Method and system for solving problem of low voltage of transformer area

Abstract

The invention relates to the field of power systems, in particular to a method and system for solving the problem of low voltage of a transformer area. The method comprises the following steps: S1, monitoring voltage data of a transformer area line in real time, and generating a low-voltage trigger signal when detecting that a current voltage value is lower than a preset voltage threshold value; s2, calculating an initial distribution proportion of active power and reactive power needing to be adjusted of the energy storage system according to the impedance characteristic parameters; s3, generating a dynamic adjustment strategy of the energy storage system; s4, collecting the deviation between the actual output power and the target value in real time through a feedback loop, and adjusting the pulse width modulation parameter of the inverter according to the deviation so as to correct the output; and S5, voltage data of the transformer area line are obtained again, if the voltage value is recovered to the preset threshold range, an adjustment completion signal is generated, and otherwise, the steps S2 to S4 are repeated based on the updated impedance characteristic parameters. The problems that in the prior art, precision is not high, active power and reactive power cooperative control cannot be achieved, and a feedback correction mechanism is lacked are solved.

Description

Technical Field

[0001] The present invention relates to the field of power systems, and particularly to a method and system for solving the low-voltage problem in a substation area. Background Art

[0002] With the rapid development of the economy, the load of the power system has been continuously increasing. Especially during peak electricity consumption periods, low-voltage problems have occurred in some substation areas, seriously affecting the normal electricity consumption of residents. The low-voltage problem not only causes electrical equipment to malfunction but may also lead to unstable operation of the power system and even damage electrical equipment. Currently, the common method for solving the low-voltage problem in a substation area is to transform the substation area and replace equipment such as transformers. However, this method requires a large investment and has a long construction period, greatly affecting the normal life of residents.

[0003] In the prior art, there have also been some attempts to solve the low-voltage problem through energy storage systems. For example, the patent with the patent number CN112488361A discloses a method and device for predicting low voltage in a substation area based on big data. This method monitors the operation data of the substation area and the electricity consumption data of users, and uses a classification model to classify the supply voltage level to predict the low-voltage situation. However, this method mainly focuses on the prediction of low voltage, lacks direct adjustment means for the low-voltage problem, and does not involve the dynamic adjustment strategy of the energy storage system. Therefore, there is an urgent need for a method and system for solving the low-voltage problem in a substation area. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for solving the low-voltage problem in a substation area to solve the problems of low adjustment accuracy, inability to achieve coordinated control of active power and reactive power, and lack of feedback correction mechanism in the prior art.

[0005] To achieve the above purpose, the following technical solutions are adopted.

[0006] A method for solving the low-voltage problem in a substation area includes the following steps:

[0007] Step S1: Real-time monitor the voltage data of the substation area line. When the detected current voltage value is lower than the preset voltage threshold, generate a low-voltage trigger signal;

[0008] Step S2: Based on the low-voltage trigger signal, obtain the impedance characteristic parameters of the substation area line, and calculate the initial distribution ratio of the active power and reactive power that the energy storage system needs to adjust according to the impedance characteristic parameters;

[0009] Step S3: Generate a dynamic adjustment strategy for the energy storage system according to the initial distribution ratio. The dynamic adjustment strategy includes the coordinated control logic of the active power adjustment component and the reactive power adjustment component, and the coordinated control logic is dynamically adjusted based on the weight relationship between the resistance component and the reactance component in the impedance characteristic parameters;

[0010] Step S4: Based on the dynamic adjustment strategy, control the target active power and target reactive power output by the inverter of the energy storage system, and collect the deviation between the actual output power and the target value in real time through the feedback loop, and adjust the pulse width modulation parameters of the inverter according to the deviation to correct the output.

[0011] Step S5: After the energy storage system outputs power, re-acquire the voltage data of the substation area line. If the voltage value returns to the preset threshold range, generate an adjustment completion signal; otherwise, repeat Steps S2 to S4 based on the updated impedance characteristic parameters.

[0012] Optionally, the generation of the dynamic adjustment strategy in Step S3 specifically includes:

[0013] Step S31: Calculate the weight coefficients of the active power adjustment component and the reactive power adjustment component according to the line resistance component and reactance component in the impedance characteristic parameters.

[0014] Step S32: Generate the dynamic distribution ratios of the active power and reactive power based on the weight coefficients and the remaining capacity of the current energy storage system.

[0015] Step S33: Combine the dynamic distribution ratios with the substation area load prediction model to generate a power adjustment instruction including time series. The power adjustment instruction includes the priority configuration of the active power in different time periods and the reactive power compensation threshold.

[0016] Optionally, the substation area load prediction model is constructed in the following way:

[0017] Collect the historical load data of the substation area, and extract the time characteristics of the load change and the weather correlation characteristics.

[0018] Based on the time characteristics and weather correlation characteristics, train a neural network model to predict the load demand in a preset future time period.

[0019] Fuse the predicted load demand with the real-time monitoring data to dynamically update the load prediction model.

[0020] Optionally, the acquisition of the impedance characteristic parameters in Step S2 includes:

[0021] Step S21: Inject a test signal with a preset frequency into the substation area line, and measure the voltage response and current response of the line; Step S22: Calculate the equivalent resistance value and equivalent reactance value of the line according to the voltage response and current response.

[0022] Step S23: Map the equivalent resistance value and equivalent reactance value into the impedance characteristic parameter matrix, where the dimension of the matrix corresponds one by one to the branch nodes of the substation area topology structure.

[0023] Optionally, the correction of the feedback loop in step S4 includes:

[0024] Step S41: Collect the actual active power and actual reactive power output by the energy storage system, and compare the deviation with the target value;

[0025] Step S42: If the deviation exceeds the preset tolerance range, adjust the pulse width modulation parameters of the inverter according to the deviation direction;

[0026] Step S43: Through the multi-level coordination control module, synchronously adjust the charge and discharge rate of the energy storage system and the output phase angle of the inverter, where the multi-level coordination control module includes a collaborative decision-making mechanism of a local control unit and a cloud optimization unit.

[0027] Optionally, the execution of steps S2 to S4 is also implemented through an edge computing node. The edge computing node is deployed at the substation terminal and performs the following functions: locally cache historical voltage data and impedance parameters, and enable an offline adjustment strategy during communication interruption; real-time compress and transmit key data to the cloud server, and receive the policy update instructions sent from the cloud.

[0028] Optionally, it further includes:

[0029] Step S6: Based on the real-time load data and the remaining capacity of the energy storage system, dynamically adjust the distribution ratio of the active power and reactive power in the dynamic adjustment strategy, so that the matching error between the load demand and the energy storage output power is less than the preset threshold.

[0030] Optionally, in step S4, if the number of times the deviation continuously exceeds the preset tolerance range reaches the threshold, an abnormal alarm signal of the energy storage system is generated, and a backup adjustment strategy switching mechanism is triggered.

[0031] A system for solving the low voltage problem in a substation area includes:

[0032] A monitoring module, configured to obtain the voltage data of the substation area line in real time and generate a low voltage trigger signal;

[0033] An impedance calculation module, configured to calculate the impedance characteristic parameters of the substation area line according to the low voltage trigger signal;

[0034] A strategy generation module, configured to generate a dynamic adjustment strategy for the active power and reactive power of the energy storage system based on the impedance characteristic parameters;

[0035] A control execution module, configured to control the energy storage system to output the target power according to the adjustment strategy, and correct the deviation through a feedback loop;

[0036] A verification module is used to re-detect voltage data after adjustment and trigger iterative adjustment or a completion signal; wherein, the policy generation module and the control execution module are connected through a real-time data bus, and the feedback loop includes a closed-loop communication link of a power sensor and an inverter controller.

[0037] Optionally, it further includes: an edge computing node, deployed at the substation terminal and connected to the monitoring module and the impedance calculation module, for performing the following functions:

[0038] Locally cache historical voltage data and impedance parameters, and enable an offline adjustment strategy during communication interruption;

[0039] Real-time compress and transmit key data to the cloud server, and receive policy update instructions issued by the cloud;

[0040] A multi-source data fusion unit integrates a meteorological data interface and a user electricity consumption behavior database, for optimizing the input parameters of the load prediction model.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The present application proposes a method for solving the low-voltage problem in the substation area. By real-time monitoring the voltage data of the substation area line and dynamically adjusting the active power and reactive power of the energy storage system based on the impedance characteristic parameters, it solves the problems of lack of direct adjustment means and imperfect adjustment strategies in the prior art, and also solves the problems of low adjustment accuracy, inability to achieve coordinated control of active power and reactive power, and lack of feedback correction mechanism in the prior art. The present application can accurately adjust according to the actual situation of the substation area, improving the accuracy and reliability of the adjustment.

[0043] Furthermore, the present application respectively makes detailed definitions on the generation of the dynamic adjustment strategy, the construction of the substation area load prediction model, the acquisition of the impedance characteristic parameters, the correction of the feedback loop, the application of the edge computing node, and the abnormal alarm mechanism, etc. It not only improves the scientificity and adaptability of the adjustment strategy, but also enhances the stability and intelligence level of the system. By constructing the substation area load prediction model, it can more accurately predict the future load demand, thereby optimizing the output power distribution of the energy storage system and further improving the adjustment effect. At the same time, the correction mechanism of the feedback loop and the abnormal alarm mechanism can timely detect and handle the deviation and abnormal situations in the adjustment process, ensuring the stable operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic flow chart of the steps of an embodiment of a method for solving the low-voltage problem in the substation area according to the present invention.

[0045] Figure 2It is a schematic diagram of a module according to an embodiment of a system for solving the low-voltage problem in a power distribution area of the present invention. Detailed implementation manners

[0046] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments may be combined with each other.

[0047] The following detailed descriptions are all exemplary descriptions, aiming to provide further detailed descriptions of the present invention. Unless otherwise specified, all technical terms adopted by the present invention have the same meaning as commonly understood by those of ordinary skill in the art to which the present application belongs. The terms used in the present invention are only for describing specific implementation manners and are not intended to limit the exemplary embodiments according to the present invention.

[0048] Embodiment 1

[0049] As Figure 1 shown, the present invention relates to a method for solving the low-voltage problem in a power distribution area, aiming to efficiently solve the low-voltage problem in the power distribution area through the dynamic regulation strategy of the energy storage system in combination with the impedance characteristic parameters of the power distribution area line. The following will describe in detail the specific implementation manners of the present invention, including the implementation details of each step and module.

[0050] When implementing the method of the present invention, it is first necessary to monitor the voltage data of the power distribution area line in real time. For this purpose, high-precision voltage sensors can be deployed at each key node in the power distribution area (such as the output end of the transformer, the starting point of the branch line, etc.). These sensors can collect the voltage data of the power distribution area line at a high frequency (for example, multiple times per second) and transmit the data to the central control unit. The central control unit performs real-time analysis on the collected voltage data to determine whether the current voltage value is lower than a preset voltage threshold. This voltage threshold can be set according to the specific situation of the power distribution area and the requirements of the electrical equipment, for example, set to 90% of 220V, that is, 198V.

[0051] To ensure the accuracy and reliability of the monitoring data, redundant design can be adopted, that is, multiple voltage sensors are deployed at each key node, and the data of multiple sensors are comprehensively analyzed through data fusion technology. For example, methods such as average value, median value or weighted average value can be used to eliminate the errors or faults that may occur in a single sensor. In addition, parameters such as the rate and duration of voltage drop can be combined to further optimize the generation logic of the trigger signal to ensure that the regulation is only started when a real low-voltage problem occurs.

[0052] When the detected current voltage value is lower than the preset voltage threshold, the central control unit generates a low-voltage trigger signal. This trigger signal is a digital signal used to initiate subsequent adjustment processes. To ensure the accuracy and reliability of the trigger signal, a short delay (e.g., 1 - 2 seconds) can be set to avoid false triggering of the adjustment process due to instantaneous voltage fluctuations. Additionally, parameters such as the rate and duration of voltage drop can be combined to further optimize the generation logic of the trigger signal. For example, if the voltage drop rate exceeds a certain threshold (such as 10V per second) and the duration exceeds a certain set value (such as 5 seconds), it is considered a valid low-voltage event, and thus a low-voltage trigger signal is generated.

[0053] After receiving the low-voltage trigger signal, the system enters the impedance characteristic parameter acquisition stage. Specifically, a test signal with a preset frequency is injected into the distribution network line. This test signal can be a sine wave signal, and its frequency can be selected according to the characteristics of the line, such as 50Hz or 60Hz. At the same time, the voltage response and current response of the line are measured. Through these two response signals, the equivalent resistance value and equivalent reactance value of the line can be calculated using Ohm's law and the impedance formula. The specific calculation formulas are as follows:

[0054] Z = V / I

[0055] Where Z is the impedance, V is the voltage response, and I is the current response. The impedance can be further decomposed into a resistance component and a reactance component:

[0056] R = Re(Z), X = Im(Z)

[0057] The calculated equivalent resistance value and equivalent reactance value are mapped into the impedance characteristic parameter matrix. The dimension of this matrix corresponds one-to-one with the branch nodes of the distribution network topology, so as to comprehensively reflect the impedance characteristics of the distribution network line. For example, for a distribution network with multiple branch nodes, the impedance parameters of each branch node can be stored in the corresponding position of the matrix to form a complete impedance characteristic map.

[0058] Based on the impedance characteristic parameters, calculate the initial allocation ratios of the active power and reactive power that the energy storage system needs to adjust. The calculation of the initial allocation ratios can be carried out according to the weight relationship between the resistance component and the reactance component in the impedance characteristic parameters. For example, if the reactance component is larger, it indicates that the reactive power demand of the line is higher, so the initial allocation ratio of reactive power can be appropriately increased; conversely, if the resistance component is larger, the initial allocation ratio of active power is increased. The specific weight relationship can be obtained through experimental data or simulation analysis and stored in the parameter library of the system for quick call during actual operation.

[0059] To further improve the accuracy of obtaining impedance characteristic parameters, multiple test signal frequencies can be used for measurement, and the measurement results at different frequencies can be comprehensively analyzed. For example, test signals of 50 Hz and 60 Hz can be injected respectively, the corresponding voltage and current responses can be measured respectively, and then the impedance parameters at different frequencies can be weighted and averaged through data fusion technology to obtain more accurate impedance characteristic parameters. In addition, the historical impedance data of the line can be combined, and the current impedance parameters can be corrected and optimized through machine learning algorithms to further improve the accuracy and reliability of the impedance parameters.

[0060] According to the initial allocation ratio, a dynamic regulation strategy for the energy storage system is generated. The dynamic regulation strategy includes the coordinated control logic of the active power regulation component and the reactive power regulation component. The coordinated control logic is dynamically adjusted based on the weight relationship between the resistance component and the reactance component in the impedance characteristic parameters. For example, if it is found that the change in the reactance component is large during the regulation process, it indicates that the reactive power demand of the line has changed. At this time, the reactive power regulation component can be dynamically adjusted to better adapt to the actual demand of the line.

[0061] After the dynamic regulation strategy is generated, the inverter of the energy storage system is controlled to output the target active power and the target reactive power. The output power of the inverter can be accurately controlled through pulse width modulation (PWM) technology. While outputting power, the deviation between the actual output power and the target value is collected in real time through a feedback loop. The feedback loop includes a closed-loop communication link between the power sensor and the inverter controller. The power sensor monitors the actual output power of the energy storage system in real time and transmits the data to the central control unit. The central control unit adjusts the pulse width modulation parameters of the inverter according to the deviation between the actual output power and the target value to correct the output power. If the deviation exceeds the preset tolerance range, the pulse width modulation parameters can be adjusted according to the deviation direction, such as increasing or decreasing the pulse width, so as to adjust the output power.

[0062] In addition, the charge and discharge rate of the energy storage system and the output phase angle of the inverter can be synchronously adjusted through a multi-level coordinated control module. The multi-level coordinated control module includes a collaborative decision-making mechanism of the local control unit and the cloud optimization unit. The local control unit is responsible for real-time monitoring and rapid response, while the cloud optimization unit can optimize and adjust the regulation strategy according to historical data and global information. This collaborative decision-making mechanism can improve the regulation accuracy and stability of the system, ensuring the efficient operation of the energy storage system under various working conditions.

[0063] To further improve the adaptability and flexibility of the dynamic regulation strategy, an adaptive control algorithm can be introduced. For example, an adaptive control algorithm based on fuzzy logic or neural network can automatically adjust the parameters in the dynamic regulation strategy according to real-time monitoring data and historical data, so as to better adapt to the changes of the substation area line. In addition, the distribution ratio of active power and reactive power can be dynamically adjusted by combining real-time load data and the remaining capacity of the energy storage system. In this way, it can be ensured that the matching error between the load demand and the energy storage output power is less than a preset threshold, so as to achieve more accurate voltage regulation.

[0064] After the energy storage system outputs power, the voltage data of the substation area line is obtained again, and it is judged whether the voltage value has returned to the preset threshold range. If the voltage value returns to the normal range, for example, more than 95% of 220V, that is, more than 209V, a regulation completion signal is generated, indicating that this regulation is successful. Otherwise, based on the updated impedance characteristic parameters, repeat the above regulation process, that is, recalculate the initial distribution ratio from step S2, generate a new dynamic regulation strategy, and control the energy storage system to perform a new round of power output.

[0065] To further improve the regulation effect, a dynamic adjustment mechanism can be introduced during the regulation process. For example, the distribution ratio of active power and reactive power in the dynamic regulation strategy is dynamically adjusted according to real-time load data and the remaining capacity of the energy storage system. In this way, it can be ensured that the matching error between the load demand and the energy storage output power is less than a preset threshold, so as to achieve more accurate voltage regulation. In addition, an abnormal alarm mechanism can be set. If the number of times the deviation continuously exceeds the preset tolerance range reaches a threshold, for example, the deviation exceeds the tolerance range continuously 3 times, an abnormal alarm signal of the energy storage system is generated, and a standby regulation strategy switching mechanism is triggered. The standby regulation strategy can include measures such as switching to other energy storage systems and adjusting the transformer tap to ensure the stability of the substation area voltage.

[0066] To further optimize the regulation effect verification process, multi-dimensional evaluation indicators can be introduced. In addition to whether the voltage value has returned to the preset threshold range, indicators such as the voltage fluctuation amplitude, recovery time, and power factor can also be considered. For example, if the voltage returns to the preset threshold range, but the voltage fluctuation amplitude is still large, or the recovery time is too long, it can also be considered that the regulation effect is not ideal, thus triggering further regulation. In addition, the regulation effect can be comprehensively evaluated by combining the user's electricity consumption experience and the operating status of the equipment. For example, through user feedback or the operating data of the equipment, it is judged whether the regulation has truly solved the user's low voltage problem, so as to further optimize the regulation strategy.

[0067] Embodiment 2

[0068] As Figure 2As shown in the figure, the present invention also provides a system for solving the low-voltage problem in a substation area. The system includes multiple modules that work together to implement the above method. The monitoring module is responsible for obtaining the voltage data of the substation area line in real time and generating a low-voltage trigger signal. The impedance calculation module calculates the impedance characteristic parameters of the substation area line according to the low-voltage trigger signal. The strategy generation module generates a dynamic adjustment strategy for the energy storage system based on the impedance characteristic parameters. The control execution module controls the energy storage system to output the target power according to the adjustment strategy and corrects the deviation through a feedback loop. The verification module re-detects the voltage data after adjustment and triggers iterative adjustment or a completion signal.

[0069] The system may further include an edge computing node deployed at the substation area terminal. The edge computing node has a local caching function and can store historical voltage data and impedance parameters. In case of a communication interruption, the edge computing node can enable an offline adjustment strategy to ensure the normal operation of the system. At the same time, the edge computing node can also compress and transmit key data to the cloud server in real time and receive the policy update instructions issued by the cloud. In addition, the system may further include a multi-source data fusion unit that integrates a meteorological data interface and a user electricity consumption behavior database to optimize the input parameters of the load prediction model. In this way, the accuracy of load prediction can be further improved, thereby optimizing the adjustment strategy of the energy storage system.

[0070] To further improve the reliability and stability of the system, redundant design can be introduced into the system. For example, multiple monitoring modules, impedance calculation modules, and control execution modules can be deployed. Through redundant backup, it is ensured that the system can still operate normally when a certain module fails. In addition, a fault diagnosis and self-healing mechanism can be introduced. By monitoring the operating state of the system in real time, faults can be detected and processed in a timely manner, thereby improving the availability and reliability of the system. For example, if a certain monitoring module fails, the system can automatically switch to a standby module, determine the cause of the fault through a fault diagnosis algorithm, and at the same time start the self-healing mechanism to attempt to repair the faulty module.

[0071] In actual implementation, the methods and systems of the present invention can be downscaled and extended according to different application scenarios and requirements. For example, for a small substation area, the system architecture can be simplified by only retaining the core modules to reduce costs and complexity. For a large substation area or a complex power grid structure, more sensors and control units can be added to achieve more refined monitoring and adjustment. In addition, intelligent power grid technology can be combined to integrate the system of the present invention with other management systems of the power grid to achieve collaborative optimization and intelligent operation.

[0072] In terms of technical features, the method and system of the present invention can be further optimized and extended. For example, machine learning algorithms can be introduced to optimize the acquisition of impedance characteristic parameters and the generation of dynamic adjustment strategies. Through machine learning algorithms, the system can automatically learn and adapt to the changes in the substation area lines, thereby improving the accuracy and stability of adjustment. In addition, the Internet of Things technology can be combined to achieve remote monitoring and management of the energy storage system and the substation area lines, improving the operation efficiency and management level of the system.

[0073] To further improve the intelligence level of the system, artificial intelligence technology can be introduced. For example, through deep learning algorithms, analyze the historical load data, voltage data, and impedance data of the substation area to predict future load demands and voltage change trends, and thus adjust the adjustment strategy of the energy storage system in advance. In addition, natural language processing technology can be combined to achieve automatic fault diagnosis and user interaction of the system. For example, through speech recognition and speech synthesis technologies, users can query the operating status of the system through voice commands, and the system can also report fault information and adjustment results to users through voice feedback.

[0074] In summary, the present invention provides a method and system for solving the low-voltage problem in the substation area. Through steps such as real-time monitoring, acquisition of impedance characteristic parameters, generation of dynamic adjustment strategies, and power output control, the efficient solution to the low-voltage problem in the substation area is achieved. The method and system of the present invention have the advantages of high adjustment accuracy, strong adaptability, high intelligence level, etc., can effectively improve the power supply quality and stability of the substation area, and have broad application prospects and practical values.

[0075] As is known by technical common sense, the present invention can be implemented through other embodiments that do not depart from its spiritual essence or essential features. Therefore, the above-disclosed embodiments are illustrative in all aspects and are not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are encompassed by the present invention.

Claims

1. A method for solving the low voltage problem in a station area, characterized in that: The following steps are involved: Step S1: monitor the voltage data of the substation line in real time, and generate a low voltage trigger signal when it is detected that the current voltage value is lower than the preset voltage threshold; Step S2: based on the low voltage trigger signal, obtaining the impedance characteristic parameters of the substation line, and calculating the initial distribution ratio of active power and reactive power to be adjusted by the energy storage system according to the impedance characteristic parameters; Step S3: generating a dynamic regulation strategy for the energy storage system according to the initial allocation ratio, wherein the dynamic regulation strategy includes a coordinated control logic of an active power regulation component and a reactive power regulation component, and the coordinated control logic is dynamically adjusted based on a weight relationship between a resistance component and a reactance component in an impedance characteristic parameter; Step S4: Based on the dynamic adjustment strategy, the inverter of the energy storage system is controlled to output the target active power and the target reactive power, and the deviation between the actual output power and the target value is collected in real time through the feedback loop, and the pulse width modulation parameters of the inverter are adjusted according to the deviation to correct the output; Step S5: After the energy storage system outputs power, the voltage data of the substation line is reacquired. If the voltage value is restored to the preset threshold range, an adjustment completion signal is generated, otherwise steps S2 to S4 are repeated based on the updated impedance characteristic parameters.

2. A method for solving the low voltage problem in a transformer area according to claim 1, characterized in that: The generation of the dynamic adjustment strategy in step S3 specifically includes: Step S31: Calculating the weight coefficients of the active power regulation component and the reactive power regulation component according to the line resistance component and the reactance component in the impedance characteristic parameter; Step S32: generating a dynamic allocation ratio of active power and reactive power based on the weight coefficient and the remaining capacity of the current energy storage system; Step S33: Combine the dynamic allocation ratio with the load forecasting model of the substation to generate a power regulation instruction including a time series, wherein the power regulation instruction includes an active power priority configuration and a reactive power compensation threshold for each time period.

3. A method for solving the low voltage problem in a transformer area according to claim 2, characterized in that: The load forecasting model of the substation is constructed in the following way: Collect historical load data of the substation area and extract the time characteristics and weather-related characteristics of load changes; Based on time characteristics and weather-related characteristics, a neural network model is trained to predict load demand in future preset periods; The predicted load demand is integrated with the real-time monitoring data to dynamically update the load forecasting model.

4. A method for solving the low voltage problem in a transformer area according to claim 1, characterized in that: The acquisition of impedance characteristic parameters in step S2 includes: Step S21: injecting a test signal of a preset frequency into the area line, and measuring the voltage response and current response of the line; Step S22: Calculating the equivalent resistance and equivalent reactance of the circuit according to the voltage response and the current response; Step S23: Mapping the equivalent resistance value and the equivalent reactance value into an impedance characteristic parameter matrix, wherein the dimension of the matrix corresponds one-to-one to the branch nodes of the substation topology structure.

5. The method for solving the low voltage problem in the substation area according to claim 1, characterized in that: The correction of the feedback loop in step S4 includes: Step S41: collecting the actual active power and actual reactive power output by the energy storage system, and comparing the deviations with the target values; Step S42: if the deviation exceeds a preset tolerance range, adjusting the pulse width modulation parameters of the inverter according to the deviation direction; Step S43: Synchronously adjust the charge and discharge rate of the energy storage system and the inverter output phase angle through a multi-level coordinated control module, wherein the multi-level coordinated control module includes a collaborative decision-making mechanism of a local control unit and a cloud optimization unit.

6. A method for solving the low voltage problem in a transformer area according to claim 1, characterized in that: The execution of steps S2 to S4 is also implemented through edge computing nodes, which are deployed at the substation terminal and perform the following functions: locally cache historical voltage data and impedance parameters, and enable offline adjustment strategies when communication is interrupted; compress and transmit key data to the cloud server in real time, and receive strategy update instructions issued by the cloud.

7. A method for solving the low voltage problem in a transformer area according to claim 1, characterized in that: Also includes: Step S6: Based on the real-time load data and the remaining capacity of the energy storage system, dynamically adjust the allocation ratio of active power and reactive power in the dynamic regulation strategy so that the matching error between the load demand and the energy storage output power is less than a preset threshold.

8. The method for solving the low voltage problem in the substation area according to claim 1, characterized in that: In step S4, if the number of times the deviation exceeds the preset tolerance range continuously reaches a threshold, an energy storage system abnormality alarm signal is generated and a standby regulation strategy switching mechanism is triggered.

9. A system for solving low voltage problems in a transformer area, based on a method for solving low voltage problems in a transformer area according to any one of claims 1 to 8, characterized in that: include: Monitoring module, used to obtain voltage data of the substation line in real time and generate low voltage trigger signal; An impedance calculation module, used to calculate the impedance characteristic parameters of the substation line according to the low voltage trigger signal; A strategy generation module, used to generate a dynamic regulation strategy for active power and reactive power of an energy storage system based on the impedance characteristic parameters; A control execution module, used to control the energy storage system to output the target power according to the regulation strategy and correct the deviation through a feedback loop; A verification module is used to re-detect voltage data after adjustment and trigger iterative adjustment or completion signal; wherein the strategy generation module is connected to the control execution module through a real-time data bus, and the feedback loop includes a closed-loop communication link between the power sensor and the inverter controller.

10. The system according to claim 9, characterized in that It also includes an edge computing node, which is deployed at the station terminal and connected to the monitoring module and the impedance calculation module to perform the following functions: Locally cache historical voltage data and impedance parameters, and enable offline adjustment strategies when communication is interrupted; Real-time compression and transmission of key data to cloud servers, and receiving policy update instructions from the cloud; The multi-source data fusion unit integrates the meteorological data interface and the user electricity consumption behavior database to optimize the input parameters of the load forecasting model.

Images