exceeding the lower limit is as follows: In the above formulas (1)-(2), YHC u Indicates that the voltage exceeds the upper limit user statistics, YHC d Indicates the voltage exceeds the lower limit of the distribution transformer statistics; Count the total number of users served by the same distribution transformer and the number of users with voltage exceeding the limit, and classify and count according to the voltage exceeding the upper limit and the voltage exceeding the lower limit, and locate the distribution transformer that needs to be adjusted. PBC′={PBC1′,PBC2′,...,PBC i ′} (5) In the above formula (3), PBC1 represents a single distribution transformer, It means that the voltage of the users exceeds the upper limit and the number of users is large and needs to be adjusted. Indicates that the number of users whose voltage is lower than the lower limit is large and needs to be adjusted, YHN1 indicates the number of users under the distribution transformer, YHUN1 indicates the number of users whose voltage is higher than the upper limit under the distribution transformer, YHDN1 indicates the number of users whose voltage is lower than the lower limit under the distribution transformer, γ is a custom parameter ranging from 0 to 1; in the above formula (5), PBC′ indicates the set of distribution transformers that need to be adjusted, Collect all the historical 96-point voltage, current, and power factor data of the low-voltage side of the distribution transformer that needs to be adjusted for one month, and the historical 96-point voltage, current, and power factor data of the users served by the distribution transformer, PBCU1′={PBCU 1(1,1) ′,PBCU 1(1,2) ′,...,PBCU 1(30,96) ′} (6) PBCI1′={PBCI 1(1,1) ′,PBCI 1(1,2) ′,...,PBCI 1(30,96) ′} (7) PBCG1′={PBCG 1(1,1) ′,PBCG 1(1,2) ′,...,PBCG 1(30,96) ′} (8) YHCU1′={YHCU 1(1,1) ′,YHCU 1(1,2) ′,...,YHCU 1(30,96) ′} (9) YHCU′={YHCU1′,YHCU2′,...,YHCU x ′} (10) In the above formulas (6)-(10), PBCU1′ represents 96 points of historical voltage data of the low-voltage side of a single distribution transformer that needs to be adjusted for one month, totaling 96*30=2880 items; PBCI1′ represents 96 points of historical current data of the low-voltage side of a single distribution transformer that needs to be adjusted for one month, totaling 96*30=2880 items; PBCG1′ represents 96 points of historical power factor data of the low-voltage side of a single distribution transformer that needs to be adjusted for one month, totaling 96*30=2880 items; YHCU1′ represents 96 points of historical voltage data of a single voltage-over-limit user for one month, totaling 96*30=2880 items; YHCU′ represents 96 points of historical voltage data of all users served by PBCU1′ for one month.
3. The method for simulated gear shifting of a distribution transformer based on machine learning as claimed in claim 1, characterized in that: The voltage qualification rate calculation and the construction of evaluation indicators to determine the feasibility of the current gear adjustment plan are specifically as follows: Assuming that the number of users with voltage exceeding the limit before the distribution transformer is adjusted is M, and the number after the adjustment is M', the evaluation index β is constructed to determine the feasibility of the current adjustment plan. In the above formula (11), FAKX=1 indicates that the current gear shifting scheme is feasible, and the process directly jumps to step 5; FAKX=0 indicates that the current gear shifting scheme is not feasible, and the gear shifting scheme is replaced and the preliminary gear shifting scheme effectiveness simulation steps are repeated.
4. A distribution transformer simulation gear adjustment system based on machine learning, characterized in that: include, The data collection module collects all the data of users’ voltage quality not meeting the standards and classifies and counts them according to the voltage exceeding the upper limit and the voltage exceeding the lower limit; The module for forming a preliminary distribution transformer adjustment plan determines the distribution transformers that need to be adjusted and the adjustment form of the distribution transformers according to the classification of the collected data and forms a preliminary adjustment plan; Initial distribution transformer adjustment scheme effectiveness simulation module, build distribution transformer adjustment scheme effectiveness simulation model and train it, and use the trained model to automatically output all user voltage data of the distribution transformer after adjustment; The feasibility determination module is used to calculate the voltage qualification rate and construct evaluation indicators to determine the feasibility of the current gear adjustment plan; The file adjustment plan output module is used to output the current file adjustment plan.
5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the distribution transformer simulation gear adjustment method based on machine learning are implemented as described in any one of claims 1-3.