Method and device for controlling electromagnetic loss of power transformer in smart grid environment

Abstract

The application provides a power transformer electromagnetic loss control method and device in a smart grid environment, and relates to the field of smart grids.The method comprises the following steps: predicting the cooling demand of a transformer according to a predicted power load sequence and a spatial temperature sequence, and outputting a predicted cooling load sequence; taking the satisfaction of the predicted cooling load sequence as a constraint, taking the minimization of energy consumption and oil temperature fluctuation as an optimization target, optimizing the cooling parameters of a forced oil cooling device, outputting an optimal cooling parameter sequence, and controlling the forced oil cooling device to dissipate heat for the transformer.The technical problem that the traditional control method lacks dynamic adjustment capability of the cooling strategy, and temperature rise abnormalities are prone to occur in a high load or high temperature environment, so that the transformer core loss and winding loss are significantly increased, and the electromagnetic loss is high can be solved.The method can realize precise and efficient cooling control, effectively reduce the electromagnetic loss, and improve the operation efficiency and stability of the transformer.

Description

Technical Field

[0001] This invention relates to the field of smart grids, and more particularly to a method and apparatus for controlling electromagnetic losses of power transformers in a smart grid environment. Background Technology

[0002] Transformers generate electromagnetic losses during operation, mainly including core losses and winding losses. Temperature rise is a key factor affecting the change of electromagnetic losses. Therefore, cooling systems (such as forced oil cooling systems) are widely used in power transformers to control equipment temperature and ensure their safe and stable operation.

[0003] However, most transformer cooling systems in the present technology adopt static or rule-driven control strategies, which usually trigger the start and stop of fans or oil pumps based on the current temperature threshold. They lack the ability to effectively perceive and predict future load changes and ambient temperature trends, and cannot achieve dynamic optimization and adjustment of the cooling strategy. This control method has problems such as response lag, excessive energy consumption or overcooling. Especially under high load or high external temperature conditions, transformers are prone to abnormal temperature rise, which leads to a significant increase in core hysteresis loss and winding resistance loss, resulting in high electromagnetic losses, which in turn affects the operating efficiency and service life of the equipment. Summary of the Invention

[0004] The purpose of this invention is to provide a method and apparatus for controlling electromagnetic losses in power transformers under a smart grid environment. This addresses the technical problem that traditional transformer cooling system control methods lack dynamic adjustment capabilities for cooling strategies, are prone to abnormal temperature rise under high load or high temperature environments, leading to a significant increase in transformer core and winding losses, and consequently, high electromagnetic losses. The invention includes:

[0005] In a first aspect, the present invention provides a method for controlling electromagnetic losses of power transformers in a smart grid environment, comprising: analyzing and obtaining a predicted power load sequence of the transformer within a preset future time zone, and a spatial temperature sequence of the area where the transformer is located; predicting the cooling demand of the transformer based on the predicted power load sequence and the spatial temperature sequence, and outputting a predicted cooling load sequence; optimizing the cooling parameters of a forced oil cooling device with the constraint of satisfying the predicted cooling load sequence and minimizing energy consumption and oil temperature fluctuations as optimization objectives, and outputting an optimal cooling parameter sequence; and controlling the forced oil cooling device to dissipate heat from the transformer within the preset future time zone according to the optimal cooling parameter sequence.

[0006] Preferably, the method for controlling electromagnetic losses of power transformers in a smart grid environment further includes: monitoring and acquiring the power load of the transformer at P consecutive monitoring time points within a historical period to obtain a historical power load sequence; monitoring and acquiring load fluctuation correlation data of the transformer in a preset future time zone based on a preset load fluctuation correlation factor; and predicting and acquiring the predicted power load sequence of the transformer in the preset future time zone based on the historical power load sequence and the load fluctuation correlation data.

[0007] Preferably, the method for controlling electromagnetic losses of power transformers in a smart grid environment further includes: using the historical time period as a constraint, collecting a sample power load sequence set and a sample load fluctuation association dataset of the transformer within the same time period, and obtaining the historical power load sequence of the transformer within a historical preset time zone as a sample predicted power load sequence set, wherein the historical time period and the historical preset time zone are continuous time periods, and the time interval of the historical preset time zone is the same as the preset future time zone; using the sample power load sequence set and the sample load fluctuation association dataset as input, and using the sample predicted power load sequence set as supervision, training a long short-term memory network until convergence to obtain a power load prediction model; inputting the historical power load sequence and the load fluctuation association data into the power load prediction model, and outputting a predicted power load sequence.

[0008] Preferably, the method for controlling electromagnetic losses of power transformers in a smart grid environment further includes: collecting sample power load sequence sets and sample spatial temperature sequence sets based on the historical operation records of the transformer, and obtaining the historical cooling load sequences required under different sample power load sequence and sample spatial temperature sequence scenarios to obtain a sample cooling load sequence set; using the sample power load sequence set, sample spatial temperature sequence set, and sample cooling load sequence set, training a long short-term memory network until convergence to obtain a cooling demand prediction model; using the cooling demand prediction model, predicting cooling demand based on the predicted power load sequence and spatial temperature sequence, and outputting a predicted cooling load sequence.

[0009] Preferably, the method for controlling electromagnetic losses of power transformers in a smart grid environment further includes: obtaining the continuous operating time of the forced oil cooling device and analyzing it to obtain a sequence of continuous operating time at the same time node of the predicted cooling load sequence; performing cooling performance degradation analysis on the forced oil cooling device and constructing a time-performance degradation comparison table; based on the time-performance degradation comparison table, matching the continuous operating time sequence to obtain a performance degradation coefficient sequence; and compensating and updating the predicted cooling load sequence according to the performance degradation coefficient sequence.

[0010] Preferably, the method for controlling electromagnetic losses of power transformers in a smart grid environment further includes: using the attribute characteristics of the forced oil cooling device as constraints, retrieving historical operating logs of similar forced oil cooling devices, collecting a sample continuous working duration set, and obtaining the performance degradation ratio corresponding to different sample continuous working durations as sample performance degradation coefficients to obtain a sample performance degradation coefficient set; dividing and determining multiple continuous working duration intervals based on the sample continuous working duration set, and randomly selecting a first continuous working duration interval to extract a first sample performance degradation coefficient set covered by the first continuous working duration interval; performing anomaly removal and mean calculation on the first sample performance degradation coefficient set to obtain the mean of the first sample performance degradation coefficients; and constructing a duration-performance degradation comparison table based on the mapping relationship between the first continuous working duration interval and the mean of the first sample performance degradation coefficients.

[0011] Preferably, the method for controlling electromagnetic losses of power transformers in a smart grid environment further includes: obtaining the cooling parameter adjustment space of the forced oil cooling device; randomly generating several initial cooling parameter sequences within the cooling parameter adjustment space, wherein the cooling parameters include oil pump flow rate and fan speed; performing cooling performance analysis based on the several initial cooling parameter sequences to output several cooling efficiency sequences; filtering the several initial cooling parameter sequences based on the several cooling efficiency sequences and constrained by the predicted cooling load sequence to obtain several qualified cooling parameter sequences; and optimizing based on the several qualified cooling parameter sequences with the goal of minimizing energy consumption and oil temperature fluctuations to output the optimal cooling parameter sequence.

[0012] Preferably, the method for controlling electromagnetic losses of power transformers in a smart grid environment further includes: performing energy consumption simulation and oil temperature simulation based on the multiple qualified cooling parameter sequences, and outputting multiple energy consumption values ​​and multiple oil temperature sequences; performing temperature fluctuation analysis based on the multiple oil temperature sequences to obtain multiple oil temperature fluctuation degrees, wherein the oil temperature fluctuation degree is the ratio of the standard deviation of the oil temperature to the mean of the oil temperature; evaluating and determining multiple fitness levels based on the multiple energy consumption values ​​and multiple oil temperature fluctuation degrees with minimizing energy consumption and oil temperature fluctuation as the optimization objective, wherein the fitness level is negatively correlated with the energy consumption value and the oil temperature fluctuation degree; and performing optimization based on the multiple fitness levels and multiple qualified cooling parameter sequences to output the optimal cooling parameter sequence.

[0013] Preferably, the method for controlling electromagnetic losses of power transformers in a smart grid environment further includes: setting a qualified cooling parameter sequence as an initial solution; arranging the qualified cooling parameter sequences in descending order of fitness based on the multiple fitness values ​​to obtain an initial solution sequence; setting the first solution of the initial solution sequence as a superior solution and the other solutions as inferior solutions; adjusting the multiple inferior solutions according to a preset optimization step size with the superior solution as the direction to obtain multiple updated inferior solutions; sorting the superior solutions and the multiple updated inferior solutions in descending order of fitness to obtain an updated solution sequence; eliminating a preset proportion of tail solutions in the updated solution sequence; and using the cooling parameter adjustment space for equivalent replenishment, wherein the preset proportion is less than 5%; performing iterative optimization until a preset number of convergences is reached; and outputting the superior solution in the current updated solution sequence as the optimal cooling parameter sequence.

[0014] Secondly, the present invention also provides an electromagnetic loss control device for power transformers in a smart grid environment, used to execute a power transformer electromagnetic loss control method in a smart grid environment as described in the first aspect, comprising: a power load prediction module, used to analyze and obtain the predicted power load sequence of the transformer in a preset future time zone, and the spatial temperature sequence of the area where the transformer is located; a cooling demand prediction module, used to predict the cooling demand of the transformer based on the predicted power load sequence and the spatial temperature sequence, and output a predicted cooling load sequence; a cooling parameter optimization module, used to optimize the cooling parameters of the forced oil cooling device with the predicted cooling load sequence as a constraint and minimizing energy consumption and oil temperature fluctuation as the optimization objective, and output an optimal cooling parameter sequence; and a transformer heat dissipation control module, used to control the forced oil cooling device to dissipate heat from the transformer in the preset future time zone according to the optimal cooling parameter sequence.

[0015] The embodiments of the present invention have the following advantages:

[0016] By analyzing and obtaining the predicted power load sequence of the transformer within a preset future time zone, as well as the spatial temperature sequence of the area where the transformer is located, the cooling demand of the transformer is predicted based on the predicted power load sequence and spatial temperature sequence, and a predicted cooling load sequence is output. Then, with the predicted cooling load sequence as a constraint and minimizing energy consumption and oil temperature fluctuations as optimization objectives, the cooling parameters of the forced oil cooling system are optimized, and an optimal cooling parameter sequence is output. Finally, within the preset future time zone, the forced oil cooling system is controlled to dissipate heat from the transformer according to the optimal cooling parameter sequence. In other words, by predicting future cooling load demand and using the cooling load sequence as a constraint, an optimization model is constructed with the goal of minimizing energy consumption and oil temperature fluctuations. The control parameters of the forced oil cooling system are optimized to obtain the optimal cooling parameter sequence to control the operation of the cooling system, thereby achieving precise and efficient cooling control, effectively reducing electromagnetic losses, and improving the operating efficiency and stability of the transformer. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the steps of a method for controlling electromagnetic losses in a power transformer under a smart grid environment, as described in this invention.

[0018] Figure 2 This is a schematic diagram of the structure of a power transformer electromagnetic loss control device in a smart grid environment according to the present invention.

[0019] Explanation of reference numerals in the attached figures:

[0020] Power load prediction module 11, cooling demand prediction module 12, cooling parameter optimization module 13, transformer heat dissipation control module 14. Detailed Implementation

[0021] This invention provides a method and device for controlling electromagnetic losses in power transformers under a smart grid environment. It addresses the technical problem that traditional transformer cooling system control methods lack dynamic adjustment capabilities for cooling strategies, are prone to abnormal temperature rises under high load or high temperature conditions, leading to significantly increased core and winding losses and consequently high electromagnetic losses. By predicting future cooling load demands and constraining the fulfillment of this load sequence, an optimization model is constructed with the goal of minimizing energy consumption and oil temperature fluctuations. This model optimizes the control parameters of the forced oil cooling system, obtaining the optimal cooling parameter sequence to control the system's operation. This achieves precise and efficient cooling control, effectively reducing electromagnetic losses and improving the transformer's operating efficiency and stability.

[0022] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. It should also be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all of them.

[0023] Example 1, please refer to the appendix. Figure 1 This invention provides a method for controlling the electromagnetic loss of a power transformer in a smart grid environment, which is applied to a power transformer electromagnetic loss control device in a smart grid environment, and specifically includes the following steps:

[0024] S10: Analyze and obtain the predicted power load sequence of the transformer in the preset future time zone, as well as the spatial temperature sequence of the area where the transformer is located.

[0025] Furthermore, step S10 of the present invention further includes:

[0026] S11: Monitor and obtain the power load of the transformer at P consecutive monitoring time points within a historical period to obtain the historical power load sequence; S12: Based on the preset load fluctuation correlation factor, monitor and obtain the load fluctuation correlation data of the transformer within a preset future time zone.

[0027] Specifically, firstly, the number of continuous monitoring time points is set to P, where P is a positive integer not less than 5 to ensure that the sequence data has a certain time span and representativeness of fluctuations. Next, the power load of the transformer at P consecutive monitoring time points within a historical period is monitored and acquired. For example, if the system collects load data every 15 minutes, then P equals 12, indicating that the power load changes in the past 3 hours are acquired. By collecting indicators such as power or current at P time points, a complete historical power load sequence is constructed. This sequence will be used in subsequent modeling as one of the inputs to the prediction model, reflecting the load evolution trend and periodic characteristics of the transformer.

[0028] On the other hand, preset load fluctuation correlation factors are obtained. Load fluctuation correlation factors refer to external variables that are highly correlated with transformer load changes in statistical or machine learning modeling, such as the operation plan or electricity consumption characteristics of the connected load side (such as the start-up and shutdown schedule of industrial equipment, electricity price trends), weather information (such as temperature, humidity, and solar radiation intensity), etc. Then, according to the time range within the set future prediction window (such as the next 1 to 4 hours), the time series data of the above correlation factors are collected to form a load fluctuation correlation dataset, which is used to assist in modeling and analyzing the potential load trend changes of the transformer in the future time zone.

[0029] By integrating historical operating data and external fluctuation correlation data, an accurate input basis is provided for subsequent cooling load prediction and optimized control, thereby improving the foresight and scientific nature of the overall control strategy.

[0030] S13: Based on the historical power load sequence and load fluctuation correlation data, predict the power load sequence of the transformer in the preset future time zone.

[0031] Furthermore, step S13 of the present invention also includes:

[0032] S131: Using the historical time period as a constraint, collect sample power load sequence sets and sample load fluctuation association datasets of transformers within the same time period, and obtain the historical power load sequence of transformers within a historical preset time zone as the sample predicted power load sequence set. The historical time period and the historical preset time zone are continuous time periods, and the time interval of the historical preset time zone is the same as the preset future time zone. S132: Using the sample power load sequence set and sample load fluctuation association dataset as input, and the sample predicted power load sequence set as supervision, train a long short-term memory network until convergence to obtain a power load prediction model. S133: Input the historical power load sequence and load fluctuation association data into the power load prediction model and output the predicted power load sequence.

[0033] Specifically, firstly, constrained by the historical time period, a sample power load sequence set and a sample load fluctuation correlation dataset of transformers within the same time period are collected. The historical time period refers to a continuous time period selected by the system for collecting multiple sample data. This time period can cover several hours, days, or even weeks, with the specific length set according to the training requirements of the prediction model and the actual data distribution. Within this historical time period, rolling sampling is performed with a fixed step size to extract multiple time segment samples. Each sequence in the sample power load sequence set represents the load change trajectory of the transformer within a time window. Each record in the sample load fluctuation correlation dataset contains correlation factors (such as temperature, industrial load status, etc.) within the same time period as the corresponding load sequence. Next, for each sampled sample, a historical preset time zone with the same length as the future prediction target time zone needs to be specified. This time zone immediately follows the sampling time period. For example, if the model predicts a future load sequence of 4 points every 15 minutes within 1 hour, then the historical preset time zone for each sample is also the 1 hour immediately following that sample. Then, the historical power load sequence of the transformer within the historical preset time zone is obtained as the sample predicted power load sequence set.

[0034] Next, using the sample power load sequence set and the sample load fluctuation association dataset as input, and the sample predicted power load sequence set as supervision, a Long Short-Term Memory (LSTM) network is trained. The LSTM network includes an input layer, multiple hidden layers, and an output layer. The input layer receives the aforementioned multi-dimensional time series; the hidden layers use multi-layer LSTM units to capture long-term load fluctuation trends; and the output layer is a regression layer (e.g., a Dense layer) that outputs the predicted load values ​​for the next T time steps. During training, all sample data are first standardized to eliminate the influence of feature scale differences. Then, forward and backward propagation are performed using the training set, and the model parameters are iteratively updated using an optimizer (e.g., Adam) to minimize the error between the predicted and actual values. A validation set is introduced during training to monitor model performance changes in real time and determine whether overfitting or convergence has occurred. When the maximum number of training epochs (e.g., 100 epochs) is reached, or the validation error is lower than a preset threshold, the model is considered to have converged, and the training process is terminated, resulting in a trained power load prediction model.

[0035] Then, the historical power load sequence and load fluctuation correlation data are used as input features and fed into the pre-trained power load prediction model. After forward propagation, the model outputs the predicted power load sequence for the future preset time period, reflecting the load trend of the transformer in the future time zone, and providing an accurate basis for subsequent cooling demand prediction and control strategy optimization.

[0036] S20: Based on the predicted power load sequence and the spatial temperature sequence, predict the cooling demand of the transformer and output the predicted cooling load sequence.

[0037] Furthermore, step S20 of the present invention also includes:

[0038] S21: Based on the historical operation records of the transformer, collect sample power load sequence sets and sample spatial temperature sequence sets, and obtain the historical cooling load sequences required under different sample power load sequence and sample spatial temperature sequence scenarios to obtain a sample cooling load sequence set; S22: Using the sample power load sequence set, sample spatial temperature sequence set, and sample cooling load sequence set, train a long short-time memory network until convergence to obtain a cooling demand prediction model; S23: Using the cooling demand prediction model, predict the cooling demand based on the predicted power load sequence and spatial temperature sequence, and output the predicted cooling load sequence.

[0039] Specifically, based on the transformer's historical operating records, the power load sequence and corresponding spatial temperature sequence are first collected for multiple sample time periods to form a sample power load sequence set and a sample spatial temperature sequence set. Then, for different load and temperature combination scenarios, combined with the actual cooling requirements of the transformer, the corresponding cooling load sequence under these historical conditions is further obtained to construct a sample cooling load sequence set. This sample set reflects the changing patterns of the transformer's cooling requirements under different environments and operating conditions, providing rich and accurate data support for the training and optimization of the cooling demand prediction model.

[0040] Next, using the collected sample power load sequence set, sample spatial temperature sequence set, and corresponding sample cooling load sequence set as input features and supervision labels, a Long Short-Term Memory (LSTM) network is trained. Multi-layer LSTM units are used to perform deep learning on the time dependencies and nonlinear relationships in the time-series data. During training, the power load and temperature sequences are input, and the model predicts future cooling load sequences, comparing them with actual sample cooling load sequences to calculate the error. The model parameters are continuously adjusted using backpropagation and an optimizer (such as Adam) to minimize the prediction error. Training iterations continue until the model's error on the validation set stabilizes or meets preset convergence conditions, thus obtaining a cooling demand prediction model that can accurately predict future cooling needs.

[0041] Then, using the trained cooling demand prediction model, the predicted power load sequence and the corresponding spatial temperature sequence are taken as input. Based on these time-series characteristics and combined with the historically learned influence of load and temperature on cooling demand, the model performs deep time-series analysis and mapping calculation. After forward inference of the model, the predicted cooling load sequence in the future preset time zone is output, reflecting the changing trend of the transformer's cooling demand under different load and ambient temperature conditions, and providing a scientific basis for subsequent parameter optimization and dynamic control of the cooling system.

[0042] Furthermore, step S20 of the present invention also includes:

[0043] S24: Obtain the continuous operating time of the forced oil cooling system and analyze it to obtain the continuous operating time sequence at the same time node of the predicted cooling load sequence.

[0044] Specifically, the first step is to obtain the current continuous operating time of the forced oil cooling system, i.e., the cumulative running time from the most recent start-up to the current moment. Then, combining this with future time points in the predicted cooling load sequence, the expected continuous operating time for each time point is calculated. This time is equal to the current continuous operating time plus the time interval from the current moment to that time point, resulting in the continuous operating time sequence. By analyzing the obtained continuous operating time sequence, the operating load status of the cooling system within the predicted time range can be accurately reflected, providing key time parameter support for cooling performance degradation assessment and control strategy optimization.

[0045] S25: Perform a cooling performance degradation analysis on the forced oil cooling system and construct a time-performance degradation comparison table.

[0046] Furthermore, step S25 of the present invention also includes:

[0047] S251: Using the attribute characteristics of the forced oil cooling system as constraints, retrieve the historical operation logs of similar forced oil cooling systems, collect a set of sample continuous working durations, and obtain the performance degradation ratio corresponding to different sample continuous working durations as the sample performance degradation coefficients to obtain a set of sample performance degradation coefficients; S252: Divide and determine multiple continuous working duration intervals based on the set of sample continuous working durations, and randomly select the first continuous working duration interval to extract the first sample performance degradation coefficient set covered by the first continuous working duration interval; S253: Perform anomaly removal and mean calculation on the first sample performance degradation coefficient set to obtain the mean of the first sample performance degradation coefficients; S254: Based on the mapping relationship between the first continuous working duration interval and the mean of the first sample performance degradation coefficients, construct a duration-performance degradation comparison table.

[0048] Specifically, firstly, based on the specific attributes of the forced oil cooling system (such as model, capacity, and operating environment), historical operating logs of similar or identical forced oil cooling systems are retrieved from the database to collect their continuous operating duration data under different operating conditions, forming a sample continuous operating duration set. Simultaneously, combined with actual maintenance and inspection records, the performance degradation ratio of these samples under the corresponding continuous operating duration is obtained, and this ratio is defined as the sample performance degradation coefficient. By aggregating the performance degradation coefficients of multiple samples, a sample performance degradation coefficient set is constructed, providing data support for subsequent cooling system performance evaluation and degradation prediction based on continuous operating duration.

[0049] Next, based on the sample continuous operating time set, it is divided into multiple continuous operating time intervals, such as dividing the continuous operating time into intervals of 0 to 100 hours, 101 to 200 hours, 201 to 300 hours, etc., every 100 hours. Then, one of these intervals is randomly selected as the first continuous operating time interval, for example, the 101 to 200 hour interval. Further, all sample performance degradation coefficients corresponding to the continuous operating time within this interval are extracted from the sample performance degradation coefficient set to form the first sample performance degradation coefficient set. Then, for the extracted first sample performance degradation coefficient set, outlier detection is performed. Statistical methods (such as the standard deviation method) are used to identify and remove outlier data points that significantly deviate from the overall data distribution, ensuring the accuracy and representativeness of the data. Subsequently, the mean of the data after removing outliers is calculated to obtain the average value of the first sample performance degradation coefficients. This mean reflects the typical level of performance degradation of the forced oil cooling system within the selected continuous operating time interval, providing a reliable statistical basis for subsequent performance evaluation and prediction.

[0050] Then, based on the aforementioned method for calculating the average performance degradation coefficient of the first continuous operating time interval and its corresponding samples, a similar analysis was performed on the other divided continuous operating time intervals. Outliers were removed and the average performance degradation coefficient within each interval was calculated. Next, each continuous operating time interval was mapped one-to-one with its corresponding average performance degradation coefficient, constructing a complete duration-performance degradation mapping table. This table intuitively reflects the performance degradation pattern of the forced oil cooling system under different operating durations, facilitating subsequent performance evaluation and prediction based on continuous operating time.

[0051] S26: Based on the duration-performance degradation comparison table, a performance degradation coefficient sequence is obtained by matching the continuous working duration sequence; S27: The predicted cooling load sequence is compensated and updated according to the performance degradation coefficient sequence.

[0052] Specifically, firstly, based on the established duration-performance degradation lookup table, the operating duration corresponding to each time point in the continuous operating duration sequence is matched with the duration interval in the lookup table to obtain the corresponding performance degradation coefficient. This forms a performance degradation coefficient sequence that corresponds one-to-one with the continuous operating duration sequence. This sequence reflects the degree of performance degradation of the cooling system due to the increase in operating time at different time points. Next, the predicted cooling load value is adjusted according to the performance degradation coefficient to correct for the weakening of cooling capacity caused by the decline in cooling system performance. For example, the product of the performance degradation coefficient and the predicted cooling load is used as the updated predicted cooling load, resulting in a predicted cooling load sequence. This allows the updated cooling load sequence to more accurately reflect the actual cooling demand, improving the accuracy and effectiveness of cooling control.

[0053] S30: With the predicted cooling load sequence as a constraint and minimizing energy consumption and oil temperature fluctuation as the optimization objective, optimize the cooling parameters of the forced oil cooling system and output the optimal cooling parameter sequence.

[0054] Furthermore, step S30 of the present invention also includes:

[0055] S31: Obtain the cooling parameter adjustment space of the forced oil cooling system, and randomly generate several initial cooling parameter sequences within the cooling parameter adjustment space, wherein the cooling parameters include oil pump flow rate and fan speed; S32: Perform cooling performance analysis based on the several initial cooling parameter sequences, and output several cooling efficiency sequences; S33: Based on the several cooling efficiency sequences, and constrained by the predicted cooling load sequence, screen the several initial cooling parameter sequences to obtain multiple qualified cooling parameter sequences.

[0056] Specifically, the adjustable cooling parameter range in the forced oil cooling system is first determined, i.e., the cooling parameter adjustment space, which mainly includes the upper and lower limits of oil pump flow rate and fan speed and their variation range. Then, based on this adjustment space, several sets of initial cooling parameter sequences are randomly generated. Each sequence consists of oil pump flow rate and fan speed values ​​randomly selected within the allowable range, covering different combinations of cooling strategies. These initial parameter sequences will serve as the starting point for the optimization algorithm and will be used for subsequent optimization of cooling control parameters and performance evaluation.

[0057] Next, based on the aforementioned initial cooling parameter sequences, the cooling performance of each set of parameters is analyzed in simulated or actual operating environments. The cooling effect under different load and temperature conditions is evaluated, and the corresponding cooling efficiency sequence is calculated. This cooling efficiency sequence reflects the dynamic performance of cooling capacity and energy utilization efficiency achieved using this parameter sequence over time. Then, based on these cooling efficiency sequences and constrained by meeting the cooling requirements of the predicted cooling load sequence, the initial cooling parameter sequences are screened. Parameter sequences that guarantee cooling performance that meets or exceeds the predicted load requirements, while possessing high cooling efficiency, are designated as qualified cooling parameter sequences, providing effective alternatives for subsequent optimization and actual control.

[0058] S34: With minimizing energy consumption and oil temperature fluctuation as the optimization objective, the system optimizes based on the multiple qualified cooling parameter sequences and outputs the optimal cooling parameter sequence.

[0059] Furthermore, step S34 of the present invention also includes:

[0060] S341: Perform energy consumption simulation and oil temperature simulation based on the multiple qualified cooling parameter sequences, and output multiple energy consumption values ​​and multiple oil temperature sequences; S342: Perform temperature fluctuation analysis based on the multiple oil temperature sequences to obtain multiple oil temperature fluctuation degrees, wherein the oil temperature fluctuation degree is the ratio of the standard deviation of the oil temperature to the mean of the oil temperature; S343: With minimizing energy consumption and oil temperature fluctuation as the optimization objective, evaluate and determine multiple fitness levels based on the multiple energy consumption values ​​and multiple oil temperature fluctuation degrees, wherein the fitness level is negatively correlated with the energy consumption value and the oil temperature fluctuation degree.

[0061] Specifically, firstly, for each qualified cooling parameter sequence, energy consumption simulation and oil temperature simulation are conducted. Energy consumption simulation assesses the energy consumption of equipment such as oil pumps and fans under that parameter configuration, deriving the corresponding energy consumption values. Oil temperature simulation, based on the cooling effect and system thermal balance model, predicts the temperature change of the oil at different time points, generating corresponding oil temperature sequences. These simulation results comprehensively evaluate the performance of each qualified parameter sequence in terms of energy efficiency and temperature control, providing a scientific basis for further optimization. Next, temperature fluctuation analysis is performed on each oil temperature sequence to assess the stability of the oil temperature throughout the entire operating cycle. Specifically, the standard deviation and mean of the temperature sequence are calculated, and then divided to obtain the oil temperature fluctuation. This fluctuation reflects the relative degree of change in oil temperature; a smaller value indicates more stable temperature and less fluctuation, while a larger value indicates greater temperature fluctuation and unstable cooling system control. Multiple oil temperature fluctuation values ​​are obtained, and by comparing the oil temperature fluctuation values ​​under multiple parameter configurations, a cooling strategy with better temperature control performance can be further selected.

[0062] Then, with minimizing energy consumption and oil temperature fluctuation as the optimization objectives, a fitness evaluation model is constructed. For each qualified cooling parameter sequence, the fitness value is calculated by combining its corresponding energy consumption value and oil temperature fluctuation. The fitness value is negatively correlated with the energy consumption value and temperature fluctuation, that is, the lower the energy consumption and fluctuation, the higher the fitness value, and vice versa. This fitness evaluation mechanism helps to select the control strategy with the best overall performance from multiple candidate cooling parameter schemes, which can be used to guide the actual operation of the forced oil cooling system.

[0063] S344: Based on the multiple fitness levels and multiple qualified cooling parameter sequences, perform optimization and output the optimal cooling parameter sequence.

[0064] Furthermore, step S344 of the present invention further includes:

[0065] S3441: Set the qualified cooling parameter sequence as the initial solution. Based on the multiple fitness values, arrange the multiple qualified cooling parameter sequences in descending order of fitness to obtain the initial solution sequence. S3442: Set the first solution of the initial solution sequence as the optimal solution and the other solutions as inferior solutions. Using the optimal solution as the direction, adjust the multiple inferior solutions according to a preset optimization step size to obtain multiple updated inferior solutions. S3443: Sort the optimal solutions and the multiple updated inferior solutions in descending order of fitness to obtain the updated solution sequence. Eliminate a preset proportion of the tail solutions in the updated solution sequence and use the cooling parameter adjustment space for equivalent replenishment, wherein the preset proportion is less than 5%. S3444: Perform iterative optimization until a preset number of convergences is reached. Output the optimal solution in the current updated solution sequence as the optimal cooling parameter sequence.

[0066] Specifically, firstly, the previously selected qualified cooling parameter sequences are used as the initial solution set. Based on the fitness values ​​of each sequence, they are sorted from largest to smallest fitness to construct the initial solution sequence. This sorting process helps identify the optimal cooling control strategy in the current parameter configuration and provides an ordered reference for subsequent optimization. Then, the cooling parameter sequence with the highest fitness in the sorted sequence is designated as the optimal solution, and the remaining sequences are designated as inferior solutions. Using this optimal solution as the target direction, and considering the differences between each inferior and optimal solution in the parameter space, combined with a preset optimization step size, the parameters of each inferior solution are fine-tuned to move closer to the optimal solution. This process simulates a heuristic search or local improvement strategy, aiming to further improve the performance of inferior solutions, gradually approach the optimal control parameter configuration, and obtain multiple updated inferior solutions.

[0067] Next, the optimized optimal solutions are merged with multiple updated inferior solutions to form an updated solution set. These updated solutions are then sorted from highest to lowest fitness value to generate an updated solution sequence. To continuously improve the overall solution set quality, the solutions at the tail end of this sequence (i.e., those with the lowest fitness) are eliminated at a preset threshold (typically less than 5%) to remove the worst-performing cooling parameter configurations. Subsequently, new solutions equal in number to the eliminated solutions are randomly generated within the cooling parameter adjustment space to replenish the set, ensuring a stable solution set size and providing diversity and exploration capabilities for the next round of optimization, thereby enhancing overall optimization efficiency. Then, based on the above sorting, elimination, and replenishment mechanism, iterative optimization is continuously performed. In each iteration, the current best solution is used as a guide to fine-tune the parameters of inferior solutions, and the solution sequence is updated according to the fitness. At the same time, low-quality solutions are eliminated and new solutions are added. This process is repeated until the preset number of convergences is reached or other convergence conditions are met (such as the fitness of the best solution tending to stabilize). Finally, the solution with the highest fitness in the updated solution sequence at the end of the iteration is determined as the optimal cooling parameter sequence, which is used to guide the forced oil cooling system to achieve precise and efficient heat dissipation control, thereby effectively reducing electromagnetic losses and improving the operating efficiency and reliability of the transformer.

[0068] S40: Within the preset future time zone, the forced oil cooling system is controlled to dissipate heat from the transformer according to the optimal cooling parameter sequence.

[0069] Specifically, within the preset future time zone, the forced oil cooling system is dynamically controlled based on the previously optimized cooling parameter sequence. This involves sequentially calling up the oil pump flow rate and fan speed settings from the parameter sequence according to time nodes, precisely adjusting the operating state of the cooling device to match the predicted cooling load. This control method not only ensures that the transformer maintains a reasonable operating temperature under future load and ambient temperature conditions but also avoids energy waste or equipment aging caused by overcooling or undercooling. This maximizes heat dissipation efficiency and minimizes electromagnetic losses, improving the overall stability and economy of the transformer's operation.

[0070] In summary, the electromagnetic loss control method for power transformers in a smart grid environment provided by this invention has the following technical effects:

[0071] By analyzing and obtaining the predicted power load sequence of the transformer within a preset future time zone, as well as the spatial temperature sequence of the area where the transformer is located, the cooling demand of the transformer is predicted based on the predicted power load sequence and spatial temperature sequence, and a predicted cooling load sequence is output. Then, with the predicted cooling load sequence as a constraint and minimizing energy consumption and oil temperature fluctuations as optimization objectives, the cooling parameters of the forced oil cooling system are optimized, and an optimal cooling parameter sequence is output. Finally, within the preset future time zone, the forced oil cooling system is controlled to dissipate heat from the transformer according to the optimal cooling parameter sequence. In other words, by predicting future cooling load demand and using the cooling load sequence as a constraint, an optimization model is constructed with the goal of minimizing energy consumption and oil temperature fluctuations. The control parameters of the forced oil cooling system are optimized to obtain the optimal cooling parameter sequence to control the operation of the cooling system, thereby achieving precise and efficient cooling control, effectively reducing electromagnetic losses, and improving the operating efficiency and stability of the transformer.

[0072] Example 2: Based on the same inventive concept as the electromagnetic loss control method for power transformers in a smart grid environment described in the foregoing examples, this invention also provides an electromagnetic loss control device for power transformers in a smart grid environment. Please refer to the appendix. Figure 2 ,include:

[0073] The power load prediction module 11 is used to analyze and obtain the predicted power load sequence of the transformer in a preset future time zone, as well as the spatial temperature sequence of the area where the transformer is located; the cooling demand prediction module 12 is used to predict the cooling demand of the transformer based on the predicted power load sequence and the spatial temperature sequence, and output the predicted cooling load sequence; the cooling parameter optimization module 13 is used to optimize the cooling parameters of the forced oil cooling system with the constraints of satisfying the predicted cooling load sequence and the optimization objectives of minimizing energy consumption and oil temperature fluctuations, and output the optimal cooling parameter sequence; the transformer heat dissipation control module 14 is used to control the forced oil cooling system to dissipate heat from the transformer in the preset future time zone according to the optimal cooling parameter sequence.

[0074] Furthermore, the power transformer electromagnetic loss control device in the smart grid environment is also used to: monitor and acquire the power load of the transformer at P consecutive monitoring time points within a historical period to obtain a historical power load sequence; monitor and acquire the load fluctuation correlation data of the transformer in a preset future time zone according to a preset load fluctuation correlation factor; and predict and acquire the predicted power load sequence of the transformer in the preset future time zone according to the historical power load sequence and the load fluctuation correlation data.

[0075] Furthermore, the electromagnetic loss control device for power transformers in the smart grid environment is also used for: collecting sample power load sequence sets and sample load fluctuation association datasets of transformers within the same time period, using the historical time period as a constraint, and obtaining the historical power load sequence of the transformer within a historical preset time zone as a sample predicted power load sequence set, wherein the historical time period and the historical preset time zone are continuous time periods, and the time interval of the historical preset time zone is the same as the preset future time zone; using the sample power load sequence set and sample load fluctuation association dataset as input, and using the sample predicted power load sequence set as supervision, training a long short-term memory network until convergence to obtain a power load prediction model; inputting the historical power load sequence and load fluctuation association data into the power load prediction model, and outputting a predicted power load sequence.

[0076] Furthermore, the electromagnetic loss control device for power transformers in the smart grid environment is also used to: collect sample power load sequence sets and sample spatial temperature sequence sets based on the historical operation records of the transformer, and obtain the historical cooling load sequences required under different sample power load sequence and sample spatial temperature sequence scenarios to obtain a sample cooling load sequence set; use the sample power load sequence set, sample spatial temperature sequence set, and sample cooling load sequence set to train a long short-term memory network until convergence to obtain a cooling demand prediction model; use the cooling demand prediction model to predict cooling demand based on the predicted power load sequence and spatial temperature sequence, and output the predicted cooling load sequence.

[0077] Furthermore, the electromagnetic loss control device for power transformers in the smart grid environment is also used to: obtain the continuous operating time of the forced oil cooling system and analyze it to obtain the continuous operating time sequence at the same time node of the predicted cooling load sequence; perform cooling performance degradation analysis on the forced oil cooling system and construct a time-performance degradation comparison table; based on the time-performance degradation comparison table, match the performance degradation coefficient sequence according to the continuous operating time sequence to obtain a performance degradation coefficient sequence; and compensate and update the predicted cooling load sequence according to the performance degradation coefficient sequence.

[0078] Furthermore, the electromagnetic loss control device for power transformers in the smart grid environment is also used for: using the attribute characteristics of the forced oil cooling system as constraints, retrieving historical operation logs of similar forced oil cooling systems, collecting a sample continuous working duration set, and obtaining the performance degradation ratio corresponding to different sample continuous working durations as sample performance degradation coefficients to obtain a sample performance degradation coefficient set; dividing and determining multiple continuous working duration intervals based on the sample continuous working duration set, and randomly selecting the first continuous working duration interval to extract the first sample performance degradation coefficient set covered by the first continuous working duration interval; performing anomaly removal and mean calculation on the first sample performance degradation coefficient set to obtain the mean of the first sample performance degradation coefficient; and constructing a duration-performance degradation comparison table based on the mapping relationship between the first continuous working duration interval and the mean of the first sample performance degradation coefficient.

[0079] Furthermore, the electromagnetic loss control device for power transformers in the smart grid environment is also used for: acquiring the cooling parameter adjustment space of the forced oil cooling system; randomly generating several initial cooling parameter sequences within the cooling parameter adjustment space, wherein the cooling parameters include oil pump flow rate and fan speed; performing cooling performance analysis based on the several initial cooling parameter sequences and outputting several cooling efficiency sequences; filtering the several initial cooling parameter sequences based on the several cooling efficiency sequences and constrained by satisfying the predicted cooling load sequence to obtain several qualified cooling parameter sequences; and optimizing based on the several qualified cooling parameter sequences with the goal of minimizing energy consumption and oil temperature fluctuations, and outputting the optimal cooling parameter sequence.

[0080] Furthermore, the electromagnetic loss control device for power transformers in the smart grid environment is also used for: performing energy consumption simulation and oil temperature simulation based on the multiple qualified cooling parameter sequences, and outputting multiple energy consumption values ​​and multiple oil temperature sequences; performing temperature fluctuation analysis based on the multiple oil temperature sequences to obtain multiple oil temperature fluctuation degrees, wherein the oil temperature fluctuation degree is the ratio of the standard deviation of the oil temperature to the mean of the oil temperature; evaluating and determining multiple fitness levels based on the multiple energy consumption values ​​and multiple oil temperature fluctuation degrees with the goal of minimizing energy consumption and oil temperature fluctuation, wherein the fitness level is negatively correlated with the energy consumption value and the oil temperature fluctuation degree; and performing optimization based on the multiple fitness levels and multiple qualified cooling parameter sequences to output the optimal cooling parameter sequence.

[0081] Furthermore, the power transformer electromagnetic loss control device in the smart grid environment is also used for: setting a qualified cooling parameter sequence as an initial solution; arranging the qualified cooling parameter sequences in descending order of fitness based on the multiple fitness values ​​to obtain an initial solution sequence; setting the first solution of the initial solution sequence as a superior solution and the other solutions as inferior solutions; adjusting the multiple inferior solutions according to a preset optimization step size with the superior solution as the direction to obtain multiple updated inferior solutions; sorting the superior solutions and multiple updated inferior solutions in descending order of fitness to obtain an updated solution sequence; eliminating a preset proportion of tail solutions in the updated solution sequence; and using the cooling parameter adjustment space for equivalent replenishment, wherein the preset proportion is less than 5%; performing iterative optimization until a preset number of convergences is reached; and outputting the superior solution in the current updated solution sequence as the optimal cooling parameter sequence.

[0082] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. The electromagnetic loss control method and specific examples of a power transformer in a smart grid environment described in Embodiment 1 above are also applicable to the electromagnetic loss control device of a power transformer in a smart grid environment in this embodiment. Through the foregoing detailed description of the electromagnetic loss control method of a power transformer in a smart grid environment, those skilled in the art can clearly understand the electromagnetic loss control device of a power transformer in a smart grid environment in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here. As for the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and relevant parts can be referred to in the method section.

[0083] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0084] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for controlling electromagnetic losses of power transformers in a smart grid environment, characterized in that, The methods include: The analysis yields the predicted power load sequence of the transformer within a preset future time zone, as well as the spatial temperature sequence of the region where the transformer is located. Based on the predicted power load sequence and the spatial temperature sequence, the cooling demand of the transformer is predicted, and the predicted cooling load sequence is output. The cooling parameters of the forced oil cooling device are optimized by satisfying the predicted cooling load sequence as a constraint and minimizing energy consumption and oil temperature fluctuation as the optimization objectives, and the optimal cooling parameter sequence is output. Within the preset future time zone, the forced oil cooling device is controlled to dissipate heat from the transformer according to the optimal cooling parameter sequence; The analysis obtains the predicted power load sequence of transformers within a preset future time zone, including: The power load of the transformer at P consecutive monitoring time points within a historical period is monitored to obtain the historical power load sequence. Based on the preset load fluctuation correlation factor, monitor and obtain the load fluctuation correlation data of the transformer in the preset future time zone; Based on the historical power load sequence and load fluctuation correlation data, the predicted power load sequence of the transformer in the preset future time zone is obtained. Based on the historical power load sequence and load fluctuation correlation data, the predicted power load sequence of transformers within a preset future time zone is obtained, including: Using the historical time period as a constraint, a sample power load sequence set and a sample load fluctuation association dataset of transformers within the same time period are collected, and the historical power load sequence of transformers within the historical preset time zone is obtained as a sample predicted power load sequence set. The historical time period and the historical preset time zone are continuous time periods, and the time interval of the historical preset time zone is the same as the preset future time zone. Using the sample power load sequence set and the sample load fluctuation association dataset as input, and the sample predicted power load sequence set as supervision, a long short-term memory network is trained until convergence to obtain the power load prediction model. The historical power load sequence and load fluctuation correlation data are input into the power load prediction model, and the predicted power load sequence is output.

2. The method for controlling electromagnetic losses of power transformers in a smart grid environment according to claim 1, characterized in that, Based on the predicted power load sequence and the spatial temperature sequence, the cooling demand of the transformer is predicted, and the predicted cooling load sequence is output, including: Based on the transformer's historical operating records, sample power load sequence sets and sample spatial temperature sequence sets are collected, and the historical cooling load sequences required under different sample power load sequence and sample spatial temperature sequence scenarios are obtained to obtain the sample cooling load sequence set; Using the sample power load sequence set, sample spatial temperature sequence set, and sample cooling load sequence set, a long short-term memory network is trained until convergence to obtain a cooling demand prediction model. Using the aforementioned cooling demand prediction model, cooling demand is predicted based on the predicted power load sequence and the spatial temperature sequence, and a predicted cooling load sequence is output.

3. The method for controlling electromagnetic losses of power transformers in a smart grid environment according to claim 1, characterized in that, The output predicted cooling load sequence then includes: The continuous operating time of the forced oil cooling device is obtained, and the continuous operating time sequence at the same time node of the predicted cooling load sequence is analyzed. A cooling performance degradation analysis was performed on the forced oil cooling device, and a time-performance degradation comparison table was constructed. Based on the duration-performance degradation lookup table, a performance degradation coefficient sequence is obtained by matching the continuous working duration sequence. The predicted cooling load sequence is compensated and updated based on the performance degradation coefficient sequence.

4. The method for controlling electromagnetic losses of power transformers in a smart grid environment according to claim 3, characterized in that, A cooling performance degradation analysis was performed on the forced oil cooling device, and a time-performance degradation comparison table was constructed, including: Using the attribute characteristics of the forced oil cooling device as a constraint, the historical operation logs of similar forced oil cooling devices are retrieved, a sample continuous working time set is collected, and the performance decay ratio corresponding to the continuous working time of different samples is set as the sample performance decay coefficient, thus obtaining a sample performance decay coefficient set. Based on the sample continuous working time set, multiple continuous working time intervals are determined, and a first continuous working time interval is randomly selected to extract the first sample performance degradation coefficient set covered by the first continuous working time interval. Anomaly removal and mean calculation are performed on the first sample performance degradation coefficient set to obtain the mean of the first sample performance degradation coefficient; Based on the mapping relationship between the first continuous working duration interval and the mean performance decay coefficient of the first sample, a duration-performance decay comparison table is constructed.

5. The method for controlling electromagnetic losses of power transformers in a smart grid environment according to claim 1, characterized in that, To optimize the cooling parameters of the forced oil cooling device by satisfying the predicted cooling load sequence and minimizing energy consumption and oil temperature fluctuations, the optimal cooling parameter sequence is output, including: Obtain the cooling parameter adjustment space of the forced oil cooling device, and randomly generate several initial cooling parameter sequences within the cooling parameter adjustment space, wherein the cooling parameters include oil pump flow rate and fan speed; Based on the aforementioned initial cooling parameter sequences, a cooling performance analysis is performed, and several cooling efficiency sequences are output. Based on the aforementioned cooling efficiency sequences, and constrained by the predicted cooling load sequence, the aforementioned initial cooling parameter sequences are screened to obtain multiple qualified cooling parameter sequences; With the goal of minimizing energy consumption and oil temperature fluctuations, the system optimizes the cooling parameter sequence based on the multiple qualified cooling parameter sequences and outputs the optimal cooling parameter sequence.

6. The method for controlling electromagnetic losses of power transformers in a smart grid environment according to claim 5, characterized in that, With the goal of minimizing energy consumption and oil temperature fluctuations, optimization is performed based on the aforementioned multiple qualified cooling parameter sequences, including: Based on the multiple qualified cooling parameter sequences, energy consumption simulation and oil temperature simulation are performed respectively, and multiple energy consumption values ​​and multiple oil temperature sequences are output. Temperature fluctuation analysis was performed on the multiple oil temperature sequences to obtain multiple oil temperature fluctuation degrees, wherein the oil temperature fluctuation degree is the ratio of the standard deviation of oil temperature to the mean of oil temperature. With the goal of minimizing energy consumption and oil temperature fluctuation, multiple fitness values ​​are determined based on the multiple energy consumption values ​​and multiple oil temperature fluctuation values. Among them, the fitness value is negatively correlated with the energy consumption value and the oil temperature fluctuation value. Based on the multiple fitness levels and multiple qualified cooling parameter sequences, optimization is performed to output the optimal cooling parameter sequence.

7. The method for controlling electromagnetic losses of power transformers in a smart grid environment according to claim 6, characterized in that, Based on the multiple fitness levels and multiple qualified cooling parameter sequences, optimization is performed to output the optimal cooling parameter sequence, including: The qualified cooling parameter sequence is set as the initial solution. Based on the multiple fitness values, the multiple qualified cooling parameter sequences are arranged in descending order of fitness to obtain the initial solution sequence. The first solution in the initial solution sequence is set as the optimal solution, and the other solutions are set as inferior solutions. Taking the optimal solution as the direction, the multiple inferior solutions are adjusted according to a preset optimization step size to obtain multiple updated inferior solutions. The optimal solutions and multiple updated inferior solutions are sorted according to their fitness from largest to smallest to obtain an updated solution sequence. A predetermined proportion of the tail solutions in the updated solution sequence are eliminated, and the cooling parameters are used to adjust the space for equivalent replacement. The predetermined proportion is less than 5%. Perform iterative optimization until the preset number of convergences is reached, and output the best solution in the current updated solution sequence as the optimal cooling parameter sequence.

8. A power transformer electromagnetic loss control device in a smart grid environment, characterized in that, The steps for implementing the electromagnetic loss control method for power transformers in a smart grid environment according to any one of claims 1 to 7 include: The power load forecasting module is used to analyze and obtain the predicted power load sequence of transformers in a preset future time zone, as well as the spatial temperature sequence of the area where the transformers are located. The cooling demand prediction module is used to predict the cooling demand of the transformer based on the predicted power load sequence and the space temperature sequence, and output the predicted cooling load sequence. The cooling parameter optimization module is used to optimize the cooling parameters of the forced oil cooling device by taking the predicted cooling load sequence as a constraint and minimizing energy consumption and oil temperature fluctuation as the optimization objectives, and output the optimal cooling parameter sequence. The transformer heat dissipation control module is used to control the forced oil cooling device to dissipate heat from the transformer according to the optimal cooling parameter sequence within the preset future time zone.

Images