Power grid operation risk monitoring method and device, electronic equipment and storage medium

Abstract

The invention discloses a power grid operation risk monitoring method and device, electronic equipment and a storage medium, and the method comprises the steps: calculating a three-phase imbalance evaluation index value corresponding to each three-phase imbalance evaluation index according to the real-time operation data of a distribution transformer and preset three-phase imbalance evaluation indexes, evaluating the three-phase imbalance degree of the distribution transformer according to each three-phase imbalance evaluation index value, and generating a corresponding three-phase imbalance alarm according to the three-phase imbalance degree; and calculating a load condition evaluation index value corresponding to each load condition evaluation index according to the real-time operation data and preset load condition evaluation indexes, then evaluating the load overload degree of the distribution transformer according to the load condition evaluation index values, and generating a corresponding load overload alarm according to the load overload degree. According to the invention, the accuracy of power grid operation risk monitoring and evaluation can be improved.

Description

Technical Field

[0001] This invention relates to the field of power grid operation risk monitoring technology, and in particular to a power grid operation risk monitoring method, device, electronic equipment and storage medium. Background Technology

[0002] With the rapid development of new energy power grids, distribution transformers, as key equipment in the power grid, directly affect the stability and power supply quality of the grid. New energy power generation, such as wind and solar power, is affected by natural conditions such as wind speed and sunshine, exhibiting significant randomness and volatility. With the large-scale integration of new energy sources, the operating environment of the power grid becomes more complex. The randomness and volatility of new energy power generation necessitate real-time assessment of the operational risks of distribution transformers to ensure grid stability and power supply quality. However, traditional power grid operation risk assessment and monitoring methods are generally designed for traditional thermal and hydropower power generation, failing to fully consider the operational risks of new energy power grids, such as three-phase imbalance and heavy overload, thus limiting the accuracy and applicability of risk assessments. Summary of the Invention

[0003] This invention provides a method, device, electronic equipment, and storage medium for monitoring power grid operation risks, in order to solve the technical problem that traditional power grid operation risk assessment and monitoring methods are generally designed for traditional thermal and hydropower, and fail to fully consider the operational risks of new energy power grids such as three-phase imbalance and heavy overload, resulting in limited accuracy and applicability of risk assessment.

[0004] To address the aforementioned technical problems, embodiments of the present invention provide a method for monitoring power grid operation risks, comprising:

[0005] Acquire real-time operating data of the distribution transformer; wherein the real-time operating data includes: current, voltage, and power;

[0006] Based on the real-time operating data and the preset three-phase imbalance assessment indicators, the three-phase imbalance assessment indicator value corresponding to each three-phase imbalance assessment indicator is calculated. Then, the degree of three-phase imbalance of the distribution transformer is assessed based on the value of each three-phase imbalance assessment indicator, and a corresponding three-phase imbalance alarm is generated based on the degree of three-phase imbalance. The three-phase imbalance assessment indicators include: imbalance degree, negative sequence current ratio, and zero sequence current.

[0007] Acquire temperature data collected by internal sensors of the distribution transformer; wherein the temperature data includes: winding temperature and oil temperature;

[0008] Based on the real-time operating data, temperature data, and preset load condition evaluation indicators, the load condition evaluation indicator values ​​corresponding to each load condition evaluation indicator are calculated. Then, the overload degree of the distribution transformer is evaluated based on the load condition evaluation indicator values, and a corresponding overload alarm is generated based on the overload degree. The load condition evaluation indicators include: load rate, capacity utilization rate, winding temperature, oil temperature, overload duration, and load change response time.

[0009] As a preferred embodiment, before calculating the three-phase imbalance evaluation index value corresponding to each three-phase imbalance evaluation index based on the real-time operating data and the preset three-phase imbalance evaluation index, the method further includes:

[0010] Obtain output power data of new energy power generation;

[0011] Based on the real-time operating data of the distribution transformer and the output power data, using the real-time operating data of the distribution transformer as input and the output power data of the new energy power generation as output, a linear expression between the real-time operating data and the output power data is constructed, and then the correlation between the real-time operating data and the output power data is evaluated based on the linear expression.

[0012] As a preferred embodiment, before calculating the three-phase imbalance evaluation index value corresponding to each three-phase imbalance evaluation index based on the real-time operating data and the preset three-phase imbalance evaluation index, the method further includes:

[0013] Obtain the rated parameters of the distribution transformer, and determine the reference load capacity value of the distribution transformer based on the rated parameters; wherein, the rated parameters include: rated current, rated voltage and rated power;

[0014] The real-time operating data of the distribution transformer is normalized, and the weighting coefficients corresponding to each real-time operating data are obtained.

[0015] Based on the weighting coefficients corresponding to each real-time operating data, a weighted summation is performed on each real-time operating data to obtain the corresponding load capacity assessment value. Then, the load capacity assessment value is compared with the benchmark load capacity value, and the current load capacity of the distribution transformer is assessed based on the comparison results.

[0016] As a preferred embodiment, the step of assessing the degree of three-phase imbalance of the distribution transformer based on the three-phase imbalance assessment index values, and generating a corresponding three-phase imbalance alarm based on the degree of three-phase imbalance, includes:

[0017] Based on the current load capacity of the distribution transformer, obtain the corresponding three-phase imbalance alarm threshold; wherein, the three-phase imbalance alarm threshold includes: imbalance degree alarm threshold, negative sequence current ratio alarm threshold and zero sequence current alarm threshold.

[0018] The values ​​of each of the three-phase imbalance assessment indicators are compared with the corresponding three-phase imbalance alarm thresholds to determine the degree of three-phase imbalance of the distribution transformer; wherein the degree of three-phase imbalance includes: mild, moderate and severe.

[0019] When the three-phase imbalance of the distribution transformer is slight, a corresponding slight three-phase imbalance alarm is generated; when the three-phase imbalance of the distribution transformer is moderate, a corresponding moderate three-phase imbalance alarm is generated; when the three-phase imbalance of the distribution transformer is severe, a corresponding severe three-phase imbalance alarm is generated.

[0020] As a preferred embodiment, the step of assessing the overload degree of the distribution transformer based on the load condition evaluation index value, and generating a corresponding overload alarm based on the overload degree, includes:

[0021] Based on the current load capacity of the distribution transformer, obtain the corresponding overload alarm threshold;

[0022] Obtain the weight coefficients corresponding to each load condition assessment index, and calculate the weighted sum of the values ​​of each load condition assessment index according to the weight coefficients corresponding to each load condition assessment index to obtain the corresponding load overload assessment value.

[0023] The overload assessment value is compared with the overload alarm threshold to determine the degree of overload of the distribution transformer; wherein, the degree of three-phase imbalance includes: light overload, medium overload and heavy overload.

[0024] When the overload level of the distribution transformer is light overload, a corresponding light overload alarm is generated; when the overload level of the distribution transformer is medium overload, a corresponding medium overload alarm is generated; and when the overload level of the distribution transformer is heavy overload, a corresponding heavy overload alarm is generated.

[0025] As a preferred option, it also includes:

[0026] When the load overload level is severe overload, the real-time operating data of the distribution transformer is input into a preset management strategy generation model, so that the management strategy generation model generates and outputs a severe overload management strategy for the distribution transformer based on the real-time operating data of the distribution transformer.

[0027] The governance strategy parameters in the load overload governance strategy are encoded into several chromosomes. The merits of the governance strategy parameters corresponding to each chromosome are evaluated according to a preset fitness function. The chromosome population is then evolved based on the evaluation results to obtain the optimal combination of governance strategy parameters. The load overload governance strategy is then optimized based on the combination of governance strategy parameters.

[0028] The governance strategy generation model is obtained by training a preset neural network model with historical operating data of the distribution transformer as input and the overload governance strategy corresponding to the historical operating data as output.

[0029] As a preferred option, it also includes:

[0030] Obtain weather forecast information for the area where the distribution transformer is located; wherein, the weather forecast information includes: wind speed, solar radiation intensity, and cloud thickness;

[0031] The weather forecast information and the real-time operating data are input into a preset load prediction model so that the load prediction model can predict the future load of the distribution transformer based on the weather forecast information and the real-time operating data, output the future load prediction value of the distribution transformer, and then analyze the possible future operating risks of the distribution transformer based on the load prediction value.

[0032] The load prediction model is obtained by training a preset LSTM model with historical operating data of the distribution transformer and historical weather forecast information as input and corresponding historical load prediction values ​​as output.

[0033] Based on the above embodiments, another embodiment of the present invention provides a power grid operation risk monitoring device, including: a real-time operation data acquisition module, a three-phase imbalance alarm module, a temperature data acquisition module, and a load overload alarm module;

[0034] The real-time operation data acquisition module is used to acquire real-time operation data of the distribution transformer; wherein, the real-time operation data includes: current, voltage and power;

[0035] The three-phase imbalance alarm module is used to calculate the three-phase imbalance assessment index value corresponding to each three-phase imbalance assessment index based on the real-time operating data and preset three-phase imbalance assessment indexes, and then assess the degree of three-phase imbalance of the distribution transformer based on each of the three-phase imbalance assessment index values, and generate a corresponding three-phase imbalance alarm based on the degree of three-phase imbalance; wherein, the three-phase imbalance assessment indexes include: imbalance degree, negative sequence current ratio, and zero sequence current;

[0036] The temperature data acquisition module is used to acquire temperature data collected by internal sensors of the distribution transformer; wherein, the temperature data includes: winding temperature and oil temperature;

[0037] The overload alarm module is used to calculate the load condition assessment index value corresponding to each load condition assessment index based on the real-time operating data, temperature data, and preset load condition assessment indexes, and then assess the overload degree of the distribution transformer based on the load condition assessment index value, and generate a corresponding overload alarm based on the overload degree; wherein, the load condition assessment indexes include: load rate, capacity utilization rate, winding temperature, oil temperature, overload duration, and load change response time.

[0038] Based on the above embodiments, another embodiment of the present invention provides an electronic device, the device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the power grid operation risk monitoring method described in the above embodiments of the invention.

[0039] Based on the above embodiments, another embodiment of the present invention provides a storage medium, the storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the storage medium is located to execute the power grid operation risk monitoring method described in the above embodiments of the invention.

[0040] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0041] This invention provides a method for monitoring power grid operation risks, which involves acquiring real-time operating data of a distribution transformer; calculating the three-phase imbalance assessment index value corresponding to each three-phase imbalance assessment index based on the real-time operating data and preset three-phase imbalance assessment indexes; assessing the degree of three-phase imbalance of the distribution transformer based on the three-phase imbalance assessment index values; generating a corresponding three-phase imbalance alarm based on the degree of three-phase imbalance; acquiring temperature data collected by internal sensors of the distribution transformer; calculating the load condition assessment index value corresponding to each load condition assessment index based on the real-time operating data, temperature data, and preset load condition assessment indexes; assessing the degree of load overload of the distribution transformer based on the load condition assessment index values; and generating a corresponding load overload alarm based on the degree of load overload. This invention can fully consider the operational risks of new energy power grids, such as three-phase imbalance and load overload. It can monitor the three-phase imbalance and load overload of the new energy power grid in real time based on the real-time operating data of the distribution transformer, and generate corresponding three-phase imbalance alarms and load overload alarms based on the degree of three-phase imbalance and the degree of load overload, thereby improving the accuracy of power grid operation risk monitoring and assessment. Attached Figure Description

[0042] Figure 1 This is a flowchart illustrating a power grid operation risk monitoring method according to an embodiment of the present invention;

[0043] Figure 2 This is a schematic diagram of the structure of a power grid operation risk monitoring device provided in an embodiment of the present invention. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0046] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0047] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0048] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0049] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0050] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0051] Example 1

[0052] Please refer to Figure 1 The following is a flowchart illustrating a power grid operation risk monitoring method according to an embodiment of the present invention, comprising the following specific steps:

[0053] S1. Obtain real-time operating data of the distribution transformer; wherein, the real-time operating data includes: current, voltage, and power;

[0054] Preferably, before calculating the three-phase imbalance assessment index value corresponding to each three-phase imbalance assessment index based on the real-time operating data and the preset three-phase imbalance assessment index, the method further includes: acquiring the output power data of the new energy power generation; constructing a linear expression between the real-time operating data of the distribution transformer and the output power data, using the real-time operating data of the distribution transformer as input and the output power data of the new energy power generation as output, and then evaluating the correlation between the real-time operating data and the output power data based on the linear expression.

[0055] Preferably, before calculating the three-phase imbalance assessment index value corresponding to each three-phase imbalance assessment index based on the real-time operating data and the preset three-phase imbalance assessment index, the method further includes: obtaining the rated parameters of the distribution transformer and determining the reference load capacity value of the distribution transformer based on the rated parameters; wherein, the rated parameters include: rated current, rated voltage, and rated power; normalizing the real-time operating data of the distribution transformer and obtaining the weight coefficient corresponding to each real-time operating data; performing a weighted summation calculation on each real-time operating data according to the weight coefficient corresponding to each real-time operating data to obtain the corresponding load capacity assessment value; then comparing the load capacity assessment value with the reference load capacity value, and assessing the current load capacity of the distribution transformer based on the comparison result.

[0056] Specifically, the power grid operation risk monitoring method of the present invention includes the following steps:

[0057] Step S1: Monitor the operating status of the distribution transformer in real time through the distribution transformer operation monitoring module.

[0058] Step S2: Set up a central control module to receive and aggregate monitoring information from each distribution transformer in the power grid fed back by the distribution transformer operation monitoring module, and perform comprehensive analysis and processing on the collected information:

[0059] Step S2-1: Classify and organize the received monitoring information, distinguishing different types of data. The monitoring information includes the operating parameters of the distribution transformer and the output power data of new energy power generation.

[0060] Step S2-2: Establish a data analysis model, conduct correlation analysis on various types of data, and find the potential relationship between the operating parameters of the distribution transformer and the output power data of new energy power generation.

[0061] In step S2-2 above, the specific implementation method is as follows: Establish a data analysis model: Use a multiple linear regression model as the data analysis model. This model is based on the operating parameters of the distribution transformer (such as voltage, current, power factor, etc.) and the output power data of new energy power generation to construct a linear relationship expression between them.

[0062] Let the operating parameter vector of the distribution transformer be X = [x1, x2, ..., x...]. n (where x) i Let x1 be the voltage, x2 be the current, etc., and let P be the output power of the new energy power generation. The model can be expressed as P = β0 + β1X1 + β2X2 + ... + β n X n +∈, where P is the predicted output power of new energy power generation, β i denoted as the regression coefficient to be estimated, and ∈ represents the error term.

[0063] The training process of the model is as follows:

[0064] A large amount of historical data on the operating parameters of distribution transformers and the output power of new energy power generation were collected as training datasets.

[0065] The operating parameters of the distribution transformers in the training dataset are used as input X, and the corresponding actual power grid operating status related indicators (such as actual total power demand) are used as output Y.

[0066] The regression coefficient β is continuously adjusted using optimization algorithms such as the least squares method. iThis minimizes the sum of squared errors between the model's predicted value Y and the actual value, thus completing the model training.

[0067] The data analysis model performs correlation analysis on the data: the regression coefficients obtained through model training reflect the correlation between data. A larger absolute value indicates that the corresponding operating parameter has a significant impact on the output (indicators related to the power grid's operating status), meaning the correlation is strong; conversely, a smaller value indicates a weaker correlation. For example, a larger value (corresponding to voltage) indicates that voltage has a significant impact on indicators related to the power grid's operating status (such as power demand), and voltage changes will cause significant changes in power demand.

[0068] Step S3: Set up a distribution transformer load capacity assessment module to assess the load capacity of each distribution transformer connected to the power grid based on the monitoring information fed back to the central control module.

[0069] Step S3-1: Collect the model and actual operating data of the distribution transformer through the distribution transformer operation monitoring module. The actual operating data includes current, voltage and power.

[0070] Step S3-2: Combining real-time monitored operating data and fluctuations in the output power of new energy power generation, a comprehensive evaluation algorithm is used to determine the current load capacity of each distribution transformer. The comprehensive evaluation algorithm employs a weighted calculation method. First, based on the rated parameters of the distribution transformer, such as rated current, rated voltage, and rated power, a baseline load capacity value is determined. Then, the real-time monitored current, voltage, and power data are normalized to ensure comparability with the rated parameters. Next, weighting coefficients are assigned to current, voltage, and power respectively; for example, the current weighting coefficient is 0.4, the voltage weighting coefficient is 0.3, and the power weighting coefficient is 0.3. The normalized current, voltage, and power values ​​are multiplied by their respective weighting coefficients and then summed to obtain a load capacity assessment value. This assessment value is compared with the baseline load capacity value to determine the proportion of each distribution transformer's current load capacity to its rated load capacity, thereby evaluating the current load capacity.

[0071] Step S3-3: Regularly update the data and reassess the current load capacity of each distribution transformer.

[0072] S2. Based on the real-time operating data and the preset three-phase imbalance assessment indicators, calculate the three-phase imbalance assessment indicator value corresponding to each three-phase imbalance assessment indicator, then assess the degree of three-phase imbalance of the distribution transformer based on each of the three-phase imbalance assessment indicator values, and generate a corresponding three-phase imbalance alarm based on the degree of three-phase imbalance; wherein, the three-phase imbalance assessment indicators include: imbalance degree, negative sequence current ratio, and zero sequence current;

[0073] Preferably, the step of assessing the degree of three-phase imbalance of the distribution transformer based on the three-phase imbalance assessment index values ​​and generating a corresponding three-phase imbalance alarm based on the degree of three-phase imbalance includes: obtaining a corresponding three-phase imbalance alarm threshold based on the current load capacity of the distribution transformer; wherein, the three-phase imbalance alarm threshold includes: an imbalance degree alarm threshold, a negative sequence current ratio alarm threshold, and a zero sequence current alarm threshold; comparing each of the three-phase imbalance assessment index values ​​with the corresponding three-phase imbalance alarm threshold to determine the degree of three-phase imbalance of the distribution transformer; wherein, the degree of three-phase imbalance includes: mild, moderate, and severe; when the degree of three-phase imbalance of the distribution transformer is mild, a corresponding mild three-phase imbalance alarm is generated; when the degree of three-phase imbalance of the distribution transformer is moderate, a corresponding moderate three-phase imbalance alarm is generated; and when the degree of three-phase imbalance of the distribution transformer is severe, a corresponding severe three-phase imbalance alarm is generated.

[0074] Step S4: Set up a three-phase imbalance alarm module for the distribution transformer to monitor the operation of the distribution transformer, assess the degree of three-phase imbalance, and trigger an alarm when the degree of three-phase imbalance exceeds the alarm threshold.

[0075] Step S4-1: Determine the evaluation indicators for three-phase imbalance, including the degree of imbalance, the proportion of negative sequence current, and the zero sequence current;

[0076] Step S4-2: Determine the threshold for triggering the alarm; different devices have different load capacities, and therefore different alarm trigger thresholds. The higher the load capacity, the higher the alarm trigger threshold.

[0077] Step S4-3: The three-phase current and voltage data of the distribution transformer are monitored in real time through the distribution transformer operation monitoring module, and various evaluation indicators are calculated to quantitatively evaluate the degree of three-phase imbalance.

[0078] Step S4-4: Set multi-level alarm thresholds and issue different levels of alarm information according to the severity of the three-phase imbalance. The severity of the three-phase imbalance is divided into three levels: mild, moderate, and severe. Mild imbalance: The imbalance is between 10% and 20%, the negative sequence current is between 5% and 10%, and the zero sequence current is in a small range. At this time, a level 1 alarm information is issued to remind maintenance personnel to pay attention. Moderate imbalance: The imbalance is between 20% and 30%, the negative sequence current is between 10% and 15%, and the zero sequence current has increased. A level 2 alarm information is issued, requiring maintenance personnel to conduct a preliminary inspection. Severe imbalance: The imbalance is greater than 30%, the negative sequence current is greater than 15%, and the zero sequence current is large. A level 3 alarm information is issued, and immediate measures must be taken to adjust the grid operation status.

[0079] Step S4-5: When the imbalance index exceeds the preset threshold, an alarm message is sent to the central control module. The alarm message includes the specific degree of imbalance and the possible range of impact. The specific degree of imbalance is determined by the imbalance degree, negative sequence current ratio and zero sequence current value calculated above. The possible range of impact is determined by analyzing the lines connected to the distribution transformer, the load distribution and the power grid topology. For example, by calculating the impedance of the connecting lines and statistically analyzing the load power distribution, the area where the imbalance may cause large voltage fluctuations and the range of equipment that may be overloaded are estimated.

[0080] Steps S4-6: The central control module monitors and processes alarm information in real time, generates an alarm list and saves the records, and takes measures to adjust the power grid operating status. The alarm list includes alarm time, equipment information, alarm type, alarm details, and severity. Equipment information includes the number, model, and location of the distribution transformer. Alarm details include the specific values ​​of three-phase current and voltage, the unbalance degree, the proportion of negative sequence current, and the calculation results of zero sequence current. The measures to adjust the power grid operating status are as follows: For mild unbalance, the three-phase load distribution can be adjusted, such as transferring some single-phase loads from the heavier phase to the lighter phase. For moderate unbalance, in addition to adjusting the load, the transformer taps can be adjusted appropriately to change the output voltage and improve the unbalance. For severe unbalance, some non-critical loads need to be disconnected, or the backup power supply or reactive power compensation device needs to be started to stabilize the power grid voltage and current.

[0081] S3. Acquire temperature data collected by internal sensors of the distribution transformer; wherein, the temperature data includes: winding temperature and oil temperature;

[0082] S4. Based on the real-time operating data, temperature data, and preset load condition evaluation indicators, calculate the load condition evaluation indicator value corresponding to each load condition evaluation indicator, and then evaluate the overload degree of the distribution transformer based on the load condition evaluation indicator value, and generate a corresponding overload alarm based on the overload degree; wherein, the load condition evaluation indicators include: load rate, capacity utilization rate, winding temperature, oil temperature, overload duration, and load change response time.

[0083] Preferably, the step of assessing the overload degree of the distribution transformer based on the load condition evaluation index value and generating a corresponding overload alarm based on the overload degree includes: obtaining a corresponding overload alarm threshold based on the current load capacity of the distribution transformer; obtaining the weight coefficients corresponding to each load condition evaluation index, and performing a weighted summation calculation on the values ​​of each load condition evaluation index based on the weight coefficients corresponding to each load condition evaluation index to obtain a corresponding overload evaluation value; comparing the overload evaluation value with the overload alarm threshold value respectively to determine the overload degree of the distribution transformer; wherein, the three-phase imbalance degree includes: light overload, medium overload, and heavy overload; when the overload degree of the distribution transformer is light overload, a corresponding light overload alarm is generated; when the overload degree of the distribution transformer is medium overload, a corresponding medium overload alarm is generated; and when the overload degree of the distribution transformer is heavy overload, a corresponding heavy overload alarm is generated.

[0084] Step S5: Set up the distribution transformer overload intelligent early warning module to monitor the operation of the distribution transformer, perform real-time monitoring and dynamic prediction of the load, and trigger an alarm when the load exceeds the threshold.

[0085] Step S5-1: Establish a real-time monitoring system to monitor the operation of distribution transformers in real time. Based on the detection data of each distribution transformer, evaluate the load condition of each transformer. The load condition evaluation indicators include: load factor, capacity utilization rate, winding temperature, oil temperature, overload duration, and load change response time. A comprehensive evaluation score reflecting the load condition is derived from these indicators. The detection data of the distribution transformers includes real-time operating data such as current, voltage, and power obtained through the distribution transformer operation monitoring module, as well as data such as winding temperature and oil temperature detected by internal sensors. The method for calculating and evaluating the load condition of each distribution transformer is as follows: Load factor = Actual Load power / rated power; capacity utilization rate = actual load capacity / rated capacity; winding temperature and oil temperature are directly obtained from their monitoring values; overload duration is obtained by accumulating the time the load exceeds the rated value; load change response time is obtained by monitoring the load change rate and calculating its average value over a certain period of time; the evaluation score reflecting the load condition is obtained by combining various indicators using a weighted summation method. For example, the weight of load rate is 0.3, capacity utilization rate is 0.2, winding temperature is 0.2, oil temperature is 0.1, overload duration is 0.1, and load change response time is 0.1. The evaluation score is obtained by multiplying each indicator value by its corresponding weight and then adding them together.

[0086] Step S5-2: Set multiple warning thresholds and classify the load level into light overload, medium overload, and heavy overload according to the evaluation score. Issue different warning messages according to the different load levels. The warning thresholds are set according to the different load capacities of each distribution transformer as evaluated by the distribution transformer load capacity evaluation module. Distribution transformers with higher load capacities have higher warning thresholds. Light overload: Evaluation score between 60-70, issue a warning message to prompt maintenance personnel to pay attention to the load change trend; Medium overload: Evaluation score between 70-85, issue a warning message requiring maintenance personnel to prepare measures to adjust the load; Heavy overload: Evaluation score greater than 85, issue an emergency warning message, and emergency measures need to be initiated immediately.

[0087] Step S5-3: When a severe overload is detected, emergency measures are initiated simultaneously with the issuance of a warning message. Emergency measures include: prioritizing the disconnection of non-critical loads, such as some air conditioning and lighting equipment; limiting power to critical loads, such as reducing the power output of certain industrial equipment; if a backup transformer is available, load transfer can be implemented, switching some loads to the backup transformer; simultaneously, monitoring of the distribution transformer is strengthened, closely monitoring changes in winding temperature and oil temperature to prevent damage to the equipment due to overheating.

[0088] Preferably, the method further includes: when the load overload level is severe overload, inputting the real-time operating data of the distribution transformer into a preset management strategy generation model, so that the management strategy generation model generates and outputs a severe overload management strategy for the distribution transformer based on the real-time operating data of the distribution transformer; encoding the management strategy parameters in the severe overload management strategy into several chromosomes, evaluating the merits of the management strategy parameters corresponding to each chromosome according to a preset fitness function, and evolving the chromosome population based on the evaluation results to obtain the optimal combination of management strategy parameters, and then optimizing the severe overload management strategy based on the combination of management strategy parameters; wherein, the management strategy generation model is obtained by training a preset neural network model with the historical operating data of the distribution transformer as input and the severe overload management strategy corresponding to the historical operating data as output.

[0089] Preferably, the method further includes: acquiring weather forecast information for the area where the distribution transformer is located; wherein the weather forecast information includes wind speed, solar radiation intensity, and cloud thickness; inputting the weather forecast information and the real-time operating data into a preset load prediction model, so that the load prediction model predicts the future load of the distribution transformer based on the weather forecast information and the real-time operating data, outputs a future load prediction value for the distribution transformer, and then analyzes the possible future operational risks of the distribution transformer based on the load prediction value; wherein the load prediction model is obtained by training a preset LSTM model with the historical operating data and historical weather forecast information of the distribution transformer as input and the corresponding historical load prediction value as output.

[0090] Step S6: Set up an intelligent generation module for managing distribution transformer overload mobile support. When a distribution transformer is overloaded, generate a management strategy that adapts to the actual needs of the power grid based on the grid's operating status and send it to the central control module.

[0091] Step S6-1: When the central control module detects a severe overload state in the distribution transformer of the power grid, it initiates emergency measures to trigger the governance strategy generation program;

[0092] Step S6-2: Establish a governance strategy generation model, comprehensively considering the power grid operating status and demand; the governance strategy generation model adopts a neural network model. The training process of the model is as follows:

[0093] A large amount of data on distribution transformer overload under different power grid operating conditions (including different load distributions, renewable energy generation ratios, line impedance, etc.) and corresponding effective governance strategies are collected as training set model inputs. The inputs include real-time power grid operating parameters, such as the load status of each distribution transformer, renewable energy generation power, line current and voltage, etc.; the outputs are governance strategies for the current state, such as load adjustment schemes and reactive power compensation schemes. Through repeated learning on the training set, the weights and thresholds of the neural network are adjusted, enabling the model to accurately generate appropriate governance strategies based on the input power grid operating conditions.

[0094] Step S6-3: Optimize governance strategies using intelligent algorithms to improve governance effectiveness;

[0095] The intelligent algorithm can use a genetic algorithm to optimize the governance strategy. First, the parameters of the governance strategy are encoded into chromosomes, such as load adjustment ratio and reactive power compensation capacity, which are encoded in binary. Then, the merits of the governance strategy corresponding to each chromosome are evaluated according to a set fitness function, which can be constructed based on indicators such as the stability of the power grid and power loss after governance. Through genetic operations such as selection, crossover, and mutation, the chromosome population is continuously evolved to find the optimal combination of governance strategy parameters, thereby optimizing the governance strategy.

[0096] Step S6-4: Evaluate and verify the generated governance strategy to ensure that it meets the actual needs of the power grid.

[0097] The evaluation and verification process is as follows: The generated governance strategy is simulated in the power grid simulation model to observe whether the various operating indicators of the power grid after the implementation of the strategy, such as voltage stability, power balance, and equipment load, are improved; at the same time, the actual governance effect data under similar power grid operating conditions in history is compared and analyzed. If all indicators meet the requirements and are better than historical data, the governance strategy is considered to be suitable for the actual needs of the power grid; otherwise, the model or strategy is adjusted and re-evaluated.

[0098] Step S7: Set up the prediction module, establish a load prediction model to address the randomness and volatility of new energy sources, predict the time when three-phase imbalance alarms and heavy overload warnings may be triggered in the future, and continuously optimize the load prediction model using updated grid data.

[0099] Step S7-1: Establish a stable data connection channel with the weather forecasting system and regularly obtain accurate weather forecast information for each region, including key meteorological data that may affect new energy power generation, such as wind speed, solar radiation intensity, and cloud thickness.

[0100] Step S7-2: Collect the location information of the new energy power generation devices connected to each distribution transformer, establish a location database, and mark the geographic information to facilitate subsequent analysis of the differences in the impact of new energy power generation at different locations on the distribution transformer.

[0101] Step S7-3: Determine the type of new energy power generation device connected to each distribution transformer and determine the associated meteorological data;

[0102] Step S7-4: Combining weather forecast information, the location and type of new energy power generation devices, analyze the changing trends of power generation characteristics of different types of power generation devices under different meteorological conditions, providing basic data support for establishing a load prediction model. For solar power generation devices, analyze the changing trends of their power generation capacity based on solar radiation intensity and cloud thickness. The stronger the solar radiation intensity, the higher the power generation capacity; increased cloud thickness leads to a decrease in power generation capacity. Describe the changes in power generation characteristics by establishing a functional relationship between solar radiation intensity and power generation capacity, as well as a model of the attenuation coefficient of power generation capacity due to cloud thickness. For wind power generation devices, analyze the changes in power generation capacity based on wind speed. Generally, when the wind speed is between the cut-off speed and the rated wind speed, the power generation capacity increases with increasing wind speed. Establish a piecewise functional relationship between wind speed and power generation capacity to reflect its characteristic changes. Then, comprehensively analyze the power generation characteristics of solar and wind power generation devices in different locations under different meteorological conditions, and analyze the trend of their impact on the load of distribution transformers. For example, in a certain area with high wind speed and good solar energy resources, the load of distribution transformers in that area may change due to the increase in new energy power generation capacity.

[0103] Step S7-5: Based on the collected and analyzed data, construct an initial prediction model, fully considering the randomness and volatility of new energy sources, as well as the impact of location, type, and other factors on the load. The input to the prediction model is weather forecast information and power grid operation data. A Long Short-Term Memory (LSTM) network is used to construct the prediction model. The training process of the model is as follows: Collect historical weather forecast information and power grid operation data (including distribution transformer load status, new energy power generation, etc.) as the training set. Preprocess and perform feature engineering on data such as wind speed and solar radiation intensity from the weather forecast information, as well as current load and new energy power generation data from the power grid operation data, such as normalization and time series feature extraction. Then, input the processed feature data into the LSTM network for training. Adjust the network weights and biases through the backpropagation algorithm so that the model can predict future load conditions based on the input data. The model output is the load prediction value for a future period of time.

[0104] Step S7-6: Use real-time updated grid data, including the actual output power of new energy power generation and the real-time load status of distribution transformers, to adjust and optimize the parameters of the load prediction model and improve the accuracy of the model.

[0105] Further, step S7-6 includes the following sub-steps:

[0106] Step S7-6-1: Use the optimized load prediction model to make preliminary predictions on the possible times when three-phase imbalance alarms and heavy overload warnings may be triggered in the future;

[0107] Step S7-6-2: Without intervention, compare and verify the prediction results with the actual power grid operation. Further adjust and improve the load prediction model based on the error situation. The method for adjusting and improving the load prediction model based on the error situation is as follows: Calculate the error index between the predicted value and the actual value, such as mean square error (MSE) and mean absolute error (MAE); if the error is large, analyze the cause of the error, such as inaccurate meteorological data prediction or sudden changes in power grid operation status; for errors related to meteorological data, a meteorological data correction mechanism can be added, such as adjusting the predicted meteorological data according to actual meteorological changes and then re-inputting it into the model; for errors caused by sudden changes in power grid operation status, a module for detecting and handling sudden events in the power grid can be added, considering the impact of sudden events on the load in the model, such as adding a load mutation factor to the prediction model, learning and adjusting based on historical load mutation data to improve the model's ability to predict sudden events;

[0108] Step S7-6-3: Continuously monitor the updated information of the weather forecast system and the changes in the location and type of new energy power generation devices. At the same time, combine the constantly updated power grid data to regularly re-evaluate and optimize the load forecasting model to ensure that the model always adapts to rapidly changing load conditions and continuously evaluate the forecast accuracy.

[0109] Step S7-6-4: After the prediction accuracy reaches the expected level, the prediction result is sent to the intelligent generation module for the management strategy of the distribution transformer overload mobile support. The intelligent generation module for the management strategy of the distribution transformer overload mobile support will adjust the power grid in advance according to the prediction result.

[0110] Therefore, the present invention provides a method for monitoring power grid operation risks, and the present invention can achieve the following beneficial effects:

[0111] (1) Improve the accuracy of assessment: In view of the characteristics of the new energy power grid, a multi-module collaborative working method is adopted to comprehensively consider the load capacity assessment of distribution transformers, three-phase imbalance alarm, intelligent early warning of heavy overload, and generation of mobile support governance strategies. This overcomes the shortcomings of traditional assessment methods that rely on simplified models and empirical formulas, and can more accurately reflect the load characteristics of transformers in actual operation, reducing the deviation between assessment results and actual conditions. By determining detailed three-phase imbalance assessment indicators, such as imbalance degree, negative sequence current ratio and zero sequence current, and conducting quantitative assessment and multi-level alarms, accurate alarm information is provided for power grid operation, which helps to discover and solve three-phase imbalance problems in a timely manner and improve power quality. In terms of intelligent early warning of heavy overload of distribution transformers, a real-time monitoring system and dynamic prediction model are established. Combined with multiple load condition assessment indicators, it can quickly respond to and effectively prevent heavy overload conditions, avoiding the lag caused by relying on static data and post-event analysis.

[0112] (2) Enhancing power grid stability and power supply quality: Real-time monitoring of the operating status of distribution transformers can promptly identify potential problems and take corresponding measures, effectively ensuring the stable operation of the power grid. For example, when a three-phase imbalance or heavy overload is detected, the central control module can quickly generate an alarm list and take adjustment measures to reduce the risk of equipment damage and improve the reliability of the power grid. Through an accurate load prediction model, considering the randomness and volatility of new energy sources as well as the impact of factors such as location and type on the load, it can better adapt to rapidly changing load conditions, providing strong support for power grid scheduling and planning, thereby improving power supply quality. The intelligent generation module for the distribution transformer heavy overload mobile support governance strategy can generate effective governance strategies according to the actual needs of the power grid, improve governance effectiveness, and further enhance the stability of the power grid and the power supply quality.

[0113] (3) Enhance the adaptability of the new energy power grid: Establish a connection with the weather forecast system, collect information on the location and type of new energy power generation devices, analyze the changing trends of power generation characteristics of power generation devices under different meteorological conditions, so that the evaluation method can fully consider the volatility and uncertainty of new energy and improve the adaptability to the new energy power grid; optimize the generation of load forecasting and governance strategies based on the characteristics of new energy power generation, so as to better cope with the changes in the power grid operating environment brought about by the large-scale access of new energy and provide a guarantee for the efficient utilization of new energy and the sustainable development of the power grid.

[0114] (4) Improve management efficiency and scientific decision-making: Data interaction and collaborative work between various modules provide power grid managers with comprehensive and accurate information, which helps to improve management efficiency. For example, the alarm list generation and record saving function makes it convenient for managers to quickly understand the power grid operation status and take timely measures; the application of load forecasting models and governance strategy generation models provides a scientific basis for power grid planning, scheduling and maintenance, making decisions more reasonable and effective, and reducing power grid operation risks and costs.

[0115] Example 2

[0116] Please refer to Figure 2 This is a schematic diagram of the structure of a power grid operation risk monitoring device according to an embodiment of the present invention. The device includes: a real-time operation data acquisition module, a three-phase imbalance alarm module, a temperature data acquisition module, and a load overload alarm module.

[0117] The real-time operation data acquisition module is used to acquire real-time operation data of the distribution transformer; wherein, the real-time operation data includes: current, voltage and power;

[0118] The three-phase imbalance alarm module is used to calculate the three-phase imbalance assessment index value corresponding to each three-phase imbalance assessment index based on the real-time operating data and preset three-phase imbalance assessment indexes, and then assess the degree of three-phase imbalance of the distribution transformer based on each of the three-phase imbalance assessment index values, and generate a corresponding three-phase imbalance alarm based on the degree of three-phase imbalance; wherein, the three-phase imbalance assessment indexes include: imbalance degree, negative sequence current ratio, and zero sequence current;

[0119] The temperature data acquisition module is used to acquire temperature data collected by internal sensors of the distribution transformer; wherein, the temperature data includes: winding temperature and oil temperature;

[0120] The overload alarm module is used to calculate the load condition assessment index value corresponding to each load condition assessment index based on the real-time operating data, temperature data, and preset load condition assessment indexes, and then assess the overload degree of the distribution transformer based on the load condition assessment index value, and generate a corresponding overload alarm based on the overload degree; wherein, the load condition assessment indexes include: load rate, capacity utilization rate, winding temperature, oil temperature, overload duration, and load change response time.

[0121] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0122] Those skilled in the art will clearly understand that, for convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0123] Example 3

[0124] Accordingly, embodiments of the present invention provide an electronic device, the device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the power grid operation risk monitoring method described in the above embodiments of the invention.

[0125] The electronic device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The device may include, but is not limited to, a processor and a memory.

[0126] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the device, connecting various parts of the device via various interfaces and lines.

[0127] Example 4

[0128] Accordingly, embodiments of the present invention provide a storage medium, the storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the storage medium is located to execute the power grid operation risk monitoring method described in the above embodiments of the invention.

[0129] The memory can be used to store the computer program. The processor implements various functions of the device by running or executing the computer program stored in the memory and calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0130] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0131] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for monitoring power grid operation risk, characterized in that: include: Acquire real-time operating data of the distribution transformer; wherein the real-time operating data includes: current, voltage and power; According to the real-time operation data and the preset three-phase imbalance evaluation index, the three-phase imbalance evaluation index value corresponding to each three-phase imbalance evaluation index is calculated, and then the three-phase imbalance degree of the distribution transformer is evaluated according to each of the three-phase imbalance evaluation index values, and a corresponding three-phase imbalance alarm is generated according to the three-phase imbalance degree; wherein the three-phase imbalance evaluation index includes: imbalance degree, negative sequence current proportion and zero sequence current; Acquire temperature data collected by internal sensors of the distribution transformer; wherein the temperature data includes: winding temperature and oil temperature; According to the real-time operation data, temperature data and preset load condition assessment indicators, the load condition assessment indicator value corresponding to each load condition assessment indicator is calculated, and then the load overload degree of the distribution transformer is evaluated according to the load condition assessment indicator value, and a corresponding load overload alarm is generated according to the load overload degree; wherein the load condition assessment indicators include: load rate, capacity utilization, winding temperature, oil temperature, overload duration and load change response time.

2. The method for monitoring power grid operation risk according to claim 1, characterized in that: Before calculating the three-phase imbalance evaluation index value corresponding to each three-phase imbalance evaluation index according to the real-time operation data and the preset three-phase imbalance evaluation index, the method further includes: Obtain output power data of renewable energy power generation; According to the real-time operating data of the distribution transformer and the output power data, with the real-time operating data of the distribution transformer as input and the output power data of the new energy power generation as output, a linear expression between the real-time operating data and the output power data is constructed, and then the correlation between the real-time operating data and the output power data is evaluated according to the linear expression.

3. The method for monitoring power grid operation risk according to claim 2, characterized in that: Before calculating the three-phase imbalance evaluation index value corresponding to each three-phase imbalance evaluation index according to the real-time operation data and the preset three-phase imbalance evaluation index, the method further includes: Acquire the rated parameters of the distribution transformer, and determine the reference load capacity value of the distribution transformer according to the rated parameters; wherein the rated parameters include: rated current, rated voltage and rated power; Normalize the real-time operation data of the distribution transformer and obtain the weight coefficient corresponding to each real-time operation data; According to the weight coefficient corresponding to each real-time operation data, a weighted sum calculation is performed on each real-time operation data to obtain a corresponding load capacity evaluation value, and then the load capacity evaluation value is compared with the benchmark load capacity value, and the current load capacity of the distribution transformer is evaluated according to the comparison result.

4. The method for monitoring power grid operation risk according to claim 3, characterized in that: The step of evaluating the three-phase imbalance degree of the distribution transformer according to each of the three-phase imbalance evaluation index values, and generating a corresponding three-phase imbalance alarm according to the three-phase imbalance degree, includes: According to the current load capacity of the distribution transformer, the corresponding three-phase imbalance alarm threshold is obtained; wherein the three-phase imbalance alarm threshold includes: an imbalance alarm threshold, a negative sequence current proportion alarm threshold and a zero sequence current alarm threshold; Comparing each of the three-phase imbalance assessment index values ​​with the corresponding three-phase imbalance alarm thresholds to determine the degree of three-phase imbalance of the distribution transformer; wherein the three-phase imbalance degree includes: mild, moderate and severe; When the three-phase imbalance degree of the distribution transformer is mild, a corresponding mild three-phase imbalance alarm is generated. When the three-phase imbalance degree of the distribution transformer is moderate, a corresponding moderate three-phase imbalance alarm is generated. When the three-phase imbalance degree of the distribution transformer is severe, a corresponding severe three-phase imbalance alarm is generated.

5. The method for monitoring power grid operation risk according to claim 3, characterized in that: The step of evaluating the load overload degree of the distribution transformer according to the load condition evaluation index value, and generating a corresponding load overload alarm according to the load overload degree, includes: According to the current load capacity of the distribution transformer, the corresponding load overload alarm threshold is obtained; Obtaining a weight coefficient corresponding to each of the load condition evaluation indicators, and performing a weighted sum calculation on each of the load condition evaluation indicator values ​​according to the weight coefficient corresponding to each of the load condition evaluation indicators to obtain a corresponding load overload evaluation value; The load overload evaluation value is compared with the load overload alarm threshold value to determine the load overload degree of the distribution transformer; wherein the three-phase imbalance degree includes: light overload, medium overload and heavy overload; When the load overload degree of the distribution transformer is light overload, a corresponding load light overload alarm is generated. When the load overload degree of the distribution transformer is medium overload, a corresponding load medium overload alarm is generated. When the load overload degree of the distribution transformer is heavy overload, a corresponding load heavy overload alarm is generated.

6. The method for monitoring power grid operation risk according to claim 1, characterized in that: Also includes: When the load overload degree is a heavy overload, the real-time operation data of the distribution transformer is input into a preset governance strategy generation model, so that the governance strategy generation model generates and outputs a load heavy overload governance strategy for the distribution transformer according to the real-time operation data of the distribution transformer; The governance strategy parameters in the load overload governance strategy are encoded into a number of chromosomes, and the governance strategy parameters corresponding to each chromosome are evaluated according to a preset fitness function, and the chromosome population is evolved according to the evaluation results to obtain the optimal governance strategy parameter combination, and then the load overload governance strategy is optimized according to the governance strategy parameter combination; Among them, the management strategy generation model is obtained by training a preset neural network model with the historical operation data of the distribution transformer as input and the load overload management strategy corresponding to the historical operation data as output.

7. The method for monitoring power grid operation risk according to claim 1, characterized in that: Also includes: Obtain weather forecast information for the area where the distribution transformer is located; wherein the weather forecast information includes: wind speed, sunshine intensity, and cloud thickness; Inputting the weather forecast information and the real-time operation data into a preset load prediction model, so that the load prediction model predicts the future load condition of the distribution transformer according to the weather forecast information and the real-time operation data, outputs the future load prediction value of the distribution transformer, and then analyzes the possible future operation risks of the distribution transformer according to the load prediction value; The load prediction model is obtained by training a preset LSTM model with historical operation data of the distribution transformer and historical weather forecast information as input and corresponding historical load prediction values ​​as output.

8. A power grid operation risk monitoring device, characterized in that: include: Real-time operation data acquisition module, three-phase imbalance alarm module, temperature data acquisition module and load overload alarm module; The real-time operation data acquisition module is used to acquire the real-time operation data of the distribution transformer; wherein the real-time operation data includes: current, voltage and power; The three-phase unbalance alarm module is used to calculate the three-phase unbalance evaluation index value corresponding to each three-phase unbalance evaluation index according to the real-time operation data and the preset three-phase unbalance evaluation index, and then evaluate the three-phase unbalance degree of the distribution transformer according to each of the three-phase unbalance evaluation index values, and generate a corresponding three-phase unbalance alarm according to the three-phase unbalance degree; wherein the three-phase unbalance evaluation index includes: unbalance degree, negative sequence current proportion and zero sequence current; The temperature data acquisition module is used to acquire temperature data collected by the internal sensor of the distribution transformer; wherein the temperature data includes: winding temperature and oil temperature; The load overload alarm module is used to calculate the load condition assessment index value corresponding to each load condition assessment index according to the real-time operation data, temperature data and preset load condition assessment index, and then evaluate the load overload degree of the distribution transformer according to the load condition assessment index value, and generate a corresponding load overload alarm according to the load overload degree; wherein the load condition assessment indicators include: load rate, capacity utilization, winding temperature, oil temperature, overload duration and load change response time.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the power grid operation risk monitoring method as described in any one of claims 1 to 7 when executing the computer program.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the power grid operation risk monitoring method according to any one of claims 1 to 7.

Images