Transformer parallel operation optimization control method and system

Abstract

The invention discloses a transformer parallel operation optimization control method and system, and relates to the technical field of power equipment control, and the method comprises the steps: obtaining the operation parameters of parallel operation transformers; constructing a multi-objective optimization function based on the operation parameters, wherein the multi-objective optimization function comprises a transformer total loss objective, a voltage deviation objective and a life loss objective; dynamically adjusting the weight coefficient of each objective function through a weight adaptive model, and generating a weighted objective function; and solving an optimal solution of the weighted objective function, and outputting a transformer gear adjustment instruction. According to the method, the multi-dimensional objective function of the total loss, the voltage deviation and the life loss is constructed, and the weight adaptive model is introduced, so that the weight can be dynamically adjusted according to the real-time influence factors, the power grid load fluctuation and the operation environment change can be flexibly coped with, the optimal solution for balancing each objective can be found under different working conditions, and the method is suitable for large-scale popularization and application. And timely and accurate adjustment of the gear instruction of the transformer is realized.

Description

Technical Field

[0001] This invention relates to the field of power equipment control technology, and in particular to an optimized control method and system for parallel operation of transformers. Background Technology

[0002] With the advancement of the "dual carbon" target, the random access of a large number of distributed power sources and electric vehicle loads in the power distribution network has caused transformers to operate under wide-range and fluctuating parallel conditions for a long time.

[0003] Traditional manual periodic tap adjustment or single-objective energy-saving strategies are no longer sufficient to balance losses, voltage quality, and equipment lifespan, resulting in low grid operating efficiency and accelerated asset aging. Although multi-objective control optimization models have been introduced, the target weight coefficients used in these models rely on human experience and cannot adaptively adjust to sudden load changes or ambient temperature variations. This leads to delayed or over-adjusted transformer tap positions, which in turn increases voltage deviation. Summary of the Invention

[0004] To address the problem in existing multi-objective control optimization models where the target weights cannot be adaptively adjusted, leading to delayed or over-adjusted transformer tap position commands, this invention provides a method and system for optimizing the parallel operation of transformers. By introducing a weighted adaptive model, the target weights can be dynamically adjusted based on real-time image factors, achieving timely and accurate adjustment of transformer tap position commands. The specific technical solution is as follows: In a first aspect, the present invention provides an optimized control method for parallel operation of transformers, comprising: Obtain the operating parameters of transformers operating in parallel; A multi-objective optimization function is constructed based on the operating parameters. The multi-objective optimization function includes the transformer total loss target, voltage deviation target, and lifetime loss target. The weight coefficients of each objective function are dynamically adjusted through a weighted adaptive model to generate a weighted objective function. Solve for the optimal solution of the weighted objective function and output the transformer tap adjustment command.

[0005] Preferably, the multi-objective optimization function is expressed as: In the formula, Represent the objective function for total loss; Indicates the voltage deviation target; Represent the objective function for lifetime loss; , and These are the weight coefficients for the corresponding objectives, and ; The objective function for total loss is expressed as: In the formula, Indicates the first Copper loss of the transformer; Indicates the first Iron loss of a transformer; The voltage deviation objective function is expressed as: In the formula, Indicates the actual voltage of the busbar; Indicates the reference voltage; The objective function for lifetime loss is expressed as: In the formula, Indicates the first Health status index of the transformer.

[0006] Preferably, the step of dynamically adjusting the weight coefficients of each objective function through a weighted adaptive model includes: By calculating the target conflict factor in real time , is represented as: In the formula, and These represent the changes in the total loss target and the voltage deviation target, respectively; When the calculated target conflict factor is greater than a preset threshold, the weights are reallocated, as follows: In the formula, , and These represent the weight coefficients of the corresponding targets after redistribution; Adjust the gain to compensate for conflicts.

[0007] Preferably, the process further includes solving the weighted objective function before: An LSTM prediction model is trained based on historical load data, and the load prediction results are output. The load prediction results are then used as boundary conditions and combined with the weighted objective function to solve the problem.

[0008] Preferably, the step of using the load forecast result as a boundary condition and solving it in conjunction with the weighted objective function includes: Based on the prediction results, the predicted load mutation rate is calculated. When the predicted load mutation rate is greater than the preset mutation threshold, a forced adjustment strategy for the weight coefficient of the corresponding target is implemented.

[0009] Preferably, after the output transformer tap adjustment command, the method further includes: Calculate the tap difference between adjacent transformers. If the tap difference is greater than a preset tap threshold, insert a transition tap sequence based on a preset switching time interval.

[0010] Preferably, the insertion of the transition gear sequence based on a preset switching time interval further includes: Monitor the rate of change of transformer oil temperature and calculate the oil temperature derivative, and implement a graded backoff strategy based on the oil temperature derivative.

[0011] Secondly, the present invention also provides an optimized control system for parallel operation of transformers, which applies the aforementioned method and includes: The data acquisition unit is used to acquire the operating parameters of transformers operating in parallel. The function construction unit is used to construct a multi-objective optimization function based on the operating parameters. The multi-objective optimization function includes the transformer total loss target, voltage deviation target, and lifetime loss target. The function adjustment unit is used to dynamically adjust the weight coefficients of each objective function through a weighted adaptive model to generate a weighted objective function. The function solving unit is used to solve the optimal solution of the weighted objective function and output the transformer tap adjustment command.

[0012] Thirdly, the present invention also provides a computer-readable storage medium comprising a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to execute the aforementioned transformer parallel operation optimization control method.

[0013] Fourthly, the present invention also provides a processor for running a program, wherein the program executes the aforementioned transformer parallel operation optimization control method during operation.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention constructs a multi-dimensional objective function encompassing total loss, voltage deviation, and lifetime loss, and introduces a weighted adaptive model. This model dynamically adjusts the weights based on real-time influencing factors, flexibly responding to power grid load fluctuations and changes in the operating environment. It can find the optimal solution balancing the various objectives under different operating conditions, enabling timely and accurate adjustment of transformer tap positions. Simultaneously, by predicting load using an LSTM model and applying the results as boundary conditions, it proactively addresses load changes and reduces real-time adjustment lag. Attached Figure Description

[0015] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0016] Figure 1 This is a flowchart of an optimized control method for parallel operation of transformers according to the present invention.

[0017] Figure 2 This is a flowchart of an embodiment of the transformer parallel operation optimization control method of the present invention.

[0018] Figure 3 This is a flowchart of another embodiment of the transformer parallel operation optimization control method of the present invention.

[0019] Figure 4 This is a schematic diagram of a transformer parallel operation optimization control system according to the present invention. Detailed Implementation

[0020] 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, not all, of the embodiments of the present invention. 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.

[0021] It should be understood that, when used in this specification, the terms “comprising” and “including” indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0022] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0023] It should also be further understood that the term "and / or" as used in this specification refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes such combinations.

[0024] Please refer to the following examples. Figures 1 to 4 .

[0025] Please see Figure 1This application provides an optimized control method for parallel operation of transformers, comprising: Step S1: Obtain the operating parameters of the transformers operating in parallel; The operating parameters include load factor, temperature, short-circuit impedance, and grid-side voltage / current. Load factor and temperature are calculated directly or indirectly through sensors built into the transformer, while voltage and current are collected collaboratively by the grid monitoring system. Data is acquired in real time using the transformer's built-in sensors and the grid monitoring system. The load factor can be calculated as the ratio of real-time load to rated capacity; temperature is obtained by monitoring winding and core temperatures using distributed fiber optic sensors; short-circuit impedance is periodically calibrated through offline testing combined with online impedance monitoring devices; grid-side voltage and current are synchronously collected by smart meters. All collected parameters are filtered and stored in a database for data retrieval.

[0026] Step S2: Construct a multi-objective optimization function based on the operating parameters. The multi-objective optimization function includes the transformer total loss target, voltage deviation target, and life loss target. Transformer total loss target The associated parameter is the load factor. Short-circuit impedance Grid-side current The objective function for total loss is expressed as: In the formula, Indicates the first The copper loss of a transformer, also known as load loss, is related to the square of the load factor, short-circuit impedance, and current. Indicates the first The iron loss of a transformer, also known as no-load loss, is determined by the inherent characteristics of the transformer and is independent of the load; it can be considered a constant. This refers to the number of transformers operating in parallel.

[0027] Copper loss The calculation formula is: In the formula, Let be the equivalent resistance of the i-th transformer (calculated from the short-circuit impedance). for .

[0028] Voltage deviation target The relevant parameters include grid-side voltage, transformer tap position, load current, short-circuit impedance, and voltage regulation rate. The voltage deviation objective function is expressed as: In the formula, This represents the actual voltage of the busbar of the i-th transformer; Indicates the reference voltage; The formula for calculating the actual voltage of the busbar is: In the formula, This represents the voltage regulation rate of the i-th transformer; Lifetime loss target The objective function for determining the lifespan loss, which is related to the temperature load rate, is expressed as follows: In the formula, Indicates the first Health status index of the transformer.

[0029] The formula for calculating the State of Health (SOH) index is: Vibration correction item: This indicates the top oil temperature of the transformer; Indicates hot spot current; Indicates the rated current; Indicates the amplitude of winding vibration; Indicates the vibration threshold; These are the model coefficients.

[0030] Based on the transformer total loss target, voltage deviation target, and lifespan loss target, a multi-objective optimization function is constructed, expressed as: In the formula, Represent the objective function for total loss; Indicates the voltage deviation target; Represent the objective function for lifetime loss; , and These are the weight coefficients for the corresponding objectives, and ; A multi-objective optimization function was constructed, encompassing total loss, voltage deviation, and lifetime loss. The total loss objective focuses on operational economy, the voltage deviation objective ensures power supply quality, and the lifetime loss objective quantifies equipment health status by incorporating parameters such as temperature and vibration, achieving a synergistic consideration of economy, safety, and equipment lifespan. The construction of this multi-objective function makes the optimization direction more aligned with the actual needs of parallel transformer operation.

[0031] Step S3: Dynamically adjust the weight coefficients of each objective function using a weighted adaptive model to generate a weighted objective function; The weighted adaptive model includes performing the following steps to adjust the weights: By calculating the target conflict factor in real time , is represented as: In the formula, and These represent the changes in the total loss target and the voltage deviation target, respectively, and are obtained by calculating the changes at the previous and next time points. When the calculated target conflict factor is greater than a preset threshold, the weights are reallocated, as follows: In the formula, , and These represent the weight coefficients of the corresponding targets after redistribution; Adjust the gain to compensate for conflicts.

[0032] By adding a target conflict factor and dynamically redistributing target weights, the multi-objective game problem is solved. The degree of conflict between targets is judged based on the target conflict factor, and weights are redistributed when conflict intensifies, avoiding optimization imbalances or oscillations under fixed weights. The dynamic adjustment mechanism enhances the transformer's adaptability to complex operating conditions, ensuring that critical performance is prioritized when targets such as loss and voltage stability conflict.

[0033] Step S4: Solve for the optimal solution of the weighted objective function and output the transformer tap adjustment command.

[0034] The optimization variable is the transformer tap position (i.e., the turns ratio). The constraints include: (1) Gear adjustment range ; (2) Load balancing ; Solve using a genetic algorithm Output the optimal gear adjustment command A genetic algorithm is used to solve the weighted objective function. Constraints on gear adjustment and load are set. The gear combination corresponding to the minimum objective function value is obtained through iterative calculation. A digital adjustment command is generated and sent to the transformer tap changer actuator after verification.

[0035] By using transformer tap position as the optimization variable and combining LSTM load forecasting results as boundary constraints, a genetic algorithm is used to solve for the optimal solution and output adjustment commands. The introduction of load forecasting proactively addresses load surges and reduces the lag in real-time adjustments; simultaneously, the constraints ensure the safety of tap position regulation.

[0036] This invention constructs a multi-dimensional objective function encompassing total loss, voltage deviation, and lifetime loss, and introduces a weighted adaptive model. This model dynamically adjusts weights based on real-time influencing factors, flexibly responding to grid load fluctuations and changes in the operating environment. It finds the optimal solution balancing these objectives under various operating conditions, enabling timely and accurate adjustment of transformer tap positions. This control method considers the economic efficiency of transformer operation, power quality, and equipment lifespan, resolving the weight game problem in multi-objective optimization, enhancing the transformer's adaptability to complex operating conditions, and providing a precise and dynamic optimization control strategy for parallel transformer operation.

[0037] Please see Figure 2 Specifically, in a preferred embodiment of this application, the method further includes the following steps before solving the weighted objective function: Step S04: Train an LSTM prediction model based on historical load data, output load prediction results, and use the load prediction results as boundary conditions to solve the weighted objective function.

[0038] In specific implementation, load forecasting constraint injection is performed before solving the weighted objective function. In this embodiment, a Long Short-Term Memory (LSTM) network is used as the load forecasting model, and the historical load sequence {P} is input. load (t-1), P load (t-2), ..., P load (tn)}, and outputs the load forecast curve for a certain future time period. Taking 15 minutes as an example, the load forecast interval is Δt=900s: in, To predict the average load, Standard deviation; This is the lower limit of load forecasting; This represents the upper limit of load forecasting.

[0039] Transform the prediction interval into a hard constraint in the optimization problem: st in, Let be the load distribution factor for the i-th transformer. This is the rated capacity.

[0040] In this embodiment, the load is predicted by an LSTM model, and the result is used as a boundary condition to inject load boundary constraints in advance. This avoids the optimization results from becoming invalid due to future load changes, and allows for early response to load changes, reducing the lag in real-time adjustment of transformer taps.

[0041] Specifically, the step of using the load forecast result as boundary conditions and solving the weighted objective function includes: Based on the prediction results, the predicted load mutation rate is calculated. When the predicted load mutation rate is greater than the preset mutation threshold, a forced adjustment strategy for the weight coefficient of the corresponding target is implemented.

[0042] Calculate the rate of change of the load forecast curve: When satisfied When the load exceeds the preset mutation threshold (10% / min), it is determined to be a load mutation, and the weight forced adjustment strategy is triggered to perform the following operations: And simultaneously relax the lifespan loss constraints, Modified to , This is the original constraint threshold.

[0043] In this embodiment, by monitoring the load prediction mutation rate, a forced adjustment of weights is triggered when the load fluctuates drastically. This increases the target weight of voltage deviation, reduces the weights of loss and lifetime loss, and relaxes lifetime constraints. Based on this strategy, the system can not only respond quickly to load mutations and prioritize voltage stability, avoiding system instability due to over-optimization of economy / lifetime, but also balance the multi-objective requirements under mutation scenarios by dynamically adjusting target priorities and constraints, reducing optimization lag and enhancing the anti-interference capability of transformer parallel operation.

[0044] Please see Figure 3 Specifically, in a preferred embodiment of this application, after the output transformer tap adjustment command, the following is also included: Step S05: Calculate the tap difference between adjacent transformers. If the tap difference is greater than the preset tap threshold, insert a transition tap sequence based on the preset switching time interval.

[0045] Let the current transformer tap vector be Optimize the target gear vector The maximum gear difference is expressed as: when When the value is greater than 3, a transition sequence is inserted. ; in, Indicates the initial state; Indicates the target state; (Maximum adjustment per step: 1 level).

[0046] The preset switching time interval is based on the real-time circulating current I. circDynamically determined: in, This represents the measured value of the circulating current before the m-th step switching.

[0047] In this embodiment, assuming two transformers operating in parallel, designated as transformer A and transformer B, the circulating current can be calculated through the following steps: Step 1: Calculate the equivalent voltages on the high-voltage side, medium-voltage side, and low-voltage side of transformer A. The calculation formulas are as follows: in, Indicates the short-circuit impedance between the high and low voltage sides; Indicates the short-circuit impedance on the high- and medium-voltage sides; This indicates the short-circuit impedance on the medium-low voltage side.

[0048] The equivalent voltages on the high-voltage side, medium-voltage side, and low-voltage side of transformer B are calculated using the following formulas: in, Indicates the short-circuit impedance between the high and low voltage sides; Indicates the short-circuit impedance on the high- and medium-voltage sides; This indicates the short-circuit impedance on the medium-low voltage side.

[0049] Step 2: Calculate the equivalent reactance values ​​of the high-voltage side, medium-voltage side, and low-voltage side of transformer A. The calculation formula is as follows: in, This represents the equivalent reactance value on the high-voltage side of transformer A. This represents the equivalent reactance value on the medium-voltage side of transformer A. This represents the equivalent reactance value on the low-voltage side of transformer A. This refers to the rated voltage value on the high-voltage side of transformer A. This is the rated power of transformer A.

[0050] The equivalent reactance values ​​for the high-voltage side, medium-voltage side, and low-voltage side of transformer B are calculated using the following formulas: in, This represents the equivalent reactance value on the high-voltage side of transformer B. This represents the equivalent reactance value on the medium-voltage side of transformer B. This represents the equivalent reactance value on the low-voltage side of transformer B. This refers to the rated voltage value on the high-voltage side of transformer B. This is the rated power of transformer B.

[0051] The third step is to calculate the voltage difference between the high and medium voltage sides connected in parallel. The calculation formula is as follows: in, It is the voltage ratio between the high-voltage side and the medium-voltage side of transformer A; It is the voltage ratio between the high-voltage side and the medium-voltage side of transformer B; These are the rated voltage values ​​on the high-voltage side of transformers A and B. and same.

[0052] Step 4: Calculate the parallel circulating current of the high and medium voltage circuits. The calculation formula is as follows: The corresponding calculation formula for the voltage difference between the high and low sides connected in parallel is as follows: in, It is the voltage ratio between the high-voltage side and the low-voltage side of transformer A; It is the voltage ratio between the high-voltage side and the medium-voltage side of transformer B; These are the rated voltage values ​​on the high-voltage side of transformers A and B.

[0053] The corresponding calculation formulas for the high-voltage and low-voltage parallel circulating currents are as follows: In this embodiment, by controlling the tap difference and inserting a transition sequence, significant abrupt changes in transformer tap positions are avoided, reducing the circulating current surge caused by sudden tap changes and ensuring the stability of parallel operation. Furthermore, the dynamic switching time interval is determined based on the real-time circulating current, allowing for adaptive adjustment of the switching rhythm according to the current magnitude. When the circulating current is large, the interval is extended to avoid additional losses or faults caused by superimposed surges.

[0054] The method of inserting the transition gear sequence based on a preset switching time interval also includes: Monitor the rate of change of transformer oil temperature and calculate the oil temperature derivative, and implement a graded backoff strategy based on the oil temperature derivative.

[0055] By collecting oil temperature Data, real-time calculation of oil temperature derivative: Implement a graded backoff strategy based on the oil temperature derivative: First trigger When the preset oil temperature derivative threshold is used, the switching speed is reduced by half. Second trigger When the preset oil temperature derivative threshold is reached, the auxiliary cooling system is activated.

[0056] In this embodiment, by monitoring the oil temperature derivative and setting a graded avoidance strategy based on the oil temperature derivative monitoring, abnormal temperature rise is detected in real time: when the threshold is exceeded for the first time, the speed is reduced and switched to slow down the temperature rise; when the threshold is exceeded for the second time, auxiliary cooling is started. This dual protection prevents the equipment from overheating, effectively avoids the risk of accelerated insulation aging, and extends the transformer life.

[0057] Please see Figure 4 This application also provides an optimized control system for parallel operation of transformers, which applies the aforementioned method and includes: The data acquisition unit is used to acquire the operating parameters of transformers operating in parallel. The function construction unit is used to construct a multi-objective optimization function based on the operating parameters. The multi-objective optimization function includes the transformer total loss target, voltage deviation target, and lifetime loss target. The function adjustment unit is used to dynamically adjust the weight coefficients of each objective function through a weighted adaptive model to generate a weighted objective function. The function solving unit is used to solve the optimal solution of the weighted objective function and output the transformer tap adjustment command.

[0058] The functional explanation of each unit in this embodiment is the same as that of a transformer parallel operation optimization control method, and the technical effect is the same, so it will not be repeated here.

[0059] This application also provides a computer-readable storage medium, which includes a stored program, wherein the program controls the device where the computer-readable storage medium is located to execute the aforementioned transformer parallel operation optimization control method when it is running.

[0060] The technical effects of this embodiment are the same as those of the transformer parallel operation optimization control method in the embodiment, and will not be repeated here.

[0061] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0062] This application also provides a processor for running a program, wherein the program executes the aforementioned transformer parallel operation optimization control method.

[0063] The technical effects of this embodiment are the same as those of the transformer parallel operation optimization control method in Embodiment 1, and will not be repeated here.

[0064] In this embodiment, the processor may be a central processing unit (CPU), a controller, a microcontroller, or other data processing chip.

[0065] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. 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 the invention.

[0066] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0067] 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.

[0068] If the integrated 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, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. 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 or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the specification of the present invention.

Claims

1. A transformer parallel operation optimization control method, characterized in that, The method comprises the following steps: acquiring operation parameters of transformers in parallel operation; constructing a multi-objective optimization function based on the operation parameters, the multi-objective optimization function including a total loss target of the transformers, a voltage deviation target, and a life loss target; dynamically adjusting weight coefficients of each target function through a weight self-adaptive model to generate a weighted target function; solving an optimal solution of the weighted target function and outputting a transformer gear adjustment instruction.

2. The method for optimal control of parallel operation of transformers according to claim 1, characterized in that, The multi-objective optimization function is expressed as: wherein represents a total loss target function; represents a voltage deviation target; represents a lifetime loss target function; , and are weight coefficients for the respective targets, and ; The total loss target function is expressed as: In the formula, represents the first copper loss of the transformer; represents the first iron loss of the transformer; The voltage deviation target function is expressed as: In the formula, represents the actual voltage of the busbar; represents the reference voltage; The life loss target function is expressed as: In the formula, indicates the health state index of the distribution transformer.

3. The method of claim 2, wherein, The dynamically adjusting weight coefficients of each target function through the weight self-adaptive model comprises: By calculating the target conflict factor in real time is represented as: In the formula, and respectively represent the variation of the total loss target and the voltage deviation target. When the calculated target conflict factor is greater than a preset threshold, re-performing weight distribution is expressed as: wherein, , and respectively represent the weight coefficient of the corresponding target after redistribution; is the conflict adjustment gain.

4. The method of claim 3, wherein, Before solving the weighted target function, the method further comprises the following steps: training an LSTM prediction model based on historical load data to output a load prediction result, taking the load prediction result as a boundary condition, and solving the weighted target function in combination with the weighted target function.

5. The method of claim 4, wherein, The taking the load prediction result as a boundary condition and solving the weighted target function in combination with the weighted target function comprises: calculating a predicted load mutation rate based on the prediction result, and performing a weight coefficient forced adjustment strategy of a corresponding target when the predicted load mutation rate is greater than a preset mutation threshold.

6. The method of claim 1, wherein, After the outputting of the transformer gear adjustment instruction, the method further comprises the following steps: calculating a gear difference of adjacent transformers, and inserting a transition gear sequence based on a preset switching time interval if the gear difference is greater than a preset gear threshold.

7. The method of claim 1, wherein, The inserting a transition gear sequence based on a preset switching time interval further comprises: monitoring a transformer oil temperature change rate, calculating an oil temperature derivative, and performing a hierarchical backoff strategy according to the oil temperature derivative.

8. A transformer parallel operation optimization control system, characterized in that, The method according to any one of claims 1 to 7 comprises: a data acquisition unit configured to acquire operation parameters of transformers in parallel operation; a function construction unit configured to construct a multi-objective optimization function based on the operation parameters, the multi-objective optimization function including a total loss target of the transformers, a voltage deviation target, and a life loss target; a function adjustment unit configured to dynamically adjust weight coefficients of each target function through a weight self-adaptive model to generate a weighted target function; a function solving unit configured to solve an optimal solution of the weighted target function and output a transformer gear adjustment instruction.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein the program controls a device where the computer readable storage medium is located to execute the transformer parallel operation optimization control method according to any one of claims 1 to 7 when the program is running.

10. A processor, comprising: The processor is configured to run a program, wherein the program executes the transformer parallel operation optimization control method according to any one of claims 1 to 7 when the program is running.

Images